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 .
Response to Amendment
The amendment filed 01/12/2026 has been entered. Claims 1-9, 23-25, and 28 are canceled and new claim 29 is added. Accordingly, claims 21-22, 26-27, and 29 remain pending in the application. Applicant’s amendments to the claims have overcome each and every objection and 112(b) rejections, except regarding claim 27, previously set forth in the Non-Final Office Action mailed 10/27/2025.
Response to Arguments
Applicant's arguments filed 01/12/2026 have been fully considered but they are not persuasive.
Applicant argues reference Aguirre and Denison do not teach or contemplate a system and method that relies on simply comparing data sets and discarding spurious data in a mobile computing device and a remote computing device. Applicant argues the teachings of Denison would be inoperable when combined with the other prior art cited. Applicant argues Denison does not teach comparing and Denison’s method could not be conducted on a mobile device as it includes transformations and complex algorithms.
Examiner respectfully disagrees. Firstly, Aguirre teaches comparing data sets in ¶ [00107]. Aguirre discloses:
“As a non-limiting example, pressure parameters could be derived from the physiological patient data using a machine learning model or algorithm (e.g., neural network), which was previously trained to relate or calibrate the physiological patient data to pressure parameters. As non-limiting examples of such physiologic patient data, pressure parameters could be derived from PPG signals, ECG signals, arterial tonometry signals, ultrasound imaging, or other cardiovascular imaging data”
The pressure parameters are specifically blood pressure parameters. In addition, the physiological data may include ultrasound data such as ultrasound imaging data as disclosed. Aguirre therefore teaches wherein ultrasound imaging data may be related or calibrated, i.e. compared, to blood pressure data. In addition, Aguirre teaches wherein a computing device (1250) comprising a smartphone may be used to implement the methods described above (Fig. 2B, [00201], “In some configurations, computing device 1250 can execute at least a portion of a cardiovascular measurement system 1204 to calculate Pcrit or TPP using the methods described herein”, wherein the step described in ¶ [00107] is part of calculating Pcrit, as further evidenced by figure 2B, [00203], “a smartphone”). Therefore, Aguirre teaches comparing and wherein this comparing may be conducted on a mobile device.
Regarding Denison’s method of discarding spurious data and Applicant’s argument that this could not be conducted on a mobile device, Examiner respectfully disagrees. Reference Aravamudan (US20260037491) teaches wherein an apparatus (100) including a computing device (116) for training a machine learning model may be a mobile telephone or smartphone ([0023], “Computing device may include, be included in, and/or communicate with a mobile device such as a mobile telephone or smartphone”, [0024], [0172]). Aravamudan teaches wherein the computing device (116) is configured to perform the processes of described in their disclosure ([0024]). Aravamudan teaches wherein spurious data may be removed via applying a preprocessing step to a training dataset ([0090]). In addition, Aravamudan teaches wherein the pre-processing steps may include applying transforms ([0032], [0124], [0131]). Moreover, Aravamudan teaches wherein pre-processing may include normalization ([0032]). Therefore, the disclosure of Denison stating “The preprocessing step may apply one or more transformations to the training data to clean and normalize the data. The preprocessing step may be configured to discard parameters which contain spurious data or contain very few observations” may be conducted on a mobile device, and therefore Applicant’s arguments are unpersuasive.
Regarding the methods described above being conducted in a remote computing device, Xu ‘269 teaches wherein the methods including application of a machine learning algorithm may be implemented in a remote computing device such as a personal computer or a cloud server ([0043], [0079]). Aguirre further teaches wherein the computing device (1250) configured to compare data may be a remote computing device such as a desktop computer or server computer ([00203]). Similarly, Denison teaches wherein machine learning algorithms may be trained in a cloud computing network and/or server, and wherein this training comprises the steps of preprocessing to normalize the data and discard spurious data ([0052], [0054], [0066], [0068]).
Regarding inoperability when combining Denison with the other prior arts cited, Denison is only being relied upon for teaching the discarding of spurious data. Thus rather than the entire disclosure of Denison being combined with the prior arts cited, only the step of discarding spurious data is being added or combined with the prior arts cited. It is unclear how this step or the addition thereof would be inoperable, particularly in view of the above, e.g. reference Aravamudan, which evidences that a mobile device such as a smart phone is capable of running machine learning algorithms and pre-processing steps including the discarding of spurious data.
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.
Claims 27 and 29 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim 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.
Claims 27 and 29 recite “the wireless radio sending the ultrasound data to the mobile computing device”. It is unclear which wireless radio is sending the ultrasound data as the inventions recite that the wearable patch, the mobile computing device, the blood pressure sensor all include a wireless radio. Claim 27 further includes a remote computer with a wireless radio. For purposes of examination, it will be interpreted for the wireless radio in this instance to refer to the wireless radio of the microprocessor which the wearable patch comprises.
Claim Rejections - 35 USC § 103
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 21-22 are rejected under 35 U.S.C. 103 as being unpatentable over Xu ‘269 (US20220133269) in view of Xu ‘204 (US20230355204), Aguirre (WO2024163819), Shen (CN202568226; translation provided), and Denison (US20220288389).
Regarding claim 21, Xu ‘269 teaches a machine learning and blood pressure monitoring system (Abstract, Claim 13, [0061]), the machine learning and blood pressure monitoring system comprising a wearable patch (100; 502), a mobile computing device (112) (Figs. 2B, 5, & 10, [0038], [0053], [0065-0066]),
the wearable patch (100; 502) including:
an array of ultrasound transducers (102) (Figs. 1 & 3, [0038-0039], [0049-0051]),
a high-speed analogue to digital converter (143) in electrical communication with the array of ultrasound transducers (102) (Figs. 2B-2C, [0044], [0048]); and
a microprocessor (106; 143) which includes a wireless radio (151) for transmitting ultrasound data to the mobile computing device (112) and is in electronic communication with the high speed analogue to digital converter (143) (Figs. 2A & 2C, [0040], [0043], [0048], [0052-0053]),
the mobile computing device (112) including: a memory; a processor; a wireless radio; and a screen, wherein the memory is configured for machine learning by wherein the memory is configured to convert the ultrasound data into blood pressure data to provide ultrasound-derived blood pressure data (Figs. 2A & 5, [0043], “A machine learning algorithm incorporated in the software 114… The algorithm may be situated on the smartphone”, [0061], “The blood pressure, blood flow, and cardiac pressure signals can be extracted from ultrasound images… using deep learning networks trained for semantic segmentation”, [0079], wherein smartphones include a memory, processor, wireless radio, and screens), and
once trained, to instruct the processor to display blood pressure data derived from the ultrasound data on the screen (Claims 12-13, [0045], “Raw ultrasound data may be decoded into the blood pressure waveforms. Finally, the decoded waveforms may be wirelessly transmitted and visualized on a display via Bluetooth or Wi-Fi”, [0079], “The outputs may be delivered to a user by way of a video graphics card or integrated graphics chipset coupled to a display that maybe seen by a user”, [0061], “The blood pressure, blood flow, and cardiac pressure signals can be extracted from ultrasound images… using deep learning networks trained for semantic segmentation”).
However, Xu ‘269 fails to teach wherein the wearable patch includes: a flexible housing which includes a contact surface; an adhesive on at least a part of the contact surface; and wherein the array of ultrasound transducers embedded in the flexible housing and facing the contact surface.
In an analogous blood pressure monitoring system comprising a wearable patch field of endeavor, Xu ‘204 teaches such a feature. Xu ‘204 teaches a wearable ultrasonic-system-on-patch (USoP) which can continuously monitor physiological signals including blood pressure (Title, Abstract, [0004], [0094]). Xu ‘204 teaches the USoP is housed in an elastomeric package (Figs. 22-23, [0099], [0119], [0218-0219], wherein the elastomeric package comprises a flexible housing). Xu ‘204 teaches the USoP includes a stretchable ultrasonic probe which consists of a piezoelectric transducer array (Figs. 1a-1d, [0197], wherein the USoP including the piezoelectric transducer array comprises an array of ultrasound transducers embedded in the flexible housing/elastomeric packaging). Xu ‘204 further teaches wherein the packaged USoP is applied to skin with commercially available adhesives and wherein the transducers contact the skin via a probe-skin interface comprising a silicone elastomer (Figs. 1A-1B, [0118], [0218], wherein the USoP applied to skin with adhesives comprises the housing including a contact surface and adhesive thereon, and wherein the transducers contacting the skin via the silicone elastomer comprises the transducers facing the contact surface; see also figures 1A-1B). Xu ‘204 therefore teaches a wearable patch including a flexible housing (elastomeric packaging) including a contact surface, an adhesive on the contact surface, and an array of ultrasound transducers embedded in the flexible housing and facing the contact surface.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to house the device in an elastomeric packaging and to use adhesives on a surface of the packaging as taught by Xu ‘204 (Figs. 1A-1B & 22-23, [0099], [0119], [0218-0219]). The elastomeric encapsulation may help mitigate strain concentrations and protect internal circuitry from irreversible deformations as recognized by Xu ‘204 ([0099]). Moreover, the adhesive may predictably be used to maintain robust adhesion of the device to the subject’s skin as further recognized by Xu ‘204 ([0204], [0218]), allowing for reliable interfacing of the ultrasound transducers with the skin to obtain physiological signals.
However the modified combination noted above fails to teach wherein the memory is configured to compare ultrasound data with blood pressure data.
In an analogous measuring of blood pressure field of endeavor, Aguirre teaches such a feature. Aguirre teaches measuring blood pressure data ([0071-0072], [0074]). Aguirre teaches wherein the blood pressure monitoring device may comprise a sphygmomanometer or blood pressure cuff ([0077]). Aguirre teaches wherein the pressure measurement module (104) may include other measurement devices such as an ultrasound imaging device ([0078]). Aguirre teaches measuring physiological patient data such as ultrasound data ([0106], “cardiac flow data (e.g., Doppler ultrasound flow measurements)”, [0107], “As non-limiting examples of such physiologic patient data, pressure parameters could be derived from… ultrasound imaging”). Aguirre teaches wherein ultrasound imaging data may be related or calibrated, i.e. compared, to blood pressure data ([0107]). In addition, Aguirre teaches wherein a computing device (1250) comprising a smartphone may be used to implement the methods described above (Fig. 2B, [00201], “In some configurations, computing device 1250 can execute at least a portion of a cardiovascular measurement system 1204 to calculate Pcrit or TPP using the methods described herein”, wherein the step described in ¶ [00107] is part of calculating Pcrit, as further evidenced by figure 2B, [00203], “a smartphone”). Therefore, Aguirre teaches comparing and wherein this comparing may be conducted on a mobile device.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to have the mobile device be configured to relate or calibrate ultrasound data to blood pressure data as taught by Aguirre ([00107], [00203]). By relating/calibrating the measured blood pressure data received by a sphygmomanometer or blood pressure cuff to ultrasound data, the need for the sphygmomanometer or cuff may be eliminated and replaced with continuous monitoring via ultrasound, thereby improving patient comfort.
However the modified combination noted above fails to teach wherein the invention further comprises the blood pressure sensor, which includes an analogue to digital converter and a wireless radio, the wireless radio for sending blood pressure data to the mobile computing device.
In an analogous blood pressure monitoring system field of endeavor, Shen teaches such a feature. Shen teaches a three-stage cloud computing blood pressure monitor which uses a mobile phone as an intermediate node ([0002]). Shen teaches a blood pressure monitor (1) including an A/D converter 15 and a single-chip microcomputer (16) which may utilize a wireless Bluetooth or Wi-Fi connection for connecting to a module (21) of a smart phone (2) (Fig. 1, [0022], [0024]). Shen teaches the blood pressure monitor (1) may measure blood pressure signals and wirelessly transmit the blood pressure signal to the smart phone (2) ([0023]). Shen therefore teaches a blood pressure sensor including an analogue to digital converter (A/D converter 15) and a wireless radio (wireless Bluetooth/Wi-Fi compatibility) for sending blood pressure data to a mobile computer device (smart phone 2).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to have the blood pressure sensor include an analogue to digital converter and wireless data transfer capability as taught by Shen (Fig. 1, [0022-0024]). The A/D converter may predictably convert an analogue signal measured by the blood pressure sensor into a digital signal readable/interpretable by a computer. Moreover, the wireless radio may predictably allow for the transmission of blood pressure data to the smart phone for the smart phone to train/relate the blood pressure data to ultrasound data via machine learning which is earlier taught by Xu ‘269 in view of Aguirre.
However, the modified combination noted above fails to teach wherein the memory of the mobile computing device is configured to discard spurious ultrasound data.
In an analogous method including training a machine learning models field of endeavor, Denison teaches such a feature. Denison teaches training machine learning models with one or more datasets and may be trained on signals measured by devices, sensors, or systems ([0057-0058]). Denison teaches applying a preprocessing step to training data ([0067-0068]). Denison teaches wherein the preprocessing may include discarding parameters which contain spurious data to clean and normalize the data ([0068]).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to discard spurious data as taught by Denison ([0068]). Aguirre teaches using ultrasound data as training data for the machine learning model/algorithm ([00107]). By discarding spurious training data, irregularities in the input data for training may be reduced, thereby improving robustness of the training as recognized by Denison ([0068]). Since the machine learning algorithm is situated in the mobile computing device as taught by Xu ‘269 ([0043]), processing of signals is performed by the mobile computing device, and the ultrasound data comprises training data for the machine learning algorithm, Xu ‘269 in view of Aguirre modified by the teachings of Denison would predictably result in the memory of the mobile computing device being configured to discard spurious ultrasound and/or blood pressure data.
Regarding claim 22, Xu ‘269 in view of Xu ‘204, Aguirre, Shen, and Denison teaches the invention as claimed above in claim 21.
However, Xu ‘269 fails to teach wherein the blood pressure monitor is a sphygmomanometer.
In an analogous measuring of blood pressure field of endeavor, Aguirre teaches such a feature. Aguirre teaches measuring blood pressure data ([0071-0072], [0074]). Aguirre teaches wherein the blood pressure monitoring device may comprise a sphygmomanometer or blood pressure cuff ([0077]).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to have the blood pressure monitor be a sphygmomanometer as taught by Aguirre ([0077]). The sphygmomanometer may sufficiently measure blood pressure non-invasively, thereby improving patient comfort over more invasive means. Moreover, sphygmomanometers are well-known and conventional devices for measuring blood pressure.
Claim 26 is rejected under 35 U.S.C. 103 as being unpatentable over Xu ‘269 (US20220133269) in view of Xu ‘204 (US20230355204), Aguirre (WO2024163819), Shusterman (US20180020931), Shen (CN202568226; translation provided), and Denison (US20220288389).
Regarding claim 26, Xu ‘269 teaches a machine learning and blood pressure monitoring system (Abstract, Claim 13, [0061]), the machine learning and blood pressure monitoring system comprising a wearable patch (100; 502), and a remote computer (112) (Figs. 1, 2B, & 10, [0038], [0043], wherein the cloud server comprises a remote computer, [0065-0066]),
the wearable patch (100; 502) including:
an array of ultrasound transducers (102) (Figs. 1 & 3, [0038-0039], [0049-0051]);
a high-speed analogue to digital converter (143) in electrical communication with the array of ultrasound transducers (102) (Figs. 2B-2C, [0044], [0048]); and
a microprocessor (106; 149) which includes a wireless radio (151) for transmitting an ultrasound data set to the remote computer (200, 112) and is in electronic communication with the high speed analogue to digital converter (143) (Figs. 2A & 2C, [0040], [0043], [0048], [0052-0053]), and
the remote computer (200, 112) including:
a memory ([0079]);
a processor ([0079]); and
a wireless radio (Figs. 1, 2A, 2C, & 5, [0053], wherein terminal device 112 receiving wirelessly transmitted data means the device includes a wireless radio, [0079])
wherein the memory is configured for machine learning and to convert the ultrasound data into blood pressure data to provide ultrasound-derived blood pressure data (Abstract, [0038], [0043], “The [machine learning] algorithm may be situated on… a cloud server”, [0061], “The blood pressure, blood flow, and cardiac pressure signals can be extracted from ultrasound images”, [0079]).
However, Xu ‘269 fails to teach wherein the wearable patch includes: a flexible housing which includes a contact surface; an adhesive on at least a part of the contact surface; and wherein the array of ultrasound transducers embedded in the flexible housing and facing the contact surface.
In an analogous blood pressure monitoring system comprising a wearable patch field of endeavor, Xu ‘204 teaches such a feature. Xu ‘204 teaches a wearable ultrasonic-system-on-patch (USoP) which can continuously monitor physiological signals including blood pressure (Title, Abstract, [0004], [0094]). Xu ‘204 teaches the USoP is housed in an elastomeric package (Figs. 22-23, [0099], [0119], [0218-0219], wherein the elastomeric package comprises a flexible housing). Xu ‘204 teaches the USoP includes a stretchable ultrasonic probe which consists of a piezoelectric transducer array (Figs. 1a-1d, [0197], wherein the USoP including the piezoelectric transducer array comprises an array of ultrasound transducers embedded in the flexible housing/elastomeric packaging). Xu ‘204 further teaches wherein the packaged USoP is applied to skin with commercially available adhesives and wherein the transducers contact the skin via a probe-skin interface comprising a silicone elastomer (Figs. 1A-1B, [0118], [0218], wherein the USoP applied to skin with adhesives comprises the housing including a contact surface and adhesive thereon, and wherein the transducers contacting the skin via the silicone elastomer comprises the transducers facing the contact surface; see also figures 1A-1B). Xu ‘204 therefore teaches a wearable patch including a flexible housing (elastomeric packaging) including a contact surface, an adhesive on the contact surface, and an array of ultrasound transducers embedded in the flexible housing and facing the contact surface.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to house the device in an elastomeric packaging and to use adhesives on a surface of the packaging as taught by Xu ‘204 (Figs. 1A-1B & 22-23, [0099], [0119], [0218-0219]). The elastomeric encapsulation may help mitigate strain concentrations and protect internal circuitry from irreversible deformations as recognized by Xu ‘204 ([0099]). Moreover, the adhesive may predictably be used to maintain robust adhesion of the device to the subject’s skin as further recognized by Xu ‘204 ([0204], [0218]), allowing for reliable interfacing of the ultrasound transducers with the skin to obtain physiological signals.
However the modified combination noted above fails to teach wherein the system comprises a blood pressure sensor which includes a blood pressure sensor wireless radio and wherein the memory of the remote computer is configured to instruct the processor to compare ultrasound data with blood pressure data.
In an analogous measuring of blood pressure field of endeavor, Aguirre teaches such a feature. Aguirre teaches measuring blood pressure data ([0071-0072], [0074]). Aguirre teaches wherein the blood pressure monitoring device may comprise a sphygmomanometer or blood pressure cuff ([0077]). Aguirre teaches wherein the pressure measurement module (104) may include other measurement devices such as an ultrasound imaging device ([0078]). Moreover, Aguirre teaches wherein the pressure measurement module (104) comprising a blood pressure sensor includes wireless data transmission such as Wi-Fi and Bluetooth, therefore teaching a blood pressure sensor wireless radio ([0070]). Aguirre teaches measuring physiological patient data such as ultrasound data ([0106], “cardiac flow data (e.g., Doppler ultrasound flow measurements)”, [0107], “As non-limiting examples of such physiologic patient data, pressure parameters could be derived from… ultrasound imaging”). Aguirre teaches wherein ultrasound imaging data may be related or calibrated, i.e. compared, to blood pressure data ([0107]). Aguirre therefore teaches a blood pressure sensor including a wireless radio and comparing ultrasound data with blood pressure data. Aguirre further teaches wherein the computing device (1250) configured to perform the methods herein may be a server computer ([00203]), and wherein the computing device includes a processor (1302) and memory (1310) for executing the methods ([00207], [00209]), therefore teaching wherein a memory of a remote computer is configured to instruct a processor to perform the methods, i.e. comparing ultrasound data with blood pressure data.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 include a blood pressure sensor which includes a wireless radio and to have the memory of the remote computing device be configured to instruct a processor to compare ultrasound data with blood pressure data as taught by Aguirre ([0070], [0076-0077], [00107], [00128], [00203], [00207], [00209]). The blood pressure sensor having a wireless radio predictably allows for transmission of blood pressure data for processing. Moreover, by relating/calibrating the measured blood pressure data received by the blood pressure sensor to ultrasound data, the need for the sphygmomanometer or cuff may be eliminated and replaced with continuous monitoring via ultrasound, improving patient comfort.
However the modified combination noted above fails to teach wherein the system comprises a mobile computing device, the mobile computing device including: a memory; a processor; a wireless radio; and a screen, wherein the wireless radio of the wearable patch transmits an ultrasound data set to the mobile computing device, and wherein the memory of the mobile computing device is configured to instruct the processor to send the ultrasound data set to the remote computer, and to display the blood pressure data set on the screen, and, once the memory is trained, instruct the processor to send the ultrasound-derived blood pressure data to the mobile computing device.
In an analogous blood pressure monitoring system including a wearable patch field of endeavor, Shusterman teaches such a feature. Shusterman teaches a wearable monitoring device having sensors incorporated therein for tracking cardiovascular activity (Abstract, [0003], [0014]). Shusterman teaches wherein the device may be implemented as a wearable patch including the sensors and/or transducers and wherein the sensors may comprise ultrasound sensors (Figs. 10A-10C, [0031], [0088], [0251]). Shusterman further teaches wherein the wearable device may communicate with an external user terminal such as a smartphone using wireless communication such as Bluetooth or Wi-Fi (Figs. 10A-10C, [0176], [0251-0253], [0286-0287]). Shusterman teaches wherein the smartphone may include components for wireless communication, a processor configured to execute instructions including data storage, and a display for displaying parameters derived from data ([0109-0118], wherein the instructions and/or data storage comprise a memory, the microprocessor comprises a processor, the wireless communication component comprises a wireless radio, and the display comprises a screen). Shusterman even further teaches wherein the external user terminal (i.e. smartphone) may communicate data to an internet server (cloud) including a remote processing module (1080) for processing data (Fig. 10B, [0287-0288], [0292]). Moreover, Shusterman teaches wherein the smartphone may display data acquired wirelessly (Fig. 12C, [0178]). Shuster teaches the smartphone may display data and results of data analysis ([0287-0291]) and teaches wherein displayed results of data processing/analysis may include arterial blood pressure ([0302]). Shusterman therefore teaches a mobile computing device (smartphone) configured to send data to a remote computer (Internet server; cloud) for data processing/analysis and wherein the mobile computing device may receive and display the results of the data analysis from the remote computer. Shusterman thus teaches instructing a processor of the remote computer to send the ultrasound-derived blood pressure data to the mobile computing device.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to have the wearable patch be wirelessly connected to a smartphone which is further wirelessly connected to an internet server/cloud for data processing and wherein the smartphone includes a memory, processor, wireless radio, and screen as taught by Shusterman (Figs. 10B & 12C, [0109-0118], [0178], [0251-0253], [0286-0292], [0302]). The mobile computing device comprising a smartphone including a memory, processor, wireless radio, and screen may be used to receive/transmit data to an internet server/cloud for data processing and display the results of the data processing as recognized by Shusterman (Fig. 10B, [0109-0118], [0287-0292]). By having the data processing done remotely, hardware requirements of the mobile device may predictably be made lower. Moreover, data processing performed over the cloud may be more efficient (e.g. the cloud has better hardware). Moreover, by displaying processed data such as blood pressure on the mobile device (smartphone), a user may predictably be made aware of their current physiological state and act accordingly. Xu ‘269 modified by the teachings of Shusterman (Fig. 10B, [0292]) to include a smartphone as an intermediate between the wearable patch and remote computer, have the remote computer process data, and have the smartphone display results of the data processing would predictably result wherein the microprocessor of the wearable patch transmits ultrasound data to the mobile computing device, the mobile computing device passing said data to the remote computer for processing, and the remote computer passing the processed data back to the mobile computing device for display. Xu ‘269 teaches wherein the data processed by the remote computer comprises raw ultrasound data (images) and wherein blood pressure is calculated therefrom ([0011], [0043], [0061]).
However, the modified combination noted above fails to teach wherein the memory of the mobile computing device is configured to instruct the processor to send a blood pressure data set from the blood pressure sensor to the remote computer.
In an analogous blood pressure monitoring system field of endeavor, Shen teaches such a feature. Shen teaches a three-stage cloud computing blood pressure monitor which uses a mobile phone as an intermediate node ([0002]). Shen teaches a blood pressure monitor (1) configured to wirelessly transmit blood pressure signals to a smart phone (2) (Fig. 1, [0022-0024]). Shen further teaches wherein the smart phone (2) processes the signal and wirelessly transmits the blood pressure data signal to a cloud computing server (3) [i.e. remote computer] ([0021], [0024]). Moreover, Shen teaches wherein the cloud computing server (3) performs further processing on the signal and transmits back the blood pressure measurement results to the user’s smart phone (2) ([0026]). Shen therefore teaches wherein a memory of a mobile computing device [i.e. smart phone 2] is configured to instruct its processor to send the blood pressure data from a blood pressure sensor [i.e. blood pressure monitor 1] to a remote computer [i.e. cloud computing server 3].
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to have the smart phone send the blood pressure data from the blood pressure monitor to the cloud server for processing as taught by Shen ([0002], [0022-0024], [0026]). Xu ‘269 already teaches wherein the machine learning algorithm is situated in the cloud server/remote computer ([0043]). Aguirre also teaches training a machine learning algorithm with blood pressure parameters and ultrasound data ([00107]). Shen explicitly teaches sending blood pressure data to the remote computer for processing ([0002], [0022-0024], [0026]). Therefore, the combined teachings of the above seem to suggest wherein the memory of the mobile phone is configured to instruct its processor to send a blood pressure data set from the blood pressure sensor to the remote computer. By sending the blood pressure data set to the remote computer, the machine learning algorithm which is situated at the remote computer may be trained to derive blood pressure from ultrasound data like taught by Aguirre ([00107]), and also the user can take advantage of the superior compute power and data processing capabilities that a cloud server may provide over a mobile phone as further recognized by Shen ([0028]).
However, the modified combination noted above fails to teach wherein the memory is configured to discard spurious ultrasound data.
In an analogous method including training a machine learning models field of endeavor, Denison teaches such a feature. Denison teaches training machine learning models with one or more datasets and may be trained on signals measured by devices, sensors, or systems ([0057-0058]). Denison teaches applying a preprocessing step to training data ([0067-0068]). Denison teaches wherein the preprocessing may include discarding parameters which contain spurious data to clean and normalize the data ([0068]).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to discard spurious data as taught by Denison ([0068]). Aguirre teaches using ultrasound data as training data for the machine learning model/algorithm ([00107]). By discarding spurious training data, irregularities in the input data for training may be reduced, thereby improving robustness of the training as recognized by Denison ([0068]). Since the machine learning algorithm is situated in the remote computing device as taught by Xu ‘269 ([0043]), processing of signals is performed by the remote computing device, and the ultrasound data comprises training data for the machine learning algorithm, Xu ‘269 in view of Aguirre modified by the teachings of Denison would predictably result in the memory of the remote computing device being configured to discard spurious ultrasound and/or blood pressure data.
Claim 27 is rejected under 35 U.S.C. 103 as being unpatentable over Xu ‘269 (US20220133269) in view of Xu ‘204 (US20230355204), Aguirre (WO2024163819), Shusterman (US20180020931), Shen (CN202568226; translation provided), and Denison (US20220288389) as applied to claim 26 above, and further in view of Mizukami (US20150289836).
Regarding claim 27, Xu ‘269 in view of Xu ‘204, Aguirre, Shusterman, Shen, and Denison teach a method of monitoring a user’s blood pressure, the method comprising: the user selecting the machine learning and blood pressure monitoring system of claim 26 (wherein Xu ‘269 in view of Xu ‘206, Aguirre, Shusterman, Shen, and Denison teaching the system of claim 26 comprises a user selecting said system).
Xu ‘269 teaches the method further comprising: the user providing a power source to the wearable patch ([0045]);
the user releasably attaching the wearable patch to a skin surface on the user’s arm (Fig. 2A & 11, [0066], [0071], wherein the figure 11 showing the patch mounted on the hand/fingers comprises attaching the patch to a skin surface of the user’s arm; the hands/fingers are part of a user’s arm anatomically);
the array of ultrasound transducers emitting ultrasound waves under control of the microprocessor (MCU, 149) ([0018], [0048], [0066-0068]);
the array of ultrasound transducers (102) receiving reflected ultrasound waves (Claims 12 & 16, [0039], [0042], [0044], [0048], [0052], [0072-0073]);
the high-speed analogue to digital converter digitizing the reflected ultrasound waves to provide ultrasound data ([0043], “All the signals are amplified through the AFE 104, digitalized by ADCs in the MCU within digital circuit 106…”, [0044]); and
the remote computer processing the ultrasound data to provide ultrasound-derived blood pressure data ([0011], [0043], wherein the machine learning algorithm configured to extract blood pressure is situated in a computer environment such as a cloud server, [0061], “The blood pressure, blood flow, and cardiac pressure signals can be extracted from ultrasound images… using deep learning networks trained for semantic segmentation”).
However, Xu ‘269 fails to teach the wireless radio sending the ultrasound data to the mobile computing device; the mobile computing device sending the ultrasound data to the remote computer, the remote computer sending the ultrasound-derived blood pressure data to the mobile computing device, and once the memory is trained, the mobile computing device displaying the blood pressure reading on the screen.
In an analogous blood pressure monitoring system including a wearable patch field of endeavor, Shusterman teaches such a feature. Shusterman teaches a wearable monitoring device having sensors incorporated therein for tracking cardiovascular activity (Abstract, [0003], [0014]). Shusterman teaches wherein the device may be implemented as a wearable patch including the sensors and/or transducers and wherein the sensors may comprise ultrasound sensors (Figs. 10A-10C, [0031], [0088], [0251]). Shusterman further teaches wherein the wearable device may wirelessly communicate data to an external user terminal such as a smartphone via a Bluetooth/wi-fi radio (Figs. 10A-10C, [0176], [0221], [0247], [0251], [0284-0290], [0297]). Shusterman teaches wherein the smartphone may include a display for displaying parameters derived from data ([0109-0118]). Shusterman even further teaches wherein the external user terminal (i.e. smartphone) may receive data recorded by the sensors and communicate the data to an internet server (cloud) including a remote processing module (1080) for processing data (Fig. 10B, [0287-0292]). Moreover, Shusterman teaches wherein the smartphone may display data acquired wirelessly (Fig. 12C, [0178]) and display the results of data analysis ([0287-0291]). Shusterman teaches wherein displayed results of data processing/analysis may include arterial blood pressure ([0302]). Shusterman therefore teaches wirelessly sending data to a mobile computing device from a wearable device, the mobile computing device sending said data to a remote computer (internet server/cloud), the remote computer sending blood pressure readings (processed data) to the mobile computing device, and the mobile computing device displaying the blood pressure reading on the screen (see particularly figure 10B, [0291-0292], and [0302]).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to have the wearable patch wirelessly transmit data to a smartphone which is further transmits the data to an internet server/cloud for data processing and to display blood pressure on the screen of the phone as taught by Shusterman (Figs. 10A-10C & 12C, [0109-0118], [0178], [0287-0292], [0302]). By having the data processing done remotely, hardware requirements of the wearable and mobile devices may predictably be made lower. Moreover, data processing performed over the cloud may be more efficient (e.g. the cloud has better hardware). Furthermore, by displaying processed data such as blood pressure on the mobile device (smartphone), a user may predictably be made aware of their current physiological state and act accordingly (e.g. form a personalized training plan as recognized by Xu ‘204 [0190]). Xu ‘269 teaches wherein the data processed by the remote computer (cloud) comprises raw ultrasound data (images) and wherein blood pressure is calculated therefrom ([0011], [0043], [0061]). Therefore, Xu ‘269 modified by the teachings of Shusterman (Fig. 10B, [0292]) to include a smartphone as an intermediate between the wearable patch and remote computer, have the remote computer process data, and have the smartphone display results of the data processing would predictably result wherein the wireless radio sends the data set to the mobile computing device; the mobile computing device sends the data to the remote computer, the remote computer sends the blood pressure reading to the mobile computing device, and the mobile computing device displays the blood pressure reading on the phone screen. Moreover, because Aguirre teaches training the machine learning algorithm to derive ultrasound-derived blood pressure ([00107]), the modification would predictably result wherein once the algorithm/memory is trained, the results (ultrasound-derived blood pressure) would be sent to the mobile computing device [i.e. smart phone] for display.
However, the modified combination noted above fails to teach the blood pressure sensor wireless radio sending blood pressure data to the mobile computing device; and the mobile computing device sending blood pressure data to the remote computer.
In an analogous blood pressure monitoring system field of endeavor, Shen teaches such a feature. Shen teaches a three-stage cloud computing blood pressure monitor which uses a mobile phone as an intermediate node ([0002]). Shen teaches a blood pressure monitor (1) configured to wirelessly transmit blood pressure signals to a smart phone (2) via wireless radio (Fig. 1, [0022-0024]). Shen further teaches wherein the smart phone (2) processes the signal and wirelessly transmits the blood pressure data signal to a cloud computing server (3) [i.e. remote computer] ([0021], [0024]). Moreover, Shen teaches wherein the cloud computing server (3) performs further processing on the signal and transmits back the blood pressure measurement results to the user’s smart phone (2) ([0026]). Shen therefore teaches wherein a wireless radio sending blood pressure data to a mobile computing device [i.e. smart phone 2] and the mobile computing device sending blood pressure data to a remote computer [i.e. cloud computing server 3].
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to have the smart phone send the blood pressure data received wirelessly from the blood pressure monitor to the cloud server for processing as taught by Shen ([0002], [0022-0024], [0026]). Xu ‘269 already teaches wherein the machine learning algorithm is situated in the cloud server/remote computer ([0043]). Aguirre also teaches training a machine learning algorithm with blood pressure parameters and ultrasound data ([00107]). Shen explicitly teaches sending blood pressure data to the remote computer for processing, with the mobile phone being an intermediate node ([0002], [0022-0024], [0026]). Therefore, the combined teachings of the above seem to teach or suggest wirelessly sending blood pressure data to a smart phone and have the smart phone send the blood pressure data to a remote computer. By sending the blood pressure data to the remote computer, the machine learning algorithm which is situated at the remote computer may be trained to derive blood pressure from ultrasound data like taught by Aguirre ([00107]), and also the user can take advantage of the superior compute power and data processing capabilities that a cloud server may provide over a mobile phone as further recognized by Shen ([0028]).
However the modified combination noted above fails to teach the remote computer comparing the ultrasound data with the blood pressure data.
In an analogous measuring of blood pressure field of endeavor, Aguirre teaches such a feature. Aguirre teaches measuring blood pressure data ([0071-0072], [0074]). Aguirre teaches wherein the blood pressure monitoring device may comprise a sphygmomanometer or blood pressure cuff ([0077]). Aguirre teaches wherein the pressure measurement module (104) may include other measurement devices such as an ultrasound imaging device ([0078]). Aguirre teaches measuring physiological patient data such as ultrasound data ([0106], “cardiac flow data (e.g., Doppler ultrasound flow measurements)”, [0107], “As non-limiting examples of such physiologic patient data, pressure parameters could be derived from… ultrasound imaging”). Aguirre teaches wherein ultrasound imaging data may be related or calibrated, i.e. compared, to blood pressure data ([0107]). Aguirre therefore teaches comparing ultrasound data with blood pressure data. Aguirre further teaches wherein the computing device (1250) configured to perform the methods herein may be a server computer ([00203]), therefore teaching the remote computer comparing ultrasound data with blood pressure data.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 have the remote computing device compare ultrasound data with blood pressure data as taught by Aguirre ([0070], [0076-0077], [00107], [00128], [00203], [00207], [00209]). By relating/calibrating the measured blood pressure data received by the blood pressure sensor to ultrasound data, the need for the sphygmomanometer or cuff may be eliminated and replaced with continuous monitoring via ultrasound, improving patient comfort.
However the modified combination noted above fails to teach the blood pressure sensor concomitantly measuring blood pressure to provide blood pressure data as the high-speed analogue to digital converter is digitizing the reflected ultrasound waves to provide ultrasound data.
In an analogous blood pressure monitoring system field of endeavor, Mizukami teaches such a feature. Mizukami similarly teaches a wearable patch (10) comprising an ultrasound probe (30) and transducer (32) configured to be attached to the neck skin of a user (2) (Figs. 1-2, [0031-0036]). Mizukami teaches wherein the wearable patch (10) may measure blood pressure using the ultrasound probe (30) ([0033]). Mizukami further teaches to measure blood pressure, calibration is required with a sphygmomanometer (40) which measures blood pressure ([0034]). Mizukami teaches transmitting and receiving ultrasound waves, thus teaching collection of ultrasound data ([0052]). Mizukami teaches blood vessel diameter is calculated from the received ultrasound wave/data ([0053]). Mizukami teaches calculation of blood vessel diameter is performed in parallel (or simultaneously/concomitantly) with blood pressure measurement using the sphygmomanometer (40) (Fig. 6, [0055]). Mizukami teaches wherein collection of ultrasound data is concomitant with the sphygmomanometer 40 measuring blood pressure (Fig. 6, [0060-0062]). Figure 6 shows wherein ultrasound data is collected while blood pressure is measured by the sphygmomanometer (40) (Fig. 6, wherein S1 indicates start of ultrasound data collection, S5 indicates measurement of blood pressure using the second blood pressure monitor sphygmomanometer 40, and S23 indicates end of ultrasound data collection; measurement of blood pressure is concomitant with collection of ultrasound data (measurement of blood vessel diameter using ultrasonic wave)).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to measure blood pressure while the wearable patch collects ultrasound data as taught by Mizukami (Fig. 6, [0055], [0060-0062]). The blood pressure measured by the second blood pressure monitor or sphygmomanometer may be used for calibration and correlated with ultrasound data measured by the wearable ultrasound patch, allowing for the wearable ultrasound patch to measure blood pressure ([0034], [0037-0040]). Moreover, by concomitantly measuring the ultrasound and blood pressure data, said data may be time synchronized and easily matched or compared for training of the machine learning algorithm.
However, Xu ‘269 fails to teach the remote computer discarding spurious ultrasound data; and thus wherein the remote computer processes the remaining ultrasound data to provide the ultrasound-derived blood pressure data.
In an analogous method including training a machine learning models field of endeavor, Denison teaches such a feature. Denison teaches training machine learning models with one or more datasets and may be trained on signals measured by devices, sensors, or systems ([0057-0058]). Denison teaches wherein the training may be completed on a server or cloud computing network [i.e. remote computer] ([0052], [0054]). Denison teaches applying a preprocessing step to training data ([0067-0068]). Denison teaches wherein the preprocessing may include discarding parameters which contain spurious data to clean and normalize the data ([0068]).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to discard spurious training data as taught by Denison ([0068]). Aguirre teaches using ultrasound data as training data for the machine learning model/algorithm ([00107]). By discarding spurious training data, irregularities in the input data for training may be reduced, thereby improving robustness of the training as recognized by Denison ([0068]). Since training and processing of signals is performed by the remote computer and the ultrasound data comprises training data for the machine learning algorithm, and Xu’ 269 teaches Xu ‘269 teaches processing ultrasound data to provide ultrasound-derived blood pressure data ([0061]), Xu ‘269 modified by the teachings of Denison would predictably result in the remote computer discarding spurious ultrasound and/or blood pressure data, thereby resulting in the remote computer processing the remaining ultrasound data to provide the ultrasound-derived data.
Claim 29 is rejected under 35 U.S.C. 103 as being unpatentable over Xu ‘269 (US20220133269) in view of Xu ‘204 (US20230355204), Aguirre (WO2024163819), Shen (CN202568226; translation provided), and Denison (US20220288389) as applied to claim 21 above, and further in view of Mizukami (US20150289836).
Regarding claim 29, Xu ‘269 in view of Xu ‘204, Aguirre, Shen, and Denison teach a method of monitoring a user’s blood pressure, the method comprising: the user selecting the machine learning and blood pressure monitoring system of claim 21 (wherein Xu ‘269 in view of Xu ‘206, Aguirre, Shen, and Denison teaching the system of claim 21 comprises a user selecting said system).
Xu ‘269 teaches the method further comprising: the user providing a power source to the wearable patch ([0045]);
the user releasably attaching the wearable patch to a selected skin surface (Fig. 2A, 10A-10B, & 11, [0066], [0071], wherein the figures 10-11 show the patch mounted on a skin surface of the user’s neck and hands);
the array of ultrasound transducers emitting ultrasound waves under control of the microprocessor (MCU, 149) ([0018], [0048], [0066-0068]);
the array of ultrasound transducers (102) receiving reflected ultrasound waves (Claims 12 & 16, [0039], [0042], [0044], [0048], [0052], [0072-0073]);
the high-speed analogue to digital converter digitizing the reflected ultrasound waves to provide ultrasound data ([0043], “All the signals are amplified through the AFE 104, digitalized by ADCs in the MCU within digital circuit 106…”, [0044]); and
the wireless radio (151) sending the ultrasound data to the mobile computing device (112) (Figs. 2A & 2C, [0040], [0043], [0048], [0053]);
the memory instructing the processor to convert the ultrasound data into blood pressure data to provide ultrasound-derived data (Figs. 2A & 5, [0043], “A machine learning algorithm incorporated in the software 114… The algorithm may be situated on the smartphone”, [0061], “The blood pressure, blood flow, and cardiac pressure signals can be extracted from ultrasound images… using deep learning networks trained for semantic segmentation”, [0079], wherein smartphones include a memory, processor, wireless radio, and screens), and
once the memory is trained, to instruct the processor to display the ultrasound-derived blood pressure data on the screen (Claims 12-13, [0045], “Raw ultrasound data may be decoded into the blood pressure waveforms. Finally, the decoded waveforms may be wirelessly transmitted and visualized on a display via Bluetooth or Wi-Fi”, [0079], “The outputs may be delivered to a user by way of a video graphics card or integrated graphics chipset coupled to a display that maybe seen by a user”, [0061], “The blood pressure, blood flow, and cardiac pressure signals can be extracted from ultrasound images… using deep learning networks trained for semantic segmentation”).
However, Xu ‘269 fails to teach the blood pressure sensor concomitantly measuring blood pressure to provide blood pressure data as the high-speed analogue to digital converter is digitizing the reflected ultrasound waves to provide ultrasound data.
In an analogous blood pressure monitoring system field of endeavor, Mizukami teaches such a feature. Mizukami similarly teaches a wearable patch (10) comprising an ultrasound probe (30) and transducer (32) configured to be attached to the neck skin of a user (2) (Figs. 1-2, [0031-0036]). Mizukami teaches wherein the wearable patch (10) may measure blood pressure using the ultrasound probe (30) ([0033]). Mizukami further teaches to measure blood pressure, calibration is required with a sphygmomanometer (40) which measures blood pressure ([0034]). Mizukami teaches transmitting and receiving ultrasound waves, thus teaching collection of ultrasound data ([0052]). Mizukami teaches blood vessel diameter is calculated from the received ultrasound wave/data ([0053]). Mizukami teaches calculation of blood vessel diameter is performed in parallel (or simultaneously/concomitantly) with blood pressure measurement using the sphygmomanometer (40) (Fig. 6, [0055]). Mizukami teaches wherein collection of ultrasound data is concomitant with the sphygmomanometer 40 measuring blood pressure (Fig. 6, [0060-0062]). Figure 6 shows wherein ultrasound data is collected while blood pressure is measured by the sphygmomanometer (40) (Fig. 6, wherein S1 indicates start of ultrasound data collection, S5 indicates measurement of blood pressure using the second blood pressure monitor sphygmomanometer 40, and S23 indicates end of ultrasound data collection; measurement of blood pressure is concomitant with collection of ultrasound data (measurement of blood vessel diameter using ultrasonic wave)).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to measure blood pressure while the wearable patch collects ultrasound data as taught by Mizukami (Fig. 6, [0055], [0060-0062]). The blood pressure measured by the second blood pressure monitor or sphygmomanometer may be used for calibration and correlated with ultrasound data measured by the wearable ultrasound patch, allowing for the wearable ultrasound patch to measure blood pressure ([0034], [0037-0040]). Moreover, by concomitantly measuring the ultrasound and blood pressure data, said data may be time synchronized and easily matched or compared for training of the machine learning algorithm.
However, the modified combination noted above fails to teach the blood pressure sensor wireless radio sending blood pressure data to the mobile computing device.
In an analogous blood pressure monitoring system field of endeavor, Shen teaches such a feature. Shen teaches a three-stage cloud computing blood pressure monitor which uses a mobile phone as an intermediate node ([0002]). Shen teaches a blood pressure monitor (1) including an A/D converter 15 and a single-chip microcomputer (16) which may utilize a wireless Bluetooth or Wi-Fi connection for connecting to a module (21) of a smart phone (2) (Fig. 1, [0022], [0024]). Shen teaches the blood pressure monitor (1) may measure blood pressure signals and wirelessly transmit the blood pressure signal to the smart phone (2) ([0023]). Shen therefore teaches a wireless radio (wireless Bluetooth/Wi-Fi compatibility) for sending blood pressure data to a mobile computer device (smart phone 2).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to have the blood pressure sensor transmit blood pressure data to the mobile computing device as taught by Shen (Fig. 1, [0022-0024]). By transmitting the blood pressure data to the smart phone for the smart phone, the data may be used to train/relate the blood pressure data to ultrasound data via machine learning which is earlier taught by Xu ‘269 in view of Aguirre.
However, the modified combination noted above fails to teach the memory instructing the processor to compare ultrasound data with blood pressure data.
In an analogous measuring of blood pressure field of endeavor, Aguirre teaches such a feature. Aguirre teaches measuring blood pressure data ([0071-0072], [0074]). Aguirre teaches wherein the blood pressure monitoring device may comprise a sphygmomanometer or blood pressure cuff ([0077]). Aguirre teaches wherein the pressure measurement module (104) may include other measurement devices such as an ultrasound imaging device ([0078]). Aguirre teaches measuring physiological patient data such as ultrasound data ([0106], “cardiac flow data (e.g., Doppler ultrasound flow measurements)”, [0107], “As non-limiting examples of such physiologic patient data, pressure parameters could be derived from… ultrasound imaging”). Aguirre teaches wherein ultrasound imaging data may be related or calibrated, i.e. compared, to blood pressure data ([0107]). Aguirre therefore teaches comparing ultrasound data with blood pressure data. In addition, Aguirre teaches wherein a computing device (1250) comprising a smartphone may be used to implement the methods described above (Fig. 2B, [00201], “In some configurations, computing device 1250 can execute at least a portion of a cardiovascular measurement system 1204 to calculate Pcrit or TPP using the methods described herein”, wherein the step described in ¶ [00107] is part of calculating Pcrit, as further evidenced by figure 2B, [00203], “a smartphone”).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to compare ultrasound data with blood pressure data as taught by Aguirre ([00107]). By relating/calibrating the measured blood pressure data received by the blood pressure sensor to ultrasound data, the need for the sphygmomanometer or cuff may be eliminated and replaced with continuous monitoring via ultrasound, improving patient comfort.
However, the modified combination noted above fails to teach the memory instructing the processor to discard spurious ultrasound data; and thus wherein converting the ultrasound data to provide the ultrasound-derived blood pressure data converts the remaining ultrasound data.
In an analogous method including training a machine learning models field of endeavor, Denison teaches such a feature. Denison teaches training machine learning models with one or more datasets and may be trained on signals measured by devices, sensors, or systems ([0057-0058]). Denison teaches applying a preprocessing step to training data ([0067-0068]). Denison teaches wherein the preprocessing may include discarding parameters which contain spurious data to clean and normalize the data ([0068]).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the invention of Xu ‘269 to discard spurious training data as taught by Denison ([0068]). Aguirre teaches using ultrasound data as training data for the machine learning model/algorithm ([00107]). By discarding spurious training data, irregularities in the input data for training may be reduced, thereby improving robustness of the training as recognized by Denison ([0068]). Since the machine learning algorithm is situated in the mobile computing device as taught by Xu ‘269 ([0043]), processing of signals is performed by the mobile computing device, and the ultrasound data comprises training data for the machine learning algorithm, Xu ‘269 in view of Aguirre modified by the teachings of Denison would predictably result in the memory of the mobile computing device instructing the processor to discard spurious ultrasound and/or blood pressure data. And since Xu ‘269 teaches processing ultrasound data to provide ultrasound-derived blood pressure data ([0061]), Xu ‘269 modified by the teachings of Denison to discard spurious ultrasound and/or blood pressure data would result in in the mobile computing device converting the remaining ultrasound data to provide the ultrasound-derived data.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TOMMY T LY whose telephone number is (571)272-6404. The examiner can normally be reached M-F 12:00pm-8:00pm eastern time.
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, Anhtuan Nguyen can be reached at 571-272-4963. 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.
/TOMMY T LY/ Examiner, Art Unit 3797
/SERKAN AKAR/ Primary Examiner, Art Unit 3797
Prosecution Insights