DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claims 1-20 are the currently pending claims hereby under examination.
Claim Objections
Claims 10, 13, 17-18, and 20 are objected to because of the following informalities:
In claim 10, line 8: "the operations further comprising" is grammatically inconsistent with "operations" and should be revised to "the operations further comprise”;
In claim 13, line 2: “that receives wirelessly the sensor data” should be revised to “that wirelessly receives the sensor data";
In claim 17, lines 5-6: "wherein inputting the PPG sensor data into the at least one computational model, further comprising inputting the additional sensor data into the at least one computational model" is grammatically incomplete and has an antecedent issue since PPG has not been previously introduced and should be revised to "wherein inputting the received sensor data into the at least one computational model further comprises inputting the additional sensor data into the at least one computational model";
In claim 18, line 2: "sending wirelessly the BP value" should be revised to "wirelessly sending the BP value"; and
In claim 20, lines 1-2: "the operation of performing at least one action comprising" is grammatically inconsistent and should be revised to "wherein performing the at least one action comprises”.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 13 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as failing to set forth the subject matter which the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the applicant regards as the invention.
Claim 13 recites "at least one wearable computing device included with at least one of the one or more sensor devices mounted on the person" in lines 6-7. It is unclear whether the wearable computing device is physically part of one of the sensor devices, merely associated with one of the sensor devices, attached to one of the sensor devices, or simply worn together with one of the sensor devices. The phrase "included with" permits multiple reasonable interpretations regarding the structural relationship between the wearable computing device and the sensor device. The Examiner is interpreting "included with at least one of the one or more sensor devices mounted on the person" under a broadest reasonable interpretation (BRI) to mean that the wearable computing device is physically part of, attached to, or otherwise associated with at least one sensor device mounted on the person. However, because the claim language does not clearly define the required relationship, the scope of the claim is indefinite under 35 U.S.C. § 112(b).
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception, i.e., an abstract idea, without significantly more. Claims 1-20 are directed to receiving physiological sensor data, processing the physiological sensor data using at least one computational model to obtain an indicated blood pressure value, and performing an action based on the indicated blood pressure value. Claims 1-20 do not include additional elements that integrate the exception into a practical application or that are sufficient to amount to significantly more than the judicial exception for the reasons provided below which are in line with the 2014 Interim Guidance on Patent Subject Matter Eligibility (Federal Register, Vol. 79, No. 241, p. 74618, December 16, 2014), the July 2015 Update on Subject Matter Eligibility (Federal Register, Vol. 80, No. 146, p. 45429, July 30, 2015), the May 2016 Subject Matter Eligibility Update (Federal Register, Vol. 81, No. 88, p. 27381, May 6, 2016), and the 2019 Revised Patent Subject Matter Eligibility Guidance (Federal Register, Vol. 84, No. 4, page 50, January 7, 2019). This analysis also accounts for Ex Parte Desjardins, Appeal No. 2024-000567 (PTAB Sept. 26, 2025, Appeals Review Panel Decision) (precedential), as reflected in the USPTO's update to MPEP §§ 2106.04(d) and 2106.05(a).
The analysis of claim 1 is as follows:
Step 1: Claim 1 is drawn to a process.
Step 2A - Prong One: Claim 1 recites an abstract idea. In particular, claim 1 recites the following limitations:
[A1] inputting, by the computing device, the received sensor data into at least one computational model;
[B1] receiving, by the computing device, an output of the at least one computational model indicative of a blood pressure (BP) value.
These elements [A1]-[B1] of claim 1 are drawn to an abstract idea because they recite a mathematical concept, namely applying a computational model to physiological sensor data to produce a blood-pressure value. Although claim 1 does not recite a specific equation on its face, the claim's recitation of a "computational model" is read in light of the specification, which describes the model as including mathematical, statistical, heuristic, simulation, combinational, machine-learning, and neural-network models, including trained models, regression-type analysis, optimized model parameters/features, joint optimized models, separate optimized models, and aggregation of outputs. Thus, claim 1 recites using a mathematical/statistical/computational model to calculate, estimate, predict, or otherwise determine BP from physiological sensor information. See, e.g., Spec. ¶¶[0020]-[0021], [0044]-[0048], [0056]-[0070].
Additionally, to the extent the above model operation is not treated as a mathematical concept, the claim alternatively recites a mental process because it is directed to evaluating information, namely physiological sensor information, and determining a BP value from that information, which is an observation, evaluation, judgment, or determination that can be performed mentally or with pen and paper at a high level of generality. See MPEP 2106.04(a)(2)(III).
Step 2A - Prong Two: Claim 1 recites the following limitations that are beyond the judicial exception:
[A2] receiving, by a computing device, sensor data from at least one of a photoplethysmographic (PPG) sensor, an electrocardiogram (ECG) sensor, a ballistocardiogram (BCG) sensor, or a microphone;
[B2] performing, by the computing device, at least one action based on the indicated BP value.
These elements [A2]-[B2] of claim 1 do not integrate the exception into a practical application of the exception. In particular, the element [A2] is merely insignificant extra-solution activity, i.e., mere data gathering at a high level of generality. See MPEP 2106.04(d) and MPEP 2106.05(g). Claim 1 does not incorporate any of the PPG sensor, ECG sensor, BCG sensor, or microphone as a positively recited structural component of the claimed method. Rather, claim 1 merely identifies the type or source of data received by the computing device for use in the abstract model-based analysis. The recitation of physiological sensor data also merely links the use of the judicial exception to a particular technological environment or field of use, namely physiological monitoring and blood pressure estimation. See MPEP 2106.05(h).
The recitation of a computing device in claim 1 also does not integrate the exception into a practical application. The computing device is recited at a high level of generality and is used only to receive sensor data, input the sensor data into a computational model, receive the output of the computational model, and perform an action based on the output. Thus, the computing device merely implements the abstract idea on a generic computer, or merely uses a computer as a tool to perform the abstract idea. See MPEP 2106.04(d) and MPEP 2106.05(f).
The element [B2] also does not integrate the exception into a practical application. The Examiner has considered the recited action/output limitations, including presenting or displaying the BP value, initiating an alert, sending the BP value to another device, and/or performing further processing. These limitations are additional claim elements beyond the model-based determination of the BP value. However, these elements merely present, communicate, or make generic downstream use of the result of the abstract model-based BP determination after the BP value has been generated. The claim does not recite a particular display configuration, alert-control technique, communication protocol, device-control feedback loop, treatment step, or technological improvement to the display, communication interface, sensor, or computational model. Accordingly, even though the output/action limitations are considered as claim limitations for purposes of prior-art analysis, they amount to insignificant post-solution activity and/or generic instructions to apply or use the result of the abstract idea, and they do not integrate the judicial exception into a practical application.
Further, the Examiner has considered the claim as a whole, including the above-identified additional elements, to determine whether the claim reflects an improvement in the functioning of a computer, an improvement to a machine-learning or computational model itself, or an improvement to another technology or technical field. See MPEP §§ 2106.04(d)(I), 2106.05(a); Ex Parte Desjardins, Appeal No. 2024-000567 (PTAB Sept. 26, 2025, Appeals Review Panel Decision) (precedential). Although the specification has been reviewed for any such technological improvement, claim 1 does not recite a particular solution to a technological problem or a particular way to achieve a technological improvement. Rather, claim 1 uses a computing device and a computational model as tools to receive physiological sensor data, process or analyze the sensor data, and output a blood pressure value. The claim does not recite specific components or steps that improve how the computing device operates, how the computational model is trained or functions, how the physiological sensors operate, or how blood-pressure-monitoring technology is improved. Therefore, when evaluated as a whole and without ignoring the individual claim limitations, claim 1 does not integrate the judicial exception into a practical application.
Step 2B: Claim 1 does not recite additional elements that amount to significantly more than the judicial exception itself. In particular, the recitation of a computing device does not qualify as significantly more because the computing device is recited at a high level of generality and performs only generic computer functions, including receiving data, inputting data into a computational model, receiving an output, and performing an action based on the output.
The recitation of sensor data from at least one of a PPG sensor, an ECG sensor, a BCG sensor, or a microphone also does not qualify as significantly more because this limitation merely describes the nature or source of the data received by the computing device. Claim 1 does not recite any particular sensor structure, sensor arrangement, sensor-control technique, sampling technique, or signal-acquisition improvement. Rather, the sensor data is merely gathered for use in the abstract model-based BP estimation.
Further, the limitation of performing at least one action based on the indicated BP value does not qualify as significantly more because it is recited generically and merely appends insignificant post-solution activity to the abstract idea. The claim does not require a particular medical treatment, a particular control of a medical device, a particular change to sensor operation, or any other specific technological operation based on the indicated BP value. Instead, the action may be merely displaying, alerting, transmitting, or further processing the BP value. Although such output/action limitations must be addressed as claim limitations under the prior-art statutes, they do not supply an inventive concept for purposes of 35 U.S.C. 101 because they only use generic device functionality to present, communicate, or make downstream use of the result of the abstract model-based analysis.
In view of the above, the additional elements individually do not integrate the exception into a practical application and do not amount to significantly more than the above judicial exception. Looking at the limitations as an ordered combination, that is, as a whole, adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer, improves the operation of a computational model, improves the operation of a physiological sensor, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements includes a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of claim 1 merely provide conventional computer implementation of model-based data analysis, i.e., the computing device is simply used as a tool to perform the abstract idea.
Claims 2-6 depend from claim 1 and recite the same abstract idea as claim 1. Claims 2-4 merely further specify the computational-model arrangement, including a joint computational model, separate sensor-specific models, and aggregation of model outputs. Claims 5 and 6 merely add additional physiological analysis and additional information, such as resistance or compliance, provided to the computational model. These limitations further limit the abstract model-based BP estimation itself and do not recite a particular improvement to the computing device, sensors, computational model, or BP-monitoring technology.
Claim 7 recites presenting the BP value on a display, initiating an alert, sending the BP value to another device, displaying the BP value, or further processing the BP value. These limitations define possible downstream uses or presentations of the BP value. They do not change how the sensor data are processed by the computational model, do not improve operation of the computing device or sensor, and do not require a particular technological implementation of the display, alert, transmission, or further processing. Although these limitations are concrete claim limitations for purposes of prior-art analysis, they merely present, communicate, or make generic downstream use of the result of the abstract analysis and therefore constitute insignificant post-solution activity and/or generic instructions to apply or use the result of the abstract idea.
Looking at the limitations of claims 2-7 as an ordered combination in conjunction with claim 1, that is, as a whole, adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer, improves the operation of a computational model, improves the operation of a physiological sensor, or improves any other technology. Rather, the collective functions merely provide conventional computer implementation of model-based data analysis and generic output or use of the resulting BP value.
The analysis of claim 8 is as follows:
Step 1: Claim 8 is drawn to a machine.
Step 2A - Prong One: Claim 8 recites an abstract idea. In particular, claim 8 recites the following limitations:
[A1] inputting, by the one or more processors, the received sensor data into at least one computational model; and
[B1] receiving, by the one or more processors, an output of the at least one computational model indicative of a blood pressure (BP) value.
These elements [A1]-[B1] of claim 8 are drawn to an abstract idea because they recite a mathematical concept, namely applying a computational model to physiological sensor data to produce a blood-pressure value. Although claim 8 does not recite a specific equation on its face, the claim's recitation of a "computational model" is read in light of the specification, which describes the model as including mathematical, statistical, heuristic, simulation, combinational, machine-learning, and neural-network models, including trained models, regression-type analysis, optimized model parameters/features, joint optimized models, separate optimized models, and aggregation of outputs. Thus, claim 8 recites using a mathematical/statistical/computational model to calculate, estimate, predict, or otherwise determine BP from physiological sensor information. See, e.g., Spec. ¶¶[0020]-[0021], [0044]-[0048], [0056]-[0070].
Additionally, to the extent the above model operation is not treated as a mathematical concept, the claim alternatively recites a mental process because it is directed to evaluating information, namely physiological sensor information, and determining a BP value from that information, which is an observation, evaluation, judgment, or determination that can be performed mentally or with pen and paper at a high level of generality. See MPEP 2106.04(a)(2)(III).
Step 2A - Prong Two: Claim 8 recites the following limitations that are beyond the judicial exception:
[A2] A computing device comprising: one or more processors configured by executable instructions to perform operations comprising:
[B2] receiving, by the one or more processors, sensor data from at least one of a photoplethysmographic (PPG) sensor, an electrocardiogram (ECG) sensor, a ballistocardiogram (BCG) sensor, or a microphone; and
[C2] performing, by the one or more processors, at least one action based on the indicated BP value.
These elements [A2]-[C2] of claim 8 do not integrate the exception into a practical application of the exception. In particular, the element [A2] merely implements the abstract idea on generic processor-based computing hardware, or merely uses a computer as a tool to perform the abstract idea. See MPEP 2106.04(d) and MPEP 2106.05(f). The computing device, processors, and executable instructions are recited at a high level of generality and are used only to receive sensor data, input the sensor data into a computational model, receive the output of the computational model, and perform an action based on the output.
The element [B2] is merely insignificant extra-solution activity, i.e., mere data gathering at a high level of generality. See MPEP 2106.04(d) and MPEP 2106.05(g). Claim 8 does not positively recite any of the PPG sensor, ECG sensor, BCG sensor, or microphone as a structural component of the computing device. Rather, claim 8 merely identifies the type or source of data received by the processors for use in the abstract model-based analysis. The recitation of physiological sensor data also merely links the use of the judicial exception to a particular technological environment or field of use, namely physiological monitoring and blood pressure estimation. See MPEP 2106.05(h).
The element [C2] also does not integrate the exception into a practical application. The Examiner has considered the recited action/output limitations, including presenting or displaying the BP value, initiating an alert, sending the BP value to another device, and/or performing further processing. These limitations are additional claim elements beyond the model-based determination of the BP value. However, these elements merely present, communicate, or make generic downstream use of the result of the abstract model-based BP determination after the BP value has been generated. The claim does not recite a particular display configuration, alert-control technique, communication protocol, device-control feedback loop, treatment step, or technological improvement to the display, communication interface, sensor, or computational model. Accordingly, even though the output/action limitations are considered as claim limitations for purposes of prior-art analysis, they amount to insignificant post-solution activity and/or generic instructions to apply or use the result of the abstract idea, and they do not integrate the judicial exception into a practical application.
Further, the Examiner has considered the claim as a whole, including the above-identified additional elements, to determine whether the claim reflects an improvement in the functioning of a computer, an improvement to a machine-learning or computational model itself, or an improvement to another technology or technical field. See MPEP §§ 2106.04(d)(I), 2106.05(a); Ex Parte Desjardins, Appeal No. 2024-000567 (PTAB Sept. 26, 2025, Appeals Review Panel Decision) (precedential). Although the specification has been reviewed for any such technological improvement, claim 8 does not recite a particular solution to a technological problem or a particular way to achieve a technological improvement. Rather, claim 8 uses a computing device, processors, executable instructions, and a computational model as tools to receive physiological sensor data, process or analyze the sensor data, and output a blood pressure value. The claim does not recite specific components or steps that improve how the computing device operates, how the processors operate, how the computational model is trained or functions, how the physiological sensors operate, or how blood-pressure-monitoring technology is improved. Therefore, when evaluated as a whole and without ignoring the individual claim limitations, claim 8 does not integrate the judicial exception into a practical application.
Step 2B: Claim 8 does not recite additional elements that amount to significantly more than the judicial exception itself. In particular, the recitation of a computing device comprising one or more processors configured by executable instructions does not qualify as significantly more because the computing device and processors are recited at a high level of generality and perform only generic computer functions, including receiving data, inputting data into a computational model, receiving an output, and performing an action based on the output.
The recitation of sensor data from at least one of a PPG sensor, an ECG sensor, a BCG sensor, or a microphone also does not qualify as significantly more because this limitation merely describes the nature or source of the data received by the processors. Claim 8 does not recite any particular sensor structure, sensor arrangement, sensor-control technique, sampling technique, or signal-acquisition improvement. Rather, the sensor data is merely gathered for use in the abstract model-based BP estimation.
Further, the limitation of performing at least one action based on the indicated BP value does not qualify as significantly more because it is recited generically and merely appends insignificant post-solution activity to the abstract idea. The claim does not require a particular medical treatment, a particular control of a medical device, a particular change to sensor operation, or any other specific technological operation based on the indicated BP value. Instead, the action may be merely displaying, alerting, transmitting, or further processing the BP value. Although such output/action limitations must be addressed as claim limitations under the prior-art statutes, they do not supply an inventive concept for purposes of 35 U.S.C. 101 because they only use generic device functionality to present, communicate, or make downstream use of the result of the abstract model-based analysis.
In view of the above, the additional elements individually do not integrate the exception into a practical application and do not amount to significantly more than the above judicial exception. Looking at the limitations as an ordered combination, that is, as a whole, adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer, improves the operation of a computational model, improves the operation of a physiological sensor, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements includes a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of claim 8 merely provide conventional computer implementation of model-based data analysis, i.e., the computing device and processors are simply used as tools to perform the abstract idea.
Claims 9-12 depend from claim 8 and recite the same abstract idea as claim 8. Claims 9 and 10 merely further specify the computational-model arrangement, including a joint computational model, separate sensor-specific models, and aggregation of model outputs. Claims 11 and 12 merely add additional physiological analysis and additional information, such as resistance or compliance, provided to the computational model. These limitations further limit the abstract model-based BP estimation itself and do not recite a particular improvement to the computing device, sensors, computational model, or BP-monitoring technology.
Claim 13 recites a mobile computing device receiving sensor data wirelessly from sensor devices mounted on a person and sending the BP value to at least one wearable computing device. These limitations are concrete limitations for purposes of prior-art analysis, but for 35 U.S.C. 101 they merely provide a generic mobile/wearable communication environment and generic wireless transmission of sensor data or the resulting BP value. The claim does not recite a particular wireless protocol improvement, network improvement, sensor improvement, device-control feedback loop, or improvement to operation of the mobile or wearable computing devices. Accordingly, these communication limitations do not integrate the abstract idea into a practical application and do not add significantly more than the judicial exception.
Claim 14 recites a wearable computing device included in a finger-mountable device having the PPG sensor. This limitation merely provides a conventional wearable/finger-mounted data-acquisition environment for the abstract model-based BP estimation. Finger-site and finger-mounted PPG sensing hardware was well-understood, routine, and conventional in the wearable physiological monitoring field. Tamura et al., Wearable Photoplethysmographic Sensors - Past and Present, Electronics 3(2):282-302 (2014), states that "Commercial clinical PPG sensors commonly use the finger, earlobe and forehead," that "The most common commercially available PPG sensor is based on finger measurement sites," and that "Finger sites are easily accessed and provide good signal for PPG sensor probes" (Tamura, section 3.1). Tamura also states that "a ring sensor can be attached to the base of the finger" and that "Data from the ring sensor are sent to a computer via a radiofrequency transmitter" (Tamura, section 3.1, Fig. 4). Charlton and Marozas, Wearable Photoplethysmography Devices, in Photoplethysmography, Kyriacou and Allen, Eds., Elsevier (2021), states that "A wide range of PPG-based wearables are now commercially available," that "Smart rings are now commercially available which acquire PPG signals at the finger," and that "Pulse oximeters typically acquire transmission PPG signals at the finger" (Charlton and Marozas, sections 2 and 2.1.1). Thus, claim 14 does not recite a particular nonconventional finger-mounted structure, optical configuration, sampling-control technique, signal-processing technique, or device-control operation that improves the finger-mountable device, PPG sensor, or BP-monitoring technology.
Looking at the limitations of claims 9-14 as an ordered combination in conjunction with claim 8, that is, as a whole, adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer, improves the operation of a computational model, improves the operation of a physiological sensor, improves wireless communication, or improves any other technology. Rather, the collective functions merely provide conventional computer implementation of model-based data analysis, generic wearable/finger-mounted data acquisition, and generic output or communication of the resulting BP value.
The analysis of claim 15 is as follows:
Step 1: Claim 15 is drawn to a machine.
Step 2A - Prong One: Claim 15 recites an abstract idea. In particular, claim 15 recites the following limitations:
[A1] inputting, by the one or more processors, the received sensor data into at least one computational model; and
[B1] receiving, by the one or more processors, an output of the at least one computational model indicative of a blood pressure (BP) value.
These elements [A1]-[B1] of claim 15 are drawn to an abstract idea because they recite a mathematical concept, namely applying a computational model to physiological sensor data to produce a blood-pressure value. Although claim 15 does not recite a specific equation on its face, the claim's recitation of a "computational model" is read in light of the specification, which describes the model as including mathematical, statistical, heuristic, simulation, combinational, machine-learning, and neural-network models, including trained models, regression-type analysis, optimized model parameters/features, joint optimized models, separate optimized models, and aggregation of outputs. Thus, claim 15 recites using a mathematical/statistical/computational model to calculate, estimate, predict, or otherwise determine BP from physiological sensor information. See, e.g., Spec. ¶¶[0020]-[0021], [0044]-[0048], [0056]-[0070].
Additionally, to the extent the above model operation is not treated as a mathematical concept, the claim alternatively recites a mental process because it is directed to evaluating information, namely physiological sensor information, and determining a BP value from that information, which is an observation, evaluation, judgment, or determination that can be performed mentally or with pen and paper at a high level of generality. See MPEP 2106.04(a)(2)(III).
Step 2A - Prong Two: Claim 15 recites the following limitations that are beyond the judicial exception:
[A2] A finger-mountable device comprising:
[B2] at least one photoplethysmographic (PPG) sensor;
[C2] a communication interface; and
[D2] one or more processors configured by executable instructions to perform operations comprising:
[E2] receiving, by the one or more processors, sensor data from at least the PPG sensor; and
[F2] performing, by the one or more processors, at least one action based on the indicated BP value.
These elements [A2]-[F2] of claim 15 do not integrate the exception into a practical application of the exception. In particular, the elements [A2]-[D2] are recited at a high level of generality and merely provide a generic physical environment, generic data source, generic communication hardware, and generic computer hardware for performing the abstract model-based BP estimation. The claim does not recite a particular nonconventional finger-mounted sensor arrangement, optical configuration, signal-acquisition technique, sampling-control technique, model-training technique, or device-control operation that improves the finger-mountable device, the PPG sensor, the communication interface, or BP-monitoring technology.
The element [E2] is merely insignificant extra-solution activity, i.e., mere data gathering at a high level of generality. See MPEP 2106.04(d) and MPEP 2106.05(g). The PPG sensor merely gathers physiological data for use in the abstract model-based analysis. The elements [A2]-[D2] also merely link the use of the judicial exception to a particular technological environment or field of use, namely wearable/finger-based physiological monitoring. See MPEP 2106.05(h). The one or more processors configured by executable instructions merely implement the abstract idea using generic computer hardware. See MPEP 2106.04(d) and MPEP 2106.05(f).
The element [F2] also does not integrate the exception into a practical application. The Examiner has considered the recited action/output limitations. The claim does not require a particular medical treatment, a particular control of a medical device, a particular change to operation of the PPG sensor, or a particular control of the finger-mountable device based on the indicated BP value. Instead, the action may be no more than outputting, displaying, alerting, transmitting, or further processing the BP value. These output/action limitations are considered as claim limitations for purposes of prior-art analysis, but for 35 U.S.C. 101 they merely present, communicate, or make generic downstream use of the result of the abstract model-based BP determination after the BP value has been generated. The claim does not recite a particular display configuration, alert-control technique, communication protocol, device-control feedback loop, treatment step, or technological improvement to the display, communication interface, PPG sensor, finger-mountable device, or computational model. Accordingly, the output/action limitations constitute insignificant post-solution activity and/or generic instructions to apply or use the result of the abstract idea.
Further, the Examiner has considered the claim as a whole, including the above-identified additional elements, to determine whether the claim reflects an improvement in the functioning of a computer, an improvement to a machine-learning or computational model itself, or an improvement to another technology or technical field. See MPEP §§ 2106.04(d)(I), 2106.05(a); Ex Parte Desjardins, Appeal No. 2024-000567 (PTAB Sept. 26, 2025, Appeals Review Panel Decision) (precedential). Although the specification has been reviewed for any such technological improvement, claim 15 does not recite a particular solution to a technological problem or a particular way to achieve a technological improvement. Rather, claim 15 uses a finger-mountable device, a PPG sensor, a communication interface, processors, and a computational model as tools to collect PPG data, process or analyze the PPG data, and output a blood pressure value. The claim does not recite specific components or operations that improve how the processors operate, how the computational model is trained or functions, how the PPG sensor operates, how the communication interface operates, or how the finger-mountable device improves BP-monitoring technology. Therefore, when evaluated as a whole and without ignoring the individual claim limitations, claim 15 does not integrate the judicial exception into a practical application.
Step 2B: Claim 15 does not recite additional elements that amount to significantly more than the judicial exception itself. In particular, the finger-mountable device, at least one PPG sensor, communication interface, and one or more processors do not qualify as significantly more because these elements are recited generically and merely perform their ordinary functions of mounting on a finger, sensing PPG data, communicating data, and executing instructions. The claim does not recite an unconventional arrangement or operation of these elements that supplies an inventive concept.
Finger-mounted or finger-site PPG sensing hardware, including ring-type PPG sensors and smart rings acquiring PPG signals at the finger, was well-understood, routine, and conventional in the wearable physiological monitoring field, as evidenced by:
Tamura et al. (Tamura et al. ,Wearable Photoplethysmographic Sensors - Past and Present, Electronics 3(2):282-302 (2014)) supports the conventional nature of finger-site/finger-mounted PPG because Tamura expressly states that "Commercial clinical PPG sensors commonly use the finger, earlobe and forehead" (Tamura, section 3.1), and further states that "The most common commercially available PPG sensor is based on finger measurement sites" and "Finger sites are easily accessed and provide good signal for PPG sensor probes" (Tamura, section 3.1). Tamura also identifies ring-type finger PPG hardware, stating that "a ring sensor can be attached to the base of the finger" for beat-to-beat pulsation monitoring and that "Data from the ring sensor are sent to a computer via a radiofrequency transmitter" (Tamura, section 3.1, Fig. 4); and
Charlton and Marozas (Charlton, Peter H. and Vaidotas Marozas. “Wearable photoplethysmography devices.” Photoplethysmography (2022)) Wearable Photoplethysmography Devices, in Photoplethysmography, Kyriacou and Allen, Eds., Elsevier (2021), supports the conventional nature of PPG-based wearables, finger PPG, and smart rings because Charlton and Marozas state that "Wearable photoplethysmography devices are now widely available in a variety of hardware configurations" and that "A wide range of PPG-based wearables are now commercially available" (Charlton and Marozas, sections 1.1 and 2). In the subsection directed to the "Finger" measurement site, Charlton and Marozas further state that "Smart rings are now commercially available which acquire PPG signals at the finger" and that "Pulse oximeters typically acquire transmission PPG signals at the finger" (Charlton and Marozas, section 2.1.1).
Thus, the additional recitation of a finger-mountable device having a PPG sensor, communication interface, and processors merely appends well-understood, routine, and conventional wearable sensor and computing hardware to the abstract idea. The claim does not recite a particular nonconventional finger-mounted structure, optical arrangement, signal-acquisition arrangement, sampling-control technique, signal-processing technique, or device-control operation that would amount to significantly more than the abstract idea.
Further, the limitation of performing at least one action based on the indicated BP value does not qualify as significantly more because it is recited generically and merely appends insignificant post-solution activity to the abstract idea. The claim does not require a particular medical treatment, a particular control of a medical device, a particular change to operation of the PPG sensor, or a particular change to operation of the finger-mountable device. Instead, the action may be merely displaying, alerting, transmitting, or further processing the BP value. Although such output/action limitations must be addressed as claim limitations under the prior-art statutes, they do not supply an inventive concept for purposes of 35 U.S.C. 101 because they only use generic device functionality to present, communicate, or make downstream use of the result of the abstract model-based analysis.
In view of the above, the additional elements individually do not integrate the exception into a practical application and do not amount to significantly more than the above judicial exception. Looking at the limitations as an ordered combination, that is, as a whole, adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer, improves the operation of a computational model, improves the operation of the PPG sensor, improves the operation of the communication interface, or improves any other technology. There is no indication that the combination of elements includes a particular solution to a technological problem or a particular way to achieve a desired technological outcome. Rather, the collective functions of claim 15 merely provide conventional wearable sensor hardware and conventional computer implementation of model-based data analysis, i.e., the finger-mountable device and processors are simply used as tools to perform the abstract idea.
Claims 16 and 17 depend from claim 15 and recite the same abstract idea as claim 15. Claim 16 merely adds additional physiological analysis and additional information, such as resistance or compliance, provided to the computational model. Claim 17 merely adds receiving additional ECG, BCG, or microphone sensor data from other body locations and inputting the additional sensor data into the computational model. These limitations further limit the abstract model-based BP estimation or add data gathering/model-input information and do not recite a particular sensor arrangement, signal-processing technique, model-training technique, or device-control operation that improves the PPG sensor, finger-mountable device, processors, computational model, or BP-monitoring technology.
Claims 18 and 20 recite sending the BP value wirelessly to a mobile device for presentation and/or presenting the BP value on a display. These limitations are concrete limitations for purposes of prior-art analysis, but for 35 U.S.C. 101 they merely communicate or present the result of the abstract model-based BP determination using generic device functionality. The claims do not recite an improvement to wireless communication, display technology, wearable-device operation, sensor operation, or the computational model. Accordingly, these limitations constitute insignificant post-solution activity and/or generic instructions to apply or use the result of the abstract analysis.
Claim 19 recites that the at least one PPG sensor has a sampling rate greater than 1000 Hz. This limitation does not integrate the abstract idea into a practical application because it merely specifies the rate at which physiological data are acquired before being provided to the computational model. The claim does not recite a particular sensor-control technique, signal-processing architecture, sampling-control feedback mechanism, or improvement to operation of the PPG sensor itself. Nor does the claim require that the greater-than-1000-Hz sampling rate be used in a particular way to improve sensor accuracy, reduce noise, reduce processing burden, or otherwise improve operation of a technological system. Accordingly, the limitation amounts to additional data acquisition for use in the abstract model-based BP determination, and it does not integrate the judicial exception into a practical application or amount to significantly more than the judicial exception.
Looking at the limitations of claims 16-20 as an ordered combination in conjunction with claim 15, that is, as a whole, adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer, improves the operation of a computational model, improves the operation of the PPG sensor, improves the operation of the communication interface, improves the operation of the display, or improves any other technology. Rather, the collective functions merely provide conventional finger-mounted sensor hardware, generic computer implementation of model-based data analysis, additional data gathering, and generic output or communication of the resulting BP value.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1 and 8 are rejected under 35 U.S.C. 102(a)(1) as anticipated by Carter et al. (US 2017/0181649 A1), hereafter referred to as Carter.
Regarding Claim 1, Carter teaches a method, comprising: receiving sensor data from at least one of a photoplethysmographic (PPG) sensor, an electrocardiogram (ECG) sensor, a ballistocardiogram (BCG) sensor, or a microphone (Carter, Abstract; FIGS. 1-3; ¶[0038], teaching collecting raw photoplethysmogram (PPG) data and processing the raw data with a biometric engine; ¶[0046], teaching method 100 configured to acquire raw data and/or process raw data to determine blood pressure; ¶[0048]: “collecting raw data 108 comprises recording raw PPG data with one or more devices configured to acquire raw PPG data and/or to process raw PPG data to determine blood pressure”; ¶[0049], teaching a bracelet configured to acquire raw PPG data and/or process raw PPG data to determine blood pressure; ¶¶[0050]-[0051], teaching LEDs and a light sensor for acquiring raw PPG data, wherein Carter teaches receiving sensor data from at least one of the recited sensor types because Carter receives raw PPG data);
inputting the sensor data into at least one computational model (Carter, FIG. 1, depicting raw data 20 processed by signal processing unit 32 into biometric features 36 and further depicting machine learning unit 46 outputting blood pressure results 50; FIG. 2, depicting “modeling with machine learning to determine blood pressure”; ¶[0038], teaching processing raw PPG data with a biometric engine to generate scaled beats and biometric features and processing the scaled beats and biometric features with a blood pressure engine configured to perform beat shape analysis, measure additional shape features, and model with machine learning to determine blood pressure; ¶[0082]: “modeling with machine learning to determine blood pressure 136 comprises using machine learning to develop a predictive model for blood pressure”; ¶[0083], teaching that blood pressure can be modeled as a regression problem and that separate regression models for systolic pressure, diastolic pressure, and/or mean arterial pressure can be developed, wherein Carter teaches inputting sensor data, including PPG-derived biometric and beat-shape data, into at least one computational model);
receiving, as an output from the at least one computational model, a model output indicative of a blood pressure value for a subject (Carter, FIG. 1, depicting machine learning unit 46 outputting blood pressure results 50 including systolic pressure, diastolic pressure, and mean arterial pressure; ¶[0039], teaching modeling with machine learning to determine blood pressure and determining and representing an individual’s blood pressure in a medically accepted standard such as millimeters of mercury; ¶[0082], teaching use of machine learning to develop a predictive model for blood pressure; ¶[0083], teaching regression models for systolic pressure, diastolic pressure, and/or mean arterial pressure, wherein Carter teaches receiving a model output indicative of a BP value, such as systolic pressure, diastolic pressure, and/or mean arterial pressure).
performing at least one action based on the blood pressure value (Carter, ¶[0039], teaching determining and representing an individual’s blood pressure in a medically accepted standard, such as millimeters of mercury; Carter, ¶[0091], teaching correlating blood pressure with hypotension, hypertension, and/or normotension, wherein Carter teaches performing an action based on the BP value by representing the BP value in a medically accepted standard and/or using the BP value to determine or correlate a blood-pressure condition).
Regarding Claim 8, Carter teaches a computing device comprising: one or more processors configured by executable instructions to perform operations comprising: (Carter, FIGS. 1, 2, and 4; ¶[0045], teaching a machine learning unit configured to develop and/or implement a predictive model for blood pressure determination; ¶[0054], teaching an electronic device 301, such as a smartphone, tablet computer, or similar device, configured to receive raw data from bracelet 200; ¶[0055], teaching that electronic device 301 may process at least in part the raw data and may comprise biometric engine 30, wherein Carter teaches the claimed computing device structure for performing BP-estimation operations);
receiving, by the one or more processors, sensor data from at least one of a photoplethysmographic (PPG) sensor, an electrocardiogram (ECG) sensor, a ballistocardiogram (BCG) sensor, or a microphone (Carter, Abstract; FIGS. 1-4; ¶[0046], teaching acquiring raw data and/or processing raw data to determine blood pressure; ¶[0048]: “collecting raw data 108 comprises recording raw PPG data with one or more devices configured to acquire raw PPG data and/or to process raw PPG data to determine blood pressure”; ¶[0049], teaching bracelet 200 configured to acquire raw PPG data and/or process raw PPG data to determine blood pressure; ¶[0050]-[0051], teaching LEDs and light sensor 202 for acquiring raw PPG data; ¶[0054], teaching that raw PPG data collected by light sensor 202 can be input to electronic device 301, wherein Carter teaches receiving, by the computing device/electronic device, sensor data from at least one of the recited sensor types because Carter receives raw PPG data from a PPG sensor);
inputting, by the one or more processors, the received sensor data into at least one computational model (Carter, FIG. 1, depicting raw data 20 processed by signal processing unit 32 into biometric features 36 and further depicting machine learning unit 46 outputting blood pressure results 50; FIG. 2, depicting “modeling with machine learning to determine blood pressure”; ¶[0038], teaching processing raw PPG data with a biometric engine to generate scaled beats and biometric features and processing the scaled beats and biometric features with a blood pressure engine configured to perform beat shape analysis, measure additional shape features, and model with machine learning to determine blood pressure; ¶[0045], teaching that machine learning unit 46 receives mean beat shape data, additional shape features, and biometric features and uses machine learning to develop and/or implement a predictive model for blood pressure determination; ¶[0082], teaching that modeling with machine learning to determine blood pressure comprises using machine learning to develop a predictive model for blood pressure; ¶[0083], teaching that blood pressure can be modeled as a regression problem and that separate regression models for systolic pressure, diastolic pressure, and/or mean arterial pressure can be developed, wherein Carter teaches inputting the received sensor data, including PPG-derived biometric and beat-shape data, into at least one computational model);
receiving, by the one or more processors, an output of the at least one computational model indicative of a blood pressure (BP) value (Carter, FIG. 1, depicting machine learning unit 46 outputting blood pressure results 50 including systolic pressure, diastolic pressure, and mean arterial pressure; ¶[0039], teaching modeling with machine learning to determine blood pressure and determining and representing an individual’s blood pressure in a medically accepted standard such as millimeters of mercury; ¶[0045], teaching that the predictive model for blood pressure determination can be implemented to determine blood pressure results, including systolic pressure, diastolic pressure, and/or mean arterial pressure; ¶[0082]-[0083], teaching use of a predictive model for blood pressure and regression models for systolic pressure, diastolic pressure, and/or mean arterial pressure, wherein Carter teaches receiving a model output indicative of a BP value); and
performing, by the one or more processors, at least one action based on the indicated BP value (Carter, ¶[0039], teaching determining and representing an individual’s blood pressure in a medically accepted standard, such as millimeters of mercury; ¶[0091], teaching correlating blood pressure with hypotension, hypertension, and/or normotension, wherein Carter teaches performing, by processor-implemented BP-estimation operations, an action based on the indicated BP value by representing the BP value in a medically accepted standard and/or using the BP value to determine or correlate a blood-pressure condition).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1 and 8 are rejected, in the alternative, under 35 U.S.C. 103 as unpatentable over Carter et al. (US 2017/0181649 A1), hereafter referred to as Carter, in view of Lusted (US 10,709,339 B1), hereafter referred to as Lusted.
Regarding Claim 1, Carter teaches a method, comprising: receiving sensor data from at least one of a photoplethysmographic (PPG) sensor, an electrocardiogram (ECG) sensor, a ballistocardiogram (BCG) sensor, or a microphone (Carter, Abstract; FIGS. 1-3; ¶[0038], teaching collecting raw photoplethysmogram (PPG) data and processing the raw data with a biometric engine; ¶[0046], teaching method 100 configured to acquire raw data and/or process raw data to determine blood pressure; ¶[0048]: “collecting raw data 108 comprises recording raw PPG data with one or more devices configured to acquire raw PPG data and/or to process raw PPG data to determine blood pressure”; ¶[0049], teaching a bracelet configured to acquire raw PPG data and/or process raw PPG data to determine blood pressure; ¶¶[0050]-[0051], teaching LEDs and a light sensor for acquiring raw PPG data, wherein Carter teaches receiving sensor data from at least one of the recited sensor types because Carter receives raw PPG data);
inputting the sensor data into at least one computational model (Carter, FIG. 1, depicting raw data 20 processed by signal processing unit 32 into biometric features 36 and further depicting machine learning unit 46 outputting blood pressure results 50; FIG. 2, depicting “modeling with machine learning to determine blood pressure”; ¶[0038], teaching processing raw PPG data with a biometric engine to generate scaled beats and biometric features and processing the scaled beats and biometric features with a blood pressure engine configured to perform beat shape analysis, measure additional shape features, and model with machine learning to determine blood pressure; ¶[0082]: “modeling with machine learning to determine blood pressure 136 comprises using machine learning to develop a predictive model for blood pressure”; ¶[0083], teaching that blood pressure can be modeled as a regression problem and that separate regression models for systolic pressure, diastolic pressure, and/or mean arterial pressure can be developed, wherein Carter teaches inputting sensor data, including PPG-derived biometric and beat-shape data, into at least one computational model); and
receiving, as an output from the at least one computational model, a model output indicative of a blood pressure value for a subject (Carter, FIG. 1, depicting machine learning unit 46 outputting blood pressure results 50 including systolic pressure, diastolic pressure, and mean arterial pressure; ¶[0039], teaching modeling with machine learning to determine blood pressure and determining and representing an individual’s blood pressure in a medically accepted standard such as millimeters of mercury; ¶[0082], teaching use of machine learning to develop a predictive model for blood pressure; ¶[0083], teaching regression models for systolic pressure, diastolic pressure, and/or mean arterial pressure, wherein Carter teaches receiving a model output indicative of a BP value, such as systolic pressure, diastolic pressure, and/or mean arterial pressure).
Also regarding claim 1, with respect to performing at least one action based on the blood pressure value, Carter teaches determining and representing an individual’s blood pressure in a medically accepted standard, such as millimeters of mercury (Carter, ¶[0039]), teaching correlating blood pressure with hypotension, hypertension, and/or normotension (Carter, ¶[0091]; wherein Carter teaches performing an action based on the BP value by representing the BP value in a medically accepted standard and/or using the BP value to determine or correlate a blood-pressure condition).
However, to the extent it is argued that Carter does not expressly teach the action as a user-facing output, display, or transmission of the blood-pressure value, Lusted teaches outputting and communicating calculated blood-pressure values. Lusted teaches a wearable biometric sensing ring having a PPG sensor, ECG electrodes, a controller, and programming for receiving PPG and ECG data, converting the PPG and ECG data into digital data, calculating blood pressure from the digital ECG and PPG sensor data, and graphically outputting the calculated BP (Lusted, Abstract). Lusted further teaches that BP calculation algorithms may be implemented on a smartphone, that “the systolic and diastolic BP are displayed,” and that values may be transmitted to the smartphone for display on an app screen (Lusted, col. 10, ll. 1-23). Lusted also teaches wirelessly communicating data relating to BP between the sensing ring and a mobile device for graphic display of BP on the mobile device (Lusted, claim 14).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Carter in view of Lusted to perform the action based on Carter’s determined blood-pressure value as a display, graphical output, or wireless communication of the BP value. The modification would have been feasible because Carter already determines and represents BP values from wearable PPG sensor data using a machine-learning predictive model, and Lusted teaches a known wearable/mobile-device output architecture for displaying and communicating calculated BP values from wearable physiological sensors. The benefit of the combination would have been to provide the subject with a readily accessible indication of Carter’s determined BP value and to support continuous blood-pressure monitoring by displaying or communicating the calculated BP result.
Regarding Claim 8, Carter teaches a computing device comprising: one or more processors configured by executable instructions to perform operations comprising: (Carter, FIGS. 1, 2, and 4; ¶[0045], teaching a machine learning unit configured to develop and/or implement a predictive model for blood pressure determination; ¶[0054], teaching an electronic device 301, such as a smartphone, tablet computer, or similar device, configured to receive raw data from bracelet 200; ¶[0055], teaching that electronic device 301 may process at least in part the raw data and may comprise biometric engine 30, wherein Carter teaches the claimed computing device structure for performing BP-estimation operations);
receiving, by the one or more processors, sensor data from at least one of a photoplethysmographic (PPG) sensor, an electrocardiogram (ECG) sensor, a ballistocardiogram (BCG) sensor, or a microphone (Carter, Abstract; FIGS. 1-4; ¶[0046], teaching acquiring raw data and/or processing raw data to determine blood pressure; ¶[0048]: “collecting raw data 108 comprises recording raw PPG data with one or more devices configured to acquire raw PPG data and/or to process raw PPG data to determine blood pressure”; ¶[0049], teaching bracelet 200 configured to acquire raw PPG data and/or process raw PPG data to determine blood pressure; ¶[0050]-[0051], teaching LEDs and light sensor 202 for acquiring raw PPG data; ¶[0054], teaching that raw PPG data collected by light sensor 202 can be input to electronic device 301, wherein Carter teaches receiving, by the computing device/electronic device, sensor data from at least one of the recited sensor types because Carter receives raw PPG data from a PPG sensor);
inputting, by the one or more processors, the received sensor data into at least one computational model (Carter, FIG. 1, depicting raw data 20 processed by signal processing unit 32 into biometric features 36 and further depicting machine learning unit 46 outputting blood pressure results 50; FIG. 2, depicting “modeling with machine learning to determine blood pressure”; ¶[0038], teaching processing raw PPG data with a biometric engine to generate scaled beats and biometric features and processing the scaled beats and biometric features with a blood pressure engine configured to perform beat shape analysis, measure additional shape features, and model with machine learning to determine blood pressure; ¶[0045], teaching that machine learning unit 46 receives mean beat shape data, additional shape features, and biometric features and uses machine learning to develop and/or implement a predictive model for blood pressure determination; ¶[0082], teaching that modeling with machine learning to determine blood pressure comprises using machine learning to develop a predictive model for blood pressure; ¶[0083], teaching that blood pressure can be modeled as a regression problem and that separate regression models for systolic pressure, diastolic pressure, and/or mean arterial pressure can be developed, wherein Carter teaches inputting the received sensor data, including PPG-derived biometric and beat-shape data, into at least one computational model); and
receiving, by the one or more processors, an output of the at least one computational model indicative of a blood pressure (BP) value (Carter, FIG. 1, depicting machine learning unit 46 outputting blood pressure results 50 including systolic pressure, diastolic pressure, and mean arterial pressure; ¶[0039], teaching modeling with machine learning to determine blood pressure and determining and representing an individual’s blood pressure in a medically accepted standard such as millimeters of mercury; ¶[0045], teaching that the predictive model for blood pressure determination can be implemented to determine blood pressure results, including systolic pressure, diastolic pressure, and/or mean arterial pressure; ¶[0082]-[0083], teaching use of a predictive model for blood pressure and regression models for systolic pressure, diastolic pressure, and/or mean arterial pressure, wherein Carter teaches receiving a model output indicative of a BP value).
Also regarding claim 8, with respect to performing, by the one or more processors, at least one action based on the indicated BP value, Carter teaches determining and representing an individual’s blood pressure in a medically accepted standard, such as millimeters of mercury (Carter, ¶[0039]), teaching correlating blood pressure with hypotension, hypertension, and/or normotension (Carter, ¶[0091]; wherein Carter teaches performing, by processor-implemented BP-estimation operations, an action based on the indicated BP value by representing the BP value in a medically accepted standard and/or using the BP value to determine or correlate a blood-pressure condition)
However, to the extent it is argued that Carter does not expressly teach the action as a user-facing output, display, or transmission of the blood-pressure value, Lusted teaches outputting and communicating calculated blood-pressure values. Lusted teaches a wearable biometric sensing ring having a PPG sensor, ECG electrodes, a controller, and programming for receiving PPG and ECG data, converting the PPG and ECG data into digital data, calculating blood pressure from the digital ECG and PPG sensor data, and graphically outputting the calculated BP (Lusted, Abstract). Lusted further teaches that BP calculation algorithms may be implemented on a smartphone, that “the systolic and diastolic BP are displayed,” and that values may be transmitted to the smartphone for display on an app screen (Lusted, col. 10, ll. 1-23). Lusted also teaches wirelessly communicating data relating to BP between the sensing ring and a mobile device for graphic display of BP on the mobile device (Lusted, claim 14).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Carter in view of Lusted to perform the action based on Carter’s determined blood-pressure value as a display, graphical output, or wireless communication of the BP value. The modification would have been feasible because Carter already determines and represents BP values from wearable PPG sensor data using a machine-learning predictive model, and Lusted teaches a known wearable/mobile-device output architecture for displaying and communicating calculated BP values from wearable physiological sensors. The benefit of the combination would have been to provide the subject with a readily accessible indication of Carter’s determined BP value and to support continuous blood-pressure monitoring by displaying or communicating the calculated BP result.
Claims 2-4, 9, and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Carter et al. (US 2017/0181649 A1), hereinafter referred to as Carter, in view of Lusted (US 10,709,339 B1), hereinafter referred to as Lusted, and further in view of Long et al. (Long, Weicai and Wang, Xingjun, Bpnet: A Multi-Modal Fusion Neural Network for Blood Pressure Estimation Using ECG and PPG. Biomedical Signal Processing and Control, vol. 86, no. 105287, September 2023), hereinafter referred to as Long.
The modified Carter teaches claims 1 and 8 as shown above.
Regarding Claim 2, the modified Carter does not expressly teach wherein the at least one computational model is a joint computational model configured to receive multiple different types of sensor data from multiple different types of sensors, respectively. Rather, the modified Carter teaches determining blood pressure from PPG sensor data using machine learning, including developing and/or implementing a predictive model for blood pressure based on PPG-derived biometric features and beat-shape features (Carter, FIGS. 1-2; ¶[0038], ¶[0045], ¶[0082]-[0083]). However, the modified Carter does not expressly teach that the computational model is a joint computational model configured to receive multiple different types of sensor data from multiple different types of sensors, respectively.
Long, who is also directed to cuffless blood-pressure estimation using physiological sensor data and computational models, teaches a joint computational model configured to receive multiple different types of sensor data from multiple different types of sensors, respectively. Long teaches BPNet, an end-to-end model for blood-pressure estimation using ECG and PPG signals, where the model addresses prior methods that concatenate ECG and PPG without fully capturing their relationship and instead proposes a multi-modal fusion model for BP estimation (Long, Abstract; p. 2, FIG. 1(c)). Long further teaches that preprocessed ECG and PPG signals are fed into BPNet, which includes pre-feature extraction, cross-modal fusion, post-feature extraction, and a multi-tasking module, and that the BPNet model outputs both SBP and DBP (Long, p. 4, FIG. 2; §3.3). Long further teaches that the input consists of a segment of the PPG signal and a segment of the ECG signal, and that PPG and ECG features are fused to achieve multi-modal feature representation for BP estimation (Long, p. 5, FIGS. 4-5; §3.3(1)). Thus, Long teaches a joint computational model configured to receive multiple different types of sensor data, including ECG and PPG sensor data, from multiple different types of sensors.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the modified Carter in view of Long so that the computational model is a joint computational model configured to receive multiple different types of sensor data from multiple different types of sensors, respectively, such as ECG sensor data and PPG sensor data. The modification would have been feasible because the modified Carter already teaches a machine-learning predictive model for determining blood pressure from wearable physiological sensor data, and Long teaches a known BP-estimation neural-network architecture that jointly processes ECG and PPG sensor data using cross-modal fusion. The benefit of the combination would have been to improve or otherwise provide an alternative model-based BP-estimation technique by using Long’s multimodal ECG/PPG fusion model to exploit complementary physiological information from different sensor types, rather than relying only on a single PPG data stream. A person of ordinary skill in the art would have had a reasonable expectation of success because both Carter and Long are directed to cuffless blood-pressure estimation using physiological waveform data and computational models, and Long expressly teaches that its ECG/PPG BPNet model outputs SBP and DBP values from the received ECG and PPG inputs.
Regarding Claim 3, the modified Carter does not expressly teach wherein the at least one computational model comprises a first computational model configured to receive the PPG sensor data as an input, and at least one of: a second computational model configured to receive the ECG sensor data as an input; a third computational model configured to receive BCG sensor data as an input; or a fourth computational model configured to receive microphone sensor data as an input. Rather, the modified Carter teaches determining blood pressure from PPG sensor data using machine learning, including developing and/or implementing a predictive model for blood pressure based on PPG-derived biometric features and beat-shape features (Carter, FIGS. 1-2; ¶[0038], ¶[0045], ¶[0082]-[0083]). However, the modified Carter does not expressly teach the at least one computational model comprising separate sensor-specific computational models, including a first computational model configured to receive PPG sensor data as an input and a second computational model configured to receive ECG sensor data as an input.
Long, who is also directed to cuffless blood-pressure estimation using physiological sensor data and computational models, teaches separate sensor-specific computational models for different types of physiological sensor data. Long teaches that BPNet receives ECG and PPG signals and includes pre-feature extraction, cross-modal fusion, post-feature extraction, and multi-tasking modules for outputting SBP and DBP (Long, p. 4, FIG. 2; §3.3). Long further teaches that BPNet first utilizes two separate Convolutional Neural Networks (CNNs) to extract diverse levels of visual feature maps from the PPG and ECG signals, respectively, before the maps are fused to generate multi-modal feature maps (Long, p. 4, §3.3). Long’s FIG. 4 depicts a PPG branch and an ECG branch, and Long further teaches that the input consists of a segment of the PPG signal and a segment of the ECG signal and that visual features of PPG and ECG are first extracted using a CNN as the backbone, respectively (Long, p. 5, FIG. 4; §3.3(1)). Thus, Long teaches a first computational model configured to receive PPG sensor data as an input and a second computational model configured to receive ECG sensor data as an input.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the modified Carter in view of Long so that the at least one computational model comprises a first computational model configured to receive PPG sensor data as an input and a second computational model configured to receive ECG sensor data as an input. The modification would have been feasible because the modified Carter already teaches a machine-learning predictive model for determining blood pressure from wearable physiological sensor data, and Long teaches a known BP-estimation neural-network architecture having separate PPG and ECG CNN branches for receiving and processing PPG and ECG signals, respectively. The benefit of the combination would have been to improve or otherwise provide an alternative model-based BP-estimation technique by separately extracting and processing sensor-specific information from PPG and ECG signals before using the resulting features for BP estimation. A person of ordinary skill in the art would have had a reasonable expectation of success because Carter and Long are both directed to cuffless blood-pressure estimation using physiological waveform data and computational/model-based processing, and Long expressly teaches using separate PPG and ECG neural-network branches in a BP-estimation model.
Regarding Claim 4, the modified Carter does not expressly teach further comprising aggregating an output of the first computational model with outputs of the at least one of the second computational model, the third computational model, or the fourth computational model to determine the indicated BP value. Rather, the modified Carter teaches determining blood pressure from PPG sensor data using machine learning, including developing and/or implementing a predictive model for blood pressure based on PPG-derived biometric features and beat-shape features (Carter, FIGS. 1-2; ¶[0038], ¶[0045], ¶[0082]-[0083]). The modified Carter further teaches aggregating outputs of multiple computational models to determine a BP value because Carter teaches generating an ensemble of individual regression models that each predict blood pressure and determining a final pressure estimate from a median value of the individual regression models (Carter, ¶[0083]-[0086]). However, the modified Carter does not expressly teach aggregating an output of a first PPG computational model with an output of a second ECG computational model to determine the indicated BP value.
Long, who is also directed to cuffless blood-pressure estimation using physiological sensor data and computational models, teaches separate sensor-specific computational model branches and aggregation of branch outputs to determine BP values. As discussed above with respect to claim 3, Long teaches BPNet, in which PPG and ECG inputs are processed using separate CNN branches to extract feature maps from the respective input signals (Long, p. 4, FIG. 4; §3.3; p. 5, FIG. 4; §3.3(1)). Long further teaches that the PPG-derived and ECG-derived feature maps are mapped to a corresponding shared space and fused at the channel level to generate multi-modal feature maps for each signal (Long, p. 4, §3.3). Long further teaches that cross-modal multi-level fusion constructs joint multi-modal feature-sharing subspaces to fuse PPG and ECG multi-level features in the channel dimension, including by concatenating PPG and ECG feature vectors, and then using FPN for modal fusion before estimating SBP and DBP (Long, p. 5, FIGS. 4-5; §3.3(1)). Thus, under a broadest reasonable interpretation, Long teaches aggregating an output of the first computational model, corresponding to the PPG CNN branch outputting PPG-derived feature maps, with an output of the second computational model, corresponding to the ECG CNN branch outputting ECG-derived feature maps, to determine the indicated BP value.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the modified Carter in view of Long so that outputs of separate PPG and ECG computational models are aggregated to determine the indicated BP value. The modification would have been feasible because the modified Carter already teaches a machine-learning predictive model for determining blood pressure from wearable physiological sensor data and further teaches determining a final BP estimate by aggregating outputs of individual regression models, while Long teaches a known BP-estimation neural-network architecture that separately processes PPG and ECG signals and aggregates the resulting sensor-specific feature-map outputs through cross-modal multi-level fusion to estimate SBP and DBP. The benefit of the combination would have been to improve or otherwise provide an alternative model-based BP-estimation technique by combining complementary information extracted from different physiological sensor types before determining the BP value, while using Carter’s known aggregation of model outputs for BP estimation. A person of ordinary skill in the art would have had a reasonable expectation of success because Carter and Long are both directed to cuffless blood-pressure estimation using physiological waveform data and computational/model-based processing, Carter expressly teaches aggregating individual regression-model outputs to determine a final BP estimate, and Long expressly teaches aggregating ECG-derived and PPG-derived information in a BP-estimation model that outputs SBP and DBP values.
Regarding Claim 9, the modified Carter does not expressly teach wherein the at least one computational model is a joint computational model configured to receive multiple different types of sensor data from multiple different types of sensors, respectively. Rather, the modified Carter teaches a computing device that determines blood pressure from PPG sensor data using machine learning, including developing and/or implementing a predictive model for blood pressure based on PPG-derived biometric features and beat-shape features (Carter, FIGS. 1-2 and 4; ¶[0038], ¶[0045], ¶[0054]-[0055], ¶[0082]-[0083]). However, the modified Carter does not expressly teach that the computational model is a joint computational model configured to receive multiple different types of sensor data from multiple different types of sensors, respectively.
Long, who is also directed to cuffless blood-pressure estimation using physiological sensor data and computational models, teaches a joint computational model configured to receive multiple different types of sensor data from multiple different types of sensors, respectively. Long teaches BPNet, an end-to-end model for blood-pressure estimation using ECG and PPG signals, where the model addresses prior methods that concatenate ECG and PPG without fully capturing their relationship and instead proposes a multi-modal fusion model for BP estimation (Long, Abstract; p. 2, FIG. 1(c)). Long further teaches that preprocessed ECG and PPG signals are fed into BPNet, which includes pre-feature extraction, cross-modal fusion, post-feature extraction, and a multi-tasking module, and that the BPNet model outputs both SBP and DBP (Long, p. 4, FIG. 2; §3.3). Long further teaches that the input consists of a segment of the PPG signal and a segment of the ECG signal, and that PPG and ECG features are fused to achieve multi-modal feature representation for BP estimation (Long, p. 5, FIGS. 4-5; §3.3(1)). Thus, Long teaches a joint computational model configured to receive multiple different types of sensor data, including ECG and PPG sensor data, from multiple different types of sensors.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the modified Carter in view of Long so that the computational model is a joint computational model configured to receive multiple different types of sensor data from multiple different types of sensors, respectively, such as ECG sensor data and PPG sensor data. The modification would have been feasible because the modified Carter already teaches a processor-implemented machine-learning predictive model for determining blood pressure from wearable physiological sensor data, and Long teaches a known BP-estimation neural-network architecture that jointly processes ECG and PPG sensor data using cross-modal fusion. The benefit of the combination would have been to improve or otherwise provide an alternative model-based BP-estimation technique by using Long’s multimodal ECG/PPG fusion model to exploit complementary physiological information from different sensor types, rather than relying only on a single PPG data stream. A person of ordinary skill in the art would have had a reasonable expectation of success because the modified Carter and Long are directed to cuffless blood-pressure estimation using physiological waveform data and computational models, and Long expressly teaches that its ECG/PPG BPNet model outputs SBP and DBP values from the received ECG and PPG inputs.
Regarding Claim 10, the modified Carter does not expressly teach wherein the at least one computational model comprises a first computational model configured to receive the PPG sensor data as an input, and at least one of: a second computational model configured to receive the ECG sensor data as an input; a third computational model configured to receive the BCG sensor data as an input; or a fourth computational model configured to receive the microphone sensor data as an input; and the operations further comprising aggregating an output of the first computational model with outputs of the at least one of the second computational model, the third computational model, or the fourth computational model to determine the indicated BP value. Rather, the modified Carter teaches a computing device that determines blood pressure from PPG sensor data using machine learning, including developing and/or implementing a predictive model for blood pressure based on PPG-derived biometric features and beat-shape features (Carter, FIGS. 1-2 and 4; ¶[0038], ¶[0045], ¶[0054]-[0055], ¶[0082]-[0083]). The modified Carter further teaches aggregating outputs of multiple computational models to determine a BP value because Carter teaches generating an ensemble of individual regression models that each predict blood pressure and determining a final pressure estimate from a median value of the individual regression models (Carter, ¶[0083]-[0086]). However, the modified Carter does not expressly teach separate sensor-specific computational models, including a first computational model configured to receive PPG sensor data as an input and a second computational model configured to receive ECG sensor data as an input, or aggregating outputs of those sensor-specific computational models to determine the indicated BP value.
Long, who is also directed to cuffless blood-pressure estimation using physiological sensor data and computational models, teaches separate sensor-specific computational model branches for different types of physiological sensor data. Long teaches BPNet, an end-to-end model for blood-pressure estimation using ECG and PPG signals, where the model addresses prior methods that concatenate ECG and PPG without fully capturing their relationship and instead proposes a multi-modal fusion model for BP estimation (Long, Abstract; p. 2, FIG. 1(c)). Long further teaches that preprocessed ECG and PPG signals are fed into BPNet, which includes pre-feature extraction, cross-modal fusion, post-feature extraction, and a multi-tasking module, and that the BPNet model outputs both SBP and DBP (Long, p. 4, FIG. 2; §3.3). Long teaches that BPNet first utilizes two separate Convolutional Neural Networks (CNNs) to extract diverse levels of visual feature maps from the PPG and ECG signals, respectively, before the maps are fused to generate multi-modal feature maps (Long, p. 4, §3.3). Long’s FIG. 4 depicts a PPG branch and an ECG branch, and Long further teaches that the input consists of a segment of the PPG signal and a segment of the ECG signal and that visual features of PPG and ECG are first extracted using a CNN as the backbone, respectively (Long, p. 5, FIG. 4; §3.3(1)). Thus, Long teaches a first computational model configured to receive PPG sensor data as an input and a second computational model configured to receive ECG sensor data as an input.
Long further teaches aggregating output feature maps of the separate sensor-specific computational model branches to determine the indicated BP value. Long teaches that the PPG-derived and ECG-derived feature maps are mapped to a corresponding shared space and fused at the channel level to generate multi-modal feature maps for each signal (Long, p. 4, §3.3). Long further teaches that cross-modal multi-level fusion constructs joint multi-modal feature-sharing subspaces to fuse PPG and ECG multi-level features in the channel dimension, including by concatenating PPG and ECG feature vectors, and then using FPN for modal fusion before estimating SBP and DBP (Long, p. 5, FIGS. 4-5; §3.3(1)). Thus, under a broadest reasonable interpretation, Long teaches aggregating an output of the first computational model, corresponding to the PPG CNN branch outputting PPG-derived feature maps, with an output of the second computational model, corresponding to the ECG CNN branch outputting ECG-derived feature maps, to determine the indicated BP value.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the modified Carter in view of Long so that the at least one computational model comprises a first computational model configured to receive PPG sensor data as an input and a second computational model configured to receive ECG sensor data as an input, and so that outputs of the separate PPG and ECG computational models are aggregated to determine the indicated BP value. The modification would have been feasible because the modified Carter already teaches a processor-implemented machine-learning predictive model for determining blood pressure from wearable physiological sensor data and further teaches determining a final BP estimate by aggregating outputs of individual regression models, while Long teaches a known BP-estimation neural-network architecture that separately processes PPG and ECG signals and fuses the resulting sensor-specific feature-map outputs through cross-modal multi-level fusion to estimate SBP and DBP. The benefit of the combination would have been to improve or otherwise provide an alternative model-based BP-estimation technique by separately extracting and processing sensor-specific information from PPG and ECG signals and combining complementary information extracted from the different physiological sensor types before determining the BP value. A person of ordinary skill in the art would have had a reasonable expectation of success because the modified Carter and Long are directed to cuffless blood-pressure estimation using physiological waveform data and computational/model-based processing, Carter expressly teaches aggregating individual regression-model outputs to determine a final BP estimate, and Long expressly teaches using separate PPG and ECG neural-network branches and fusing ECG-derived and PPG-derived information in a BP-estimation model that outputs SBP and DBP values.
Claims 5 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Carter et al. (US 2017/0181649 A1), hereinafter referred to as Carter, in view of Lusted (US 10,709,339 B1), hereinafter referred to as Lusted, and further in view of Lange (US 2016/0360974 A1), hereinafter referred to as Lange.
The modified Carter teaches claims 1 and 8 as shown above.
Regarding Claim 5, the modified Carter does not expressly teach further comprising: determining, based at least on the sensor data, an indication of at least one physiological characteristic of a portion of a vascular system of a person corresponding to the sensor data; providing the at least one physiological characteristic to the at least one computational model. Rather, the modified Carter teaches determining blood pressure from PPG sensor data using machine learning, including developing and/or implementing a predictive model for blood pressure based on PPG-derived biometric features and beat-shape features (Carter, FIGS. 1-2; ¶[0038], ¶[0045], ¶[0082]-[0083]). However, the modified Carter does not expressly teach determining, based at least on the sensor data, an indication of at least one physiological characteristic of a portion of a vascular system of a person corresponding to the sensor data and providing the physiological characteristic to the at least one computational model.
Lange, who is also directed to cuffless blood-pressure estimation using wearable physiological sensor data and a model, teaches determining, based at least on sensor data, an indication of at least one physiological characteristic of a portion of a vascular system corresponding to the sensor data and providing the physiological characteristic to a model. Lange teaches simultaneously recording ECG and PPG, where the PPG is measured at a blood artery, analyzing the ECG and PPG to determine pulse transit time (PTT), pulse rate (PR), and a diameter parameter, wherein the diameter parameter includes a diameter of the blood artery or a change in the diameter of the blood artery (Lange, Abstract; ¶[0010]; FIG. 6). Lange further teaches determining BP using a predefined model based on PTT, PR, and the diameter parameter, wherein the predefined model establishes a relationship between PTT, PR, the diameter parameter, and BP (Lange, Abstract; ¶[0010]-[0012]; FIG. 6). Lange also teaches that the change in the diameter of the blood artery may be determined using PPG-derived AC and DC components (Lange, claim 9). Thus, Lange teaches determining an indication of a physiological characteristic of a vascular-system portion, namely a blood-artery diameter or change in blood-artery diameter, and providing that physiological characteristic to a BP model.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the modified Carter in view of Lange so that the method determines, based at least on the sensor data, an indication of at least one physiological characteristic of a portion of a vascular system of a person corresponding to the sensor data and provides the physiological characteristic to the at least one computational model. The modification would have been feasible because the modified Carter already teaches a machine-learning predictive model for determining blood pressure from wearable physiological sensor data, and Lange teaches a known cuffless BP-estimation model that uses physiological vascular information, including an artery diameter parameter or change in artery diameter, together with ECG/PPG-derived timing information to determine BP. The benefit of the combination would have been to improve or otherwise provide an alternative model-based BP-estimation technique by including vascular-system information that reflects the physical condition of the artery associated with the measured physiological signal, thereby allowing the BP model to account for vascular characteristics relevant to blood-pressure determination. A person of ordinary skill in the art would have had a reasonable expectation of success because Carter and Lange are both directed to cuffless blood-pressure estimation using wearable physiological sensor data and model-based processing, and Lange expressly teaches using a vascular diameter parameter as an input to a BP model.
Regarding Claim 11, the modified Carter does not expressly teach determining, based at least on the sensor data, an indication of at least one physiological characteristic of a portion of a vascular system of a person corresponding to the sensor data; and providing the at least one physiological characteristic to the at least one computational model. Rather, the modified Carter teaches a computing device that determines blood pressure from PPG sensor data using machine learning, including developing and/or implementing a predictive model for blood pressure based on PPG-derived biometric features and beat-shape features (Carter, FIGS. 1-2 and 4; ¶[0038], ¶[0045], ¶[0054]-[0055], ¶[0082]-[0083]). However, the modified Carter does not expressly teach determining, based at least on the sensor data, an indication of at least one physiological characteristic of a portion of a vascular system of a person corresponding to the sensor data and providing the physiological characteristic to the at least one computational model.
Lange, who is also directed to cuffless blood-pressure estimation using wearable physiological sensor data and a model, teaches determining, based at least on sensor data, an indication of at least one physiological characteristic of a portion of a vascular system corresponding to the sensor data and providing the physiological characteristic to a model. Lange teaches simultaneously recording ECG and PPG, where the PPG is measured at a blood artery, analyzing the ECG and PPG to determine pulse transit time (PTT), pulse rate (PR), and a diameter parameter, wherein the diameter parameter includes a diameter of the blood artery or a change in the diameter of the blood artery (Lange, Abstract; ¶[0010]; FIG. 6). Lange further teaches determining BP using a predefined model based on PTT, PR, and the diameter parameter, wherein the predefined model establishes a relationship between PTT, PR, the diameter parameter, and BP (Lange, Abstract; ¶[0010]-[0012]; FIG. 6). Lange also teaches that the change in the diameter of the blood artery may be determined using PPG-derived AC and DC components (Lange, claim 9). Thus, Lange teaches determining an indication of a physiological characteristic of a vascular-system portion, namely a blood-artery diameter or change in blood-artery diameter, and providing that physiological characteristic to a BP model by using the diameter parameter as an input or variable in the predefined BP model.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the modified Carter in view of Lange so that the computing-device operations determine, based at least on the sensor data, an indication of at least one physiological characteristic of a portion of a vascular system of a person corresponding to the sensor data and provide the physiological characteristic to the at least one computational model. The modification would have been feasible because the modified Carter already teaches a processor-implemented machine-learning predictive model for determining blood pressure from wearable physiological sensor data, and Lange teaches a known cuffless BP-estimation model that uses physiological vascular information, including an artery diameter parameter or change in artery diameter, together with ECG/PPG-derived timing information to determine BP. The benefit of the combination would have been to improve or otherwise provide an alternative model-based BP-estimation technique by including vascular-system information that reflects the physical condition of the artery associated with the measured physiological signal, thereby allowing the BP model to account for vascular characteristics relevant to blood-pressure determination. A person of ordinary skill in the art would have had a reasonable expectation of success because the modified Carter and Lange are both directed to cuffless blood-pressure estimation using wearable physiological sensor data and model-based processing, and Lange expressly teaches using a vascular diameter parameter as an input to a BP model.
Claims 6 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Carter et al. (US 2017/0181649 A1), hereinafter referred to as Carter, in view of Lusted (US 10,709,339 B1), hereinafter referred to as Lusted, and further in view of Lange (US 2016/0360974 A1), hereinafter referred to as Lange, and further in view of Miao et al. (Miao, Fen et al., Multi-Sensor Fusion Approach for Cuff-Less Blood Pressure Measurement, IEEE Journal of Biomedical and Health Informatics, Vol. 24, No. 1, January 2020), hereinafter referred to as Miao.
The modified Carter teaches claims 1 and 8 as shown above.
Regarding Claim 6, the modified Carter does not expressly teach wherein the at least one physiological characteristic includes at least one of a resistance or compliance of a portion of an artery of the person. Rather, the modified Carter, as further modified by Lange with respect to claim 5, teaches determining a physiological characteristic of a vascular-system portion, including a diameter parameter corresponding to a blood artery or change in blood-artery diameter, and providing that parameter to a BP model (Lange, Abstract; ¶[0010]-[0012]; FIG. 6; ¶[0060]-[0062]). Lange further teaches that determining BP based on PTT alone may not be sufficiently accurate because of other cardiovascular parameters affecting hemodynamics, including vascular resistance, cardiac output, pulse rate, and finger temperature, and teaches applying correction factors to account for vascular resistance in PPG-based BP measurement, wherein the correction factors may be determined by an empirical formula (Lange, ¶[0007]). Thus, Lange teaches or at least suggests that the physiological characteristic provided for BP determination includes a resistance-related characteristic of the vascular system, namely vascular resistance or a correction factor accounting for vascular resistance.
Miao further supports the known use of resistance- and compliance-related vascular characteristics in cuffless BP estimation. Miao teaches that BP is produced by blood flow through arterial vessels, which are similar to elastic tubes, and that BP fluctuations are affected by factors including vessel elasticity, peripheral resistance, cardiac output, and blood volume (Miao, p. 80). Miao further teaches that pulse-wave analysis can be used to evaluate blood-vessel function, including arterial stiffness, and that vessel elasticity is one of the most important factors influencing BP fluctuations (Miao, p. 81). Miao also teaches that peripheral microvascular tissue resistance affects PPG morphology and that pulse pressure waveform information has been studied for evaluating arterial stiffness and cardiac function (Miao, p. 80). Thus, Miao confirms that resistance- and compliance-related vascular characteristics, including peripheral resistance, vessel elasticity, and arterial stiffness, were known physiological characteristics relevant to cuffless BP estimation.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the modified Carter in view of Lange and Miao so that the at least one physiological characteristic includes at least one of a resistance or compliance of a portion of an artery of the person. The modification would have been feasible because the modified Carter already teaches model-based BP estimation using wearable physiological sensor data, Lange teaches providing vascular physiological information to a BP model and expressly teaches accounting for vascular resistance in PPG-based BP measurement, and Miao confirms that peripheral resistance, vessel elasticity, and arterial stiffness are known vascular characteristics affecting BP and physiological waveform morphology. The benefit of the combination would have been to improve or otherwise provide an alternative BP-estimation technique by allowing the model to account for vascular resistance or compliance-related characteristics that affect the relationship between physiological sensor data and blood pressure. A person of ordinary skill in the art would have had a reasonable expectation of success because Carter, Lange, and Miao are each directed to cuffless BP estimation using physiological sensor data and model-based processing, Lange expressly teaches accounting for vascular resistance in BP measurement, and Miao confirms that vessel elasticity and arterial stiffness are relevant compliance-related vascular factors in BP estimation.
Regarding Claim 12, the modified Carter does not expressly teach that the at least one physiological characteristic includes at least one of a resistance or compliance of a portion of an artery of the person. Rather, the modified Carter, as further modified by Lange with respect to claim 11, teaches determining a physiological characteristic of a vascular-system portion, including a diameter parameter corresponding to a blood artery or change in blood-artery diameter, and providing that parameter to a BP model (Lange, Abstract; ¶[0010]-[0012]; FIG. 6; ¶[0060]-[0062]). Lange further teaches that determining BP based on PTT alone may not be sufficiently accurate because of other cardiovascular parameters affecting hemodynamics, including vascular resistance, cardiac output, pulse rate, and finger temperature, and teaches applying correction factors to account for vascular resistance in PPG-based BP measurement, wherein the correction factors may be determined by an empirical formula (Lange, ¶[0007]). Thus, Lange teaches or at least suggests that the physiological characteristic used for BP determination includes a resistance-related characteristic of the vascular system, namely vascular resistance or a correction factor accounting for vascular resistance.
Miao further supports the known use of resistance- and compliance-related vascular characteristics in cuffless BP estimation. Miao teaches that BP is produced by blood flow through arterial vessels, which are similar to elastic tubes, and that BP fluctuations are affected by factors including vessel elasticity, peripheral resistance, cardiac output, and blood volume (Miao, p. 80). Miao further teaches that pulse-wave analysis can be used to evaluate blood-vessel function, including arterial stiffness, and that vessel elasticity is one of the most important factors influencing BP fluctuations (Miao, p. 81). Miao also teaches that peripheral microvascular tissue resistance affects PPG morphology and that pulse pressure waveform information has been studied for evaluating arterial stiffness and cardiac function (Miao, p. 80). Thus, Miao confirms that resistance- and compliance-related vascular characteristics, including peripheral resistance, vessel elasticity, and arterial stiffness, were known physiological characteristics relevant to cuffless BP estimation.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the modified Carter in view of Lange and Miao so that the at least one physiological characteristic includes at least one of a resistance or compliance of a portion of an artery of the person. The modification would have been feasible because the modified Carter already teaches processor-implemented model-based BP estimation using wearable physiological sensor data, Lange teaches providing vascular physiological information to a BP model and expressly teaches accounting for vascular resistance in PPG-based BP measurement, and Miao confirms that peripheral resistance, vessel elasticity, and arterial stiffness are known vascular characteristics affecting BP and physiological waveform morphology. The benefit of the combination would have been to improve or otherwise provide an alternative BP-estimation technique by allowing the model to account for vascular resistance or compliance-related characteristics that affect the relationship between physiological sensor data and blood pressure. A person of ordinary skill in the art would have had a reasonable expectation of success because the modified Carter, Lange, and Miao are each directed to cuffless BP estimation using physiological sensor data and model-based processing, Lange expressly teaches accounting for vascular resistance in BP measurement, and Miao confirms that vessel elasticity and arterial stiffness are relevant compliance-related vascular factors in BP estimation.
Claims 7 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Carter et al. (US 2017/0181649 A1), hereinafter referred to as Carter, in view of Lusted (US 10,709,339 B1), hereinafter referred to as Lusted.
The modified Carter teaches claims 1 and 8 as shown above.
Regarding Claim 7, the modified Carter teaches wherein the at least one action comprises at least one of: displaying the BP value, generating an alert based on the BP value, sending the BP value to another device, or performing a further processing step based on the BP value (Carter, ¶[0039], teaching determining and representing an individual’s blood pressure in a medically accepted standard, such as millimeters of mercury; ¶[0091], teaching correlating blood pressure with hypotension, hypertension, and/or normotension, wherein Carter teaches or at least suggests performing a further processing step based on the BP value by using the BP value to determine or correlate a blood-pressure condition).
To the extent it is argued that Carter does not expressly teach displaying the BP value or sending the BP value to another device, Lusted teaches these limitations. Lusted teaches a wearable biometric sensing ring having a PPG sensor, ECG electrodes, a controller, and programming for receiving PPG and ECG data, converting the PPG and ECG data into digital data, calculating blood pressure from the digital ECG and PPG sensor data, and graphically outputting the calculated BP (Lusted, Abstract). Lusted further teaches that BP calculation algorithms may be implemented on a smartphone, that “the systolic and diastolic BP are displayed,” and that values may be transmitted to the smartphone for display on an app screen (Lusted, col. 10, ll. 1-23). Lusted also teaches wirelessly communicating data relating to BP between the sensing ring and a mobile device for graphic display of BP on the mobile device (Lusted, claim 14). Thus, Lusted teaches that the at least one action comprises displaying the BP value and/or sending the BP value to another device.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Carter in view of Lusted so that the at least one action comprises displaying the BP value and/or sending the BP value to another device. The modification would have been feasible because Carter already determines and represents BP values from wearable PPG sensor data using a machine-learning predictive model, and Lusted teaches a known wearable/mobile-device output architecture for displaying and communicating calculated BP values from wearable physiological sensors. The benefit of the combination would have been to provide the subject with a readily accessible indication of Carter’s determined BP value and to support continuous blood-pressure monitoring by displaying or communicating the calculated BP result.
Regarding Claim 14, the modified Carter does not expressly teach that the computing device is a wearable computing device included in a finger-mountable device, the finger-mountable device including the PPG sensor that provides the PPG sensor data to the one or more processors. Rather, the modified Carter teaches a computing device that receives PPG sensor data and determines blood pressure using a machine-learning predictive model, including an electronic device 301, such as a smartphone, tablet computer, or similar device, configured to receive raw data from bracelet 200 and process the raw data using biometric engine 30 (Carter, FIGS. 1-4; ¶[0038], ¶[0045], ¶[0054]-[0055], ¶[0082]-[0083]). Carter also teaches that the one or more devices may be wearable devices worn on suitable portions of the subject’s body, including the hand or finger, and may acquire raw PPG data and/or process raw PPG data to determine blood pressure (Carter, ¶[0047]-[0049]). However, the modified Carter does not expressly teach that the computing device is included in a finger-mountable device that comprises the PPG sensor.
Lusted, who is also directed to continuous blood-pressure monitoring using wearable physiological sensors, teaches a wearable computing device included in a finger-mountable device that comprises a PPG sensor. Lusted teaches a wearable biometric sensing ring apparatus having a ring housing for retention on a finger of a user, a PPG sensor disposed within the housing, ECG electrodes, a controller and programming for receiving PPG and ECG data, calculating blood pressure, and graphically outputting the calculated BP (Lusted, Abstract). Lusted further teaches a ring-shaped housing having a finger aperture so that the device is wearable on a finger, and teaches a PPG module/sensor disposed on the ring sensor surface (Lusted, FIGS. 1-5; col. 4, ll. 9-34). Lusted further teaches an integrated BLE processor having a CPU, memory, BLE data input/output module, and wireless transmission/receiver module, and teaches a BLE device/transmitter/receiver for wirelessly communicating with another electronic device, such as a smartphone (Lusted, col. 5, ll. 54-65; col. 6, ll. 1-4; col. 6, ll. 50-65). Thus, Lusted teaches a wearable computing device included in a finger-mountable ring device that comprises the PPG sensor.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Carter in view of Lusted so that the computing device is a wearable computing device included in a finger-mountable device that comprises the PPG sensor that provides the data to the one or more processors. The modification would have been feasible because Carter already teaches determining blood pressure from wearable PPG sensor data using processor-implemented machine-learning operations, and Lusted teaches a known finger-mounted wearable BP-monitoring device having a PPG sensor, processor, memory, executable instructions, and wireless communication circuitry. The benefit of the combination would have been to provide Carter’s model-based BP-estimation functionality, at least in part, in a compact finger-mounted wearable device that can collect PPG sensor data locally while supporting wearable BP monitoring and user-accessible output/communication functionality. A person of ordinary skill in the art would have had a reasonable expectation of success because Carter and Lusted are both directed to wearable blood-pressure monitoring using PPG-based physiological sensor data, and Lusted’s finger ring already includes the PPG sensor and processor/controller architecture needed to receive and process PPG data for BP monitoring.
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Carter et al. (US 2017/0181649 A1), hereinafter referred to as Carter, in view of Lusted (US 10,709,339 B1), hereinafter referred to as Lusted, and further in view of Klaassen et al. (US 2017/0340209 A1), hereinafter referred to as Klaassen.
The modified Carter teaches claim 8 as shown above.
Regarding Claim 13, the modified Carter teaches the computing device as recited in claim 8, wherein: the computing device is a mobile computing device that receives wirelessly the sensor data from the at least one of the PPG sensor, the ECG sensor, the BCG sensor, or the microphone from one or more sensor devices mounted on a person (Carter, FIGS. 3-4; ¶[0047], teaching one or more wearable devices configured to be worn on a portion of a subject’s body effective for acquiring raw data, including on the wrist, hand, finger, arm, torso, leg, foot, neck, chest, back, face, ear, or any other suitable portion of the subject’s body; ¶[0048], teaching recording raw PPG data with one or more devices configured to acquire raw PPG data and/or process raw PPG data to determine blood pressure, wherein the devices may be wearable by the subject; ¶[0049], teaching a bracelet configured to acquire raw PPG data and/or process raw PPG data to determine blood pressure; ¶[0054], teaching that electronic device 301 may be a smartphone, tablet computer, or similar device configured to receive raw data from bracelet 200 and that raw PPG data collected by light sensor 202 can be input to electronic device 301; ¶[0055], teaching that light sensor 202 and/or motion sensor 203 are configured to wirelessly transmit raw data to electronic device 301, wherein Carter teaches a mobile computing device, such as a smartphone, wirelessly receiving PPG sensor data from a sensor device mounted on the person, such as bracelet 200);
Also regarding claim 13, the modified Carter does not expressly teach wherein performing, by the one or more processors, the at least one action comprises sending the BP value to at least one wearable computing device included with at least one of the one or more sensor devices mounted on the person. Rather, the modified Carter teaches a mobile computing device receiving wearable PPG sensor data and determining a BP value using a machine-learning predictive model, but does not expressly teach sending the BP value to a wearable computing device included with at least one of the one or more sensor devices mounted on the person. Under the Examiner’s broadest reasonable interpretation, included with at least one of the one or more sensor devices mounted on the person means physically part of, attached to, or otherwise associated with at least one sensor device mounted on the person.
Klaassen, who is also directed to blood-pressure monitoring using wearable devices, teaches transmitting blood-pressure values/signals to a wearable computing device that is physically part of, attached to, or otherwise associated with a sensor device mounted on the person. Klaassen teaches that calibration may be carried out externally of a wrist-worn device by a mobile device, tablet, computer, or database, and that a plurality of calibrated relative blood-pressure values may be transmitted to a second wrist-worn device, mobile device, tablet, computer, or database for further processing, storage, retrieval, or display (Klaassen, ¶[0017]). Klaassen further teaches that a telemetry interface may transmit relative or absolute blood-pressure signals to a second wrist-worn electronic device, a mobile device, tablet, computer, or database for further processing, storage, retrieval by other devices or programs, and/or display, and may transmit the relative or absolute blood-pressure signals to a display on the second wrist-worn electronic device or a third non-wrist device, such as a mobile device, tablet, or computer (Klaassen, ¶[0026]). Klaassen further teaches transmitting calibrated and/or non-filtered blood-pressure values to a second electronic device, such as a watch, mobile device, tablet, computer, or database for further processing, storage, retrieval, and/or display to the user or health care professional (Klaassen, ¶[0215]).
Klaassen further teaches an overall system including a first wrist-worn band, a second wrist-worn electronic device, such as a watch, and a third non-wrist device, such as a mobile device, wherein the first wrist-worn band includes at least one PTT or pressure sensor, one or more processors, memory, and a telemetry/wireless interface, and wherein the second wrist-worn watch includes one or more heart-rate monitor sensors, a processor, memory, telemetry interface, and user display (Klaassen, ¶[0216]-[0217]). Klaassen further teaches that the first wrist-worn band may communicate with the second wrist-worn watch via Wi-Fi or Bluetooth, including transmitting blood-pressure values and receiving updated instructions, such as new calibration equations (Klaassen, ¶[0217]). Thus, under the Examiner’s broadest reasonable interpretation, Klaassen teaches or suggests the recited relationship because Klaassen’s second wrist-worn watch is itself a sensor-containing wearable computing device having one or more heart-rate monitor sensors, a processor, memory, telemetry interface, and display, and because the second wrist-worn watch is otherwise associated with the first wrist-worn sensor band by being part of the same wearable blood-pressure monitoring system and communicating with the first wrist-worn sensor band via Wi-Fi or Bluetooth, including receiving blood-pressure values and exchanging updated instructions or calibration information (Klaassen, ¶[0216]-[0217]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the modified Carter in view of Klaassen so that performing, by the one or more processors, the at least one action comprises sending the BP value to at least one wearable computing device included with at least one of the one or more sensor devices mounted on the person. The modification would have been feasible because the modified Carter already teaches a mobile computing device wirelessly receiving PPG sensor data from a wearable sensor device and determining BP using a computational model, and Klaassen teaches wearable blood-pressure monitoring systems in which blood-pressure values/signals are transmitted to wrist-worn/wearable electronic devices having sensors, processors, memory, telemetry interfaces, and displays. The benefit of the combination would have been to permit the BP value determined at Carter’s mobile computing device to be sent to a wearable computing device that is physically part of, attached to, or otherwise associated with a sensor device mounted on the person for local display, storage, status updating, user accessibility, updated instruction handling, or further blood-pressure monitoring functionality. A person of ordinary skill in the art would have had a reasonable expectation of success because Carter and Klaassen are both directed to wearable physiological monitoring and blood-pressure determination, Carter already teaches wireless communication between a wearable sensor device and a mobile computing device, and Klaassen teaches communication and use of blood-pressure values/signals by wrist-worn electronic devices having sensor, communication, processing, memory, and display hardware.
Claims 15 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Lusted (US 10,709,339 B1), hereinafter referred to as Lusted, in view of Carter et al. (US 2017/0181649 A1), hereinafter referred to as Carter.
Regarding Claim 15, Lusted teaches a finger-mountable device comprising: at least one photoplethysmographic (PPG) sensor; a communication interface; and one or more processors configured by executable instructions to perform operations comprising: (Lusted, Abstract, teaching “a wearable biometric sensing ring apparatus” having “a ring housing for retention on a finger of a user,” a “photoplethysmograph (PPG) sensor disposed within the housing,” a controller and programming for receiving PPG and ECG data, calculating BP, and graphically outputting calculated BP; Lusted, FIGS. 1-5; col. 4, ll. 9-25, teaching a ring-shaped housing having a finger aperture so that the device is wearable on a finger; col. 4, ll. 26-34, teaching a PPG module/sensor on the ring sensor surface; col. 4, ll. 50-60, teaching a Bluetooth Low Energy chip on the flexible circuit board; col. 5, ll. 54-65 and col. 6, ll. 1-4, teaching inputs received by an integrated BLE processor having a CPU, memory, BLE data I/O module, and wireless transmission/receiver module; col. 6, ll. 50-65, teaching a BLE device/transmitter/receiver for wirelessly communicating with another electronic device, such as a smartphone, wherein Lusted teaches a finger-mountable ring device having a PPG sensor, wireless communication interface, processor, memory, and executable instructions);
receiving, by the one or more processors, sensor data from at least the PPG sensor (Lusted, Abstract, teaching a controller and programming for receiving analog pulse rate data from the PPG sensor and analog ECG data from the electrodes and converting the analog pulse rate data and ECG data into digital data; Lusted, FIGS. 4-5; col. 5, ll. 39-48, teaching PPG sensor 34/22 producing a light-varying analog signal output to processor A/D input 62b; col. 5, ll. 54-65, teaching that inputs are received at the integrated BLE processor and converted to digital signals for processing, wherein Lusted teaches receiving sensor data from at least the PPG sensor);
performing, by the one or more processors, at least one action based on the indicated BP value (Lusted, Abstract, teaching calculating blood pressure from a combination of digital ECG and PPG sensor data and graphically outputting the calculated BP; Lusted, FIG. 10, illustrating an application screen showing HR, HRV, and BP values; col. 6, ll. 50-65, teaching wireless communication with another electronic device to allow controlling device operation, registering collected sensor data, analyzing collected data, and displaying collected or analyzed data; col. 10, ll. 1-23, teaching that the systolic and diastolic BP are displayed and that values may be transmitted to a smartphone for display on an app screen; col. 13, ll. 1-5, teaching communicating data relating to HR, HRV, and BP to a mobile device and graphically displaying HR, HRV, and BP on the mobile device; claim 14, teaching wirelessly communicating BP between the sensing ring and a mobile device for graphic display of BP on the mobile device, wherein Lusted teaches performing an action based on the BP value by graphically displaying and/or wirelessly communicating the BP value).
Also regarding claim 15, Lusted does not expressly teach inputting, by the one or more processors, the received sensor data into at least one computational model and receiving, by the one or more processors, an output of the at least one computational model indicative of a blood pressure (BP) value in the same manner as claimed. Rather, Lusted teaches calculating BP from ECG and PPG sensor data using pulse-transit-time/correlation-based BP determination. Although Lusted’s BP-calculation algorithm may broadly constitute a computational model under a broad interpretation, Carter expressly teaches the claimed model-based implementation because Carter teaches processing raw PPG data to generate biometric features and beat-shape features, using machine learning to develop a predictive model for blood pressure, modeling blood pressure as a regression problem, and outputting systolic pressure, diastolic pressure, and/or mean arterial pressure (Carter, FIGS. 1-2; ¶[0038], ¶[0039], ¶[0045], ¶[0082]-[0083]).
Carter, who is also directed to determining blood pressure from wearable PPG data, teaches inputting PPG-derived sensor data into a computational model and receiving a BP output from the model. Carter teaches processing raw PPG data with a biometric engine to generate scaled beats and biometric features, and processing the scaled beats and biometric features with a blood pressure engine configured to perform beat shape analysis, measure additional shape features, and model with machine learning to determine blood pressure (Carter, FIGS. 1-2; ¶[0038]). Carter teaches that “modeling with machine learning to determine blood pressure 136 comprises using machine learning to develop a predictive model for blood pressure” (Carter, ¶[0082]). Carter further teaches that blood pressure can be modeled as a regression problem and that separate regression models may be developed for systolic pressure, diastolic pressure, and/or mean arterial pressure (Carter, ¶[0083]). Carter teaches output from the computational model because Carter’s machine learning unit outputs blood pressure results, including systolic pressure, diastolic pressure, and mean arterial pressure (Carter, FIG. 1; ¶[0039], ¶[0045], ¶[0082]-[0083]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Lusted in view of Carter so that Lusted’s finger-mountable BP-monitoring device inputs the received PPG sensor data, including PPG-derived features or waveform information, into Carter’s machine-learning predictive model and receives a model output indicative of a BP value. The modification would have been feasible because Lusted already includes a finger-mounted PPG sensor, processor, memory, executable instructions, wireless communication circuitry, and BP-calculation functionality, and Carter teaches a processor-implemented machine-learning predictive model for determining BP from wearable PPG data. The modification would not require redesigning Lusted’s finger-ring device or destroying Lusted’s principle of operation because Lusted’s ring already contains the PPG sensor and processor architecture needed to collect and process PPG data, and substituting or supplementing Lusted’s BP-calculation programming with Carter’s PPG-based predictive model would be a predictable use of Lusted’s existing hardware rather than a removal of the wearable BP-monitoring functionality. A person of ordinary skill in the art would have had a reasonable expectation of success because Carter’s predictive model is expressly designed to determine BP from PPG-derived data, and Lusted’s ring already includes a PPG sensor and processor/controller architecture for receiving and processing PPG data to calculate BP. The benefit of the combination would have been to provide an improved or alternative model-based BP-estimation technique in Lusted’s finger-ring BP monitor by using Carter’s predictive machine-learning model to determine systolic pressure, diastolic pressure, and/or mean arterial pressure from PPG sensor data while preserving Lusted’s finger-mounted sensor hardware and BP output/display functionality.
Regarding Claim 18, the modified Lusted teaches the finger-mountable device as recited in claim 15, wherein performing the at least one action comprises wirelessly sending the BP value to a mobile device for presentation by the mobile device (Lusted, Abstract, teaching a wearable biometric sensing ring apparatus having a PPG sensor, ECG electrodes, controller/programming for calculating BP from ECG and PPG sensor data, and graphically outputting the calculated BP; col. 6, ll. 50-65, teaching a BLE device, including a BLE transmitter/receiver, for wirelessly communicating with another electronic device, such as a smartphone, to allow controlling operation of the apparatus, registering collected sensor data, analyzing collected data, and displaying collected or analyzed data; col. 10, ll. 1-23, teaching that BP calculation algorithms may be implemented on a smartphone, that “the systolic and diastolic BP are displayed”, and that values may be transmitted to the smartphone for display on the app screen; Lusted, claim 14, teaching wirelessly communicating data relating to HR, HRV, and BP between the sensing ring and a mobile device for graphic display of HR, HRV, and BP on the mobile device, wherein Lusted teaches wirelessly sending the BP value to a mobile device for presentation by the mobile device).
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Lusted (US 10,709,339 B1), hereinafter referred to as Lusted, in view of Carter et al. (US 2017/0181649 A1), hereinafter referred to as Carter, and further in view of Lange (US 2016/0360974 A1), hereinafter referred to as Lange, and further in view of Miao et al. (Miao, Fen et al., Multi-Sensor Fusion Approach for Cuff-Less Blood Pressure Measurement, IEEE Journal of Biomedical and Health Informatics, Vol. 24, No. 1, January 2020), hereinafter referred to as Miao.
The modified Lusted teaches claim 15 as shown above.
Regarding Claim 16, the modified Lusted does not expressly teach that the operations further comprise: determining, based at least on the sensor data, an indication of at least one physiological characteristic of a portion of a vascular system of a person corresponding to the sensor data; and providing the at least one physiological characteristic to the at least one computational model, wherein the at least one physiological characteristic includes at least one of a resistance or compliance of a portion of an artery of the person. Rather, the modified Lusted teaches a finger-mountable device including a PPG sensor, communication interface, processor, memory, executable instructions, BP calculation, and graphical/wireless BP output, as modified by Carter to input received PPG sensor data into a machine-learning predictive model and receive a BP output from the model (Lusted, Abstract; FIGS. 1-5; col. 4, ll. 9-34; col. 5, ll. 54-65; col. 6, ll. 1-4; col. 6, ll. 50-65; Carter, FIGS. 1-2; ¶[0038], ¶[0045], ¶[0082]-[0083]). However, the modified Lusted does not expressly teach determining, based at least on the sensor data, an indication of at least one physiological characteristic of a portion of a vascular system of a person corresponding to the sensor data, providing the physiological characteristic to the at least one computational model, and wherein the physiological characteristic includes at least one of a resistance or compliance of a portion of an artery of the person.
Lange, who is also directed to cuffless blood-pressure estimation using wearable physiological sensor data and a model, teaches determining a physiological characteristic of a vascular-system portion and providing that characteristic to a BP model. Lange teaches simultaneously recording ECG and PPG, where the PPG is measured at a blood artery, analyzing the ECG and PPG to determine pulse transit time (PTT), pulse rate (PR), and a diameter parameter, wherein the diameter parameter includes a diameter of the blood artery or a change in the diameter of the blood artery (Lange, Abstract; ¶[0010]; FIG. 6). Lange further teaches determining BP using a predefined model based on PTT, PR, and the diameter parameter, wherein the predefined model establishes a relationship between PTT, PR, the diameter parameter, and BP (Lange, Abstract; ¶[0010]-[0012]; FIG. 6). Lange also teaches that the change in the diameter of the blood artery may be determined using PPG-derived AC and DC components (Lange, claim 9). Thus, Lange teaches determining an indication of a physiological characteristic of a vascular-system portion, namely a blood-artery diameter or change in blood-artery diameter, and providing that physiological characteristic to a BP model by using the diameter parameter as an input or variable in the predefined BP model.
Lange further teaches or at least suggests that the physiological characteristic used for BP determination includes a resistance-related characteristic of the vascular system. Lange teaches that determining BP based on PTT alone may not be sufficiently accurate because of other cardiovascular parameters affecting hemodynamics, including vascular resistance, cardiac output, pulse rate, and finger temperature, and teaches applying correction factors to account for vascular resistance in PPG-based BP measurement, wherein the correction factors may be determined by an empirical formula (Lange, ¶[0007]). Thus, Lange teaches or at least suggests that the physiological characteristic used for BP determination includes a resistance-related characteristic of the vascular system, namely vascular resistance or a correction factor accounting for vascular resistance.
Miao further supports the known use of compliance-related vascular characteristics in cuffless BP estimation. Miao teaches that BP is produced by blood flow through arterial vessels, which are similar to elastic tubes, and that BP fluctuations are affected by factors including vessel elasticity, peripheral resistance, cardiac output, and blood volume (Miao, p. 80). Miao further teaches that pulse-wave analysis can be used to evaluate blood-vessel function, including arterial stiffness, and that vessel elasticity is one of the most important factors influencing BP fluctuations (Miao, p. 81). Miao also teaches that peripheral microvascular tissue resistance affects PPG morphology and that pulse pressure waveform information has been studied for evaluating arterial stiffness and cardiac function (Miao, p. 80). Thus, Miao confirms that resistance- and compliance-related vascular characteristics, including peripheral resistance, vessel elasticity, and arterial stiffness, were known physiological characteristics relevant to cuffless BP estimation.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the modified Lusted in view of Lange and Miao so that the finger-mountable device operations determine, based at least on the sensor data, an indication of at least one physiological characteristic of a portion of a vascular system of a person corresponding to the sensor data, provide the physiological characteristic to the at least one computational model, and wherein the physiological characteristic includes at least one of a resistance or compliance of a portion of an artery of the person. The modification would have been feasible because the modified Lusted already teaches a finger-mounted wearable BP-monitoring device using PPG sensor data and processor-implemented model-based BP estimation as taught by Carter, Lange teaches providing vascular physiological information to a BP model and expressly teaches accounting for vascular resistance in PPG-based BP measurement, and Miao confirms that peripheral resistance, vessel elasticity, and arterial stiffness are known vascular characteristics affecting BP and physiological waveform morphology. The benefit of the combination would have been to improve or otherwise provide an alternative BP-estimation technique by allowing the computational model of the finger-mountable device to account for vascular resistance or compliance-related characteristics that affect the relationship between physiological sensor data and blood pressure. A person of ordinary skill in the art would have had a reasonable expectation of success because Lusted, Carter, Lange, and Miao are each directed to cuffless or wearable BP estimation using physiological sensor data and model-based processing, Lange expressly teaches accounting for vascular resistance in BP measurement, and Miao confirms that vessel elasticity and arterial stiffness are relevant compliance-related vascular factors in BP estimation.
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Lusted (US 10,709,339 B1), hereinafter referred to as Lusted, in view of Carter et al. (US 2017/0181649 A1), hereinafter referred to as Carter, and further in view of Tran (US 2014/0249429 A1), hereinafter referred to as Tran, and further in view of Long et al. (Long, Weicai and Wang, Xingjun, Bpnet: A Multi-Modal Fusion Neural Network for Blood Pressure Estimation Using ECG and PPG. Biomedical Signal Processing and Control, vol. 86, no. 105287, September 2023), hereinafter referred to as Long.
The modified Lusted teaches claim 15 as shown above.
Regarding Claim 17, the modified Lusted does not expressly teach that the operations further comprise: receiving additional sensor data from sensor devices located at one or more other body locations, the additional sensor data being received from at least one of an electrocardiogram (ECG) sensor, a ballistocardiogram (BCG) sensor, or a microphone; and wherein inputting the PPG sensor data into the at least one computational model, further comprising inputting the additional sensor data into the at least one computational model. Rather, the modified Lusted teaches a finger-mounted device that receives PPG sensor data and ECG sensor data, calculates BP from a combination of the digital ECG and PPG sensor data, and is modified by Carter to input received PPG sensor data into a machine-learning predictive model and receive a BP output from the model (Lusted, Abstract; FIGS. 1-5; col. 4, ll. 9-34; col. 5, ll. 54-65; col. 6, ll. 1-4; col. 6, ll. 50-65; Carter, FIGS. 1-2; ¶[0038], ¶[0045], ¶[0082]-[0083]). Lusted further teaches that a third electrode on an outer surface of the ring may contact a contralateral body portion, including an opposite finger, contralateral wrist, contralateral shoulder, contralateral neck, contralateral clavicle, sternum, ipsilateral clavicle, ipsilateral shoulder, ipsilateral thigh, and contralateral thigh (Lusted, Abstract; claim 17). However, the modified Lusted does not expressly teach receiving additional sensor data from separate sensor devices located at one or more other body locations, or inputting such additional sensor data into the Carter-style computational model.
Tran, who is also directed to fitness and vital-sign monitoring using body-worn sensor devices and wireless communication, teaches receiving additional sensor data from sensor devices located at one or more other body locations. Tran teaches that sensors may be worn on the body, such as in watch bands, finger rings, or adhesive sensors, and that telemetry, rather than wires, may be used to communicate with the controller (Tran, ¶[0275]). Tran further teaches an earphone embodiment having mesh-network communication electronics and physiological sensors, such as EKG/ECG sensors, and a microphone that may pick up heart sound when the user is not using the microphone for voice communication (Tran, ¶[0312]). Tran further teaches an adhesive patch having a module containing electronics for communicating with the mesh network and for sensing acceleration, bioimpedance, EKG/ECG, heart sound, microphone, optical sensor, or ultrasonic sensor in contact with a wearer’s skin, and teaches that one or more patches may be applied to the wearer’s body and may communicate wirelessly using the mesh network or a personal area network (Tran, ¶[0313]-[0314]). Thus, Tran teaches additional sensor devices located at one or more other body locations that provide additional sensor data from an ECG sensor and/or microphone.
Long, who is also directed to cuffless blood-pressure estimation using physiological sensor data and computational models, teaches inputting both PPG sensor data and additional ECG sensor data into a computational model for BP estimation. Long teaches BPNet, an end-to-end model for blood-pressure estimation using ECG and PPG signals, where preprocessed ECG and PPG signals are fed into BPNet, which includes pre-feature extraction, cross-modal fusion, post-feature extraction, and a multi-tasking module, and the BPNet model outputs both SBP and DBP (Long, Abstract; p. 4, FIG. 2; §3.3). Long teaches that BPNet first utilizes two separate convolutional neural networks to extract diverse levels of visual feature maps from the PPG and ECG signals, respectively, before the feature maps are fused to generate multi-modal feature maps (Long, p. 4, §3.3; p. 5, FIG. 4; §3.3(1)). Long further teaches that the input consists of a segment of the PPG signal and a segment of the ECG signal, and that both ECG and PPG signals are used in the BPNet model for BP estimation (Long, p. 5, FIG. 4; §3.3(1)). Thus, Long teaches inputting both PPG sensor data and additional ECG sensor data into the at least one computational model.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the modified Lusted in view of Tran and Long so that the finger-mountable device receives additional sensor data from sensor devices located at one or more other body locations, the additional sensor data being received from at least one ECG sensor or microphone, and so that the additional sensor data is input into the at least one computational model. The modification would have been feasible because the modified Lusted already teaches a finger-mounted BP-monitoring device having a PPG sensor, ECG capability, BLE wireless communication circuitry, processor/controller architecture, and BP-calculation functionality; Tran teaches additional body-worn sensor devices, such as adhesive patches and earphones, having ECG and/or microphone sensors and wireless telemetry; and Long teaches a BP-estimation model that receives both PPG and ECG sensor data as inputs. The modification would not require redesigning Lusted’s finger-mounted device because Lusted already teaches using both PPG and ECG information for BP calculation, and Tran’s additional body-worn sensors communicate using wireless telemetry. The benefit of the combination would have been to improve or otherwise provide an alternative model-based BP-estimation technique by allowing the finger-mounted device to use additional physiological information collected from other body locations, including ECG or microphone/heart-sound information, while retaining Lusted’s compact finger-mounted PPG structure. A person of ordinary skill in the art would have had a reasonable expectation of success because Lusted, Tran, and Long are each directed to physiological monitoring using wearable or body-mounted sensors, Lusted and Tran teach wireless communication circuitry suitable for exchanging sensor data, and Long expressly teaches that ECG and PPG signals can be jointly used by a computational BP model to output SBP and DBP values.
Claim 19 is rejected under 35 U.S.C. 103 as being unpatentable over Lusted (US 10,709,339 B1), hereinafter referred to as Lusted, in view of Carter et al. (US 2017/0181649 A1), hereinafter referred to as Carter, and further in view of Liao et al. (Liao, Shangdi, et al. “Effect of Filtering on Pulse Wave Transit Time Measured by Photoplethysmography.” Computing in Cardiology, vol. 498, 2022), hereinafter referred to as Liao.
The modified Lusted teaches claim 15 as shown above.
Regarding Claim 19, the modified Lusted does not expressly teach the finger-mountable device as recited in claim 15, wherein the PPG sensor has a sampling rate greater than 1000 Hz. Rather, the modified Lusted teaches a finger-mounted device including a PPG sensor, communication interface, processor, memory, executable instructions, BP calculation, and graphical/wireless BP output, as modified by Carter to input received PPG sensor data into a machine-learning predictive model and receive a BP output from the model (Lusted, Abstract; FIGS. 1-5; col. 4, ll. 9-34; col. 5, ll. 54-65; col. 6, ll. 1-4; col. 6, ll. 50-65; Carter, FIGS. 1-2; ¶[0038], ¶[0045], ¶[0082]-[0083]). However, the modified Lusted does not expressly teach that the PPG sensor has a sampling rate greater than 1000 Hz.
Liao, who is directed to photoplethysmography and pulse-transit-time analysis relevant to cuffless blood-pressure estimation, teaches acquiring PPG signals at a sampling rate greater than 1000 Hz. Liao teaches that pulse transit time (PTT) is an important physiological parameter for blood-pressure estimation and can be derived from ECG and PPG waveform features (Liao, Abstract; p. 1, Introduction). Liao further teaches that filtering can change the PPG signal waveform and the timing of PPG feature points, and that PTT is negatively related to blood pressure, which provides a theoretical basis for cuffless blood-pressure measurement using wearable PPG sensors (Liao, Abstract; p. 1, Introduction). Liao teaches that ECG and PPG signals from the right index fingertip and right earlobe were recorded simultaneously for 120 seconds at a sampling rate of 2500 Hz (Liao, p. 2, §2.1). Thus, Liao teaches acquiring fingertip PPG sensor data at a sampling rate greater than 1000 Hz.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the modified Lusted in view of Liao so that the PPG sensor has a sampling rate greater than 1000 Hz, such as Liao’s 2500 Hz sampling rate. The modification would have been feasible because the modified Lusted already teaches a finger-mounted PPG-based BP-monitoring device using PPG sensor data and processor-implemented model-based BP estimation as taught by Carter, and Liao teaches fingertip PPG signal acquisition at 2500 Hz in a PTT/BP-estimation context. The benefit of the combination would have been to provide increased temporal resolution for PPG waveform acquisition and PPG feature-point detection, thereby reducing timing error in PPG-derived timing features used for BP estimation. A person of ordinary skill in the art would have had a reasonable expectation of success because Lusted, Carter, and Liao are each directed to physiological monitoring using PPG signals, Lusted and Carter use PPG information for BP determination, and Liao expressly teaches fingertip PPG acquisition at a sampling rate greater than 1000 Hz.
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Lusted (US 10,709,339 B1), hereinafter referred to as Lusted, in view of Carter et al. (US 2017/0181649 A1), hereinafter referred to as Carter, and further in view of Connor (US 2018/0042513 A1), hereinafter referred to as Connor.
The modified Lusted teaches claim 15 as shown above.
Regarding Claim 20, the modified Lusted does not expressly teach the finger-mountable device as recited in claim 15, further comprising a display, the operation of performing at least one action comprising presenting the BP value on the display. Rather, the modified Lusted teaches a finger-mounted device including a PPG sensor, communication interface, processor, memory, executable instructions, BP calculation, and graphical/wireless BP output, as modified by Carter to input received PPG sensor data into a machine-learning predictive model and receive a BP output from the model (Lusted, Abstract; FIGS. 1-5; col. 4, ll. 9-34; col. 5, ll. 54-65; col. 6, ll. 1-4; col. 6, ll. 50-65; Carter, FIGS. 1-2; ¶[0038], ¶[0045], ¶[0082]-[0083]). Lusted further teaches graphically outputting calculated BP and displaying analyzed sensor information, including BP-related information, through a mobile device or app screen (Lusted, Abstract; col. 6, ll. 50-65; col. 10, ll. 1-23). However, the modified Lusted does not expressly teach that the finger-mountable device itself further comprises a display on which the BP value is presented.
Connor teaches a wearable device, including a finger-ring or finger-sleeve embodiment, having a local display. Connor teaches that an arcuate wearable device for measuring a physiological property may be embodied in a smart watch band, specialized hydration-monitoring band, or finger ring (Connor, Abstract; ¶[0193]-[0196]). Connor further teaches that the wearable device may include an electronics housing held on the body by an arcuate band, wherein the electronics housing may include a display component (Connor, ¶[0258]). Connor also teaches that the band can be a finger ring or finger sleeve, and that the band or housing can include electronic components such as a display (Connor, ¶[0334]-[0335]). Thus, Connor teaches a finger-worn wearable device comprising a display.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have further modified the modified Lusted in view of Connor so that the finger-mountable device further comprises a display and presents the BP value on the display. The modification would have been feasible because the modified Lusted already teaches a finger-mounted BP-monitoring device having a PPG sensor, processor/controller architecture, memory, BP-calculation functionality, battery/power components, wireless communication, and graphical BP output, while Connor teaches that a finger-ring or finger-sleeve wearable device may include a local display. The benefit of the combination would have been to allow the BP value determined using the finger-mounted device to be presented locally on the finger-mounted device, thereby improving immediate user access to the BP value without requiring exclusive reliance on a separate mobile-device display. A person of ordinary skill in the art would have had a reasonable expectation of success because Lusted and Connor are both directed to wearable physiological monitoring devices with body-worn electronics, and adding a known wearable-device display to Lusted’s finger-mounted BP-monitoring device would have involved the predictable use of a known display component for its ordinary purpose of presenting physiological measurement information.
Conclusion
Any inquiry concerning this communication or earlier communications from the
examiner should be directed to AARON MERRIAM whose telephone number is (703) 756-
5938. The examiner can normally be reached M-F 7:00 am - 4:00 pm EST.
Examiner interviews are available via telephone, in-person, and video conferencing
using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is
encouraged to use the USPTO Automated Interview Request (AIR) at
http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s
supervisor, Jason Sims can be reached on (571)272-4867. The fax phone number for the
organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained
from Patent Center. Unpublished application information in Patent Center is available to
registered users. To file and manage patent submissions in Patent Center, visit:
https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for
more information about Patent Center and https://www.uspto.gov/patents/docx for
information about filing in DOCX format. For additional questions, contact the Electronic
Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO
Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/AARON MERRIAM/Examiner, Art Unit 3791
/MATTHEW KREMER/Primary Examiner, Art Unit 3791
Prosecution Insights