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 .
Status of Claims
Claims 1-10 are presently pending and under examination.
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 1-10 are rejected under 35 U.S.C. 101 because the claimed invention is directed to judicial exception, specifically an abstract idea without significantly more.
Step 1
Claims 1-10 are directed to statutory subject matter as the claims recite a system.
Step 2A, Prong One:
Claim 1 recites the limitations of:
A system comprising:
an electrocardiogram (ECG) sensor, configured to obtain an ECG signal related to a user;
a photoplethysmography (PPG) sensor, configured to obtain a PPG signal related to the user; and
a processing circuit, electrically connected to the ECG sensor and the PPG sensor and configured to generate a cardiac assessment result according to the PPG signal sensed during a first time period and the ECG signal sensed during a second time period, wherein the first time period is longer than the second time period.
These above limitations, under their broadest reasonable interpretation, are merely a mental process because these steps are akin to having a doctor or other human actor performing a medical diagnosis of a patient and mentally evaluating sensed data. Therefore, these steps may be performed mentally by a human actor. If claim limitations, under the broadest reasonable interpretation, cover performance of the limitation as a mental process, then it falls within the “Mental Processes” group of abstract ideas.
Claims 2-10 depend from claim 1. The dependent claims only recite additional features of the process of analyzing the data and the type of output generated. For example, claim 2 recites “input the ECG signal into a first machine learning model to generate a first feature vector…” and claim 9 recites “the cardiac assessment result comprises a survival curve and a risk score”. These limitations and other limitations of the dependent claims are merely a substitution of the data that is already mentioned in claim 1.
Step 2A, Prong Two
For claim 1, the judicial exception is not integrated into a practical application. In particular, claim 1 recites “an electrocardiogram (ECG) sensor”, “a photoplethysmography (PPG) sensor”, and a “processing circuit”.
These additional elements are recited at a high-level of generality (i.e. most generical computer and medical systems would be known to have these components for sensing, general computation, processing sensed data, and outputting data), and they amount to no more than mere pre-solution activity of data gathering from a sensor. This pre-solution activity of data gathering using sensors such as ECG sensor and PPG sensor are known in the field of medical sensing and computing technology. For example, see Velo (US 2020/0100693 A1), hereinafter Velo which discloses an electrocardiogram (ECG) sensor (ECG sensor 128), a photoplethysmography (PPG) sensor (a PPG sensor 122), and a processing circuit (processor 204). Therefore, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Thus, the claims are directed to an abstract idea. As described above, claims 1-10 are merely a mental process, because these steps are akin to having a doctor or other human actor performing a medical diagnosis of a patient and evaluating sensed data, which may be done mentally by a human actor.
Additionally, Claim 2 and 4 recite using machine learning models as a tool to perform an abstract idea, which is not indicative of integration into a practical application. MPEP 2106.05(f). This limitation is understood to be generic computer equipment and mere instructions to implement an abstract idea on a computer, or merely used a computer as a tool to perform an abstract idea – see MPEP 2106.05(F).
Step 2B
The claims do not include additional elements that are that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integration of the judicial exception into a practical application (Step 2A- Prong Two), the additional elements of “an electrocardiogram (ECG) sensor”, “a photoplethysmography (PPG) sensor”, and a “processing circuit” to gather and analyze sensed data amount to no more than mere instruction to apply the exception using known and generic elements and then outputting the results using known computing elements. Further, simply appending well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract ide requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known to the industry, as discussed in Alice Corp., 573 U.S. at 225, 110 USPQ2d at 1984 (see MPEP § 2106.05 (d)). In this case, elements of general computer are being used to implement the abstract idea.
For example, see Velo (US 2020/0100693 A1), hereinafter Velo which discloses an electrocardiogram (ECG) sensor (ECG sensor 128), a photoplethysmography (PPG) sensor (a PPG sensor 122), and a processing circuit (processor 204). Therefore, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Merely including instruction to implement an idea on a computer does not integrate a judicial exception into practical application.
Claims 2-10 depend on claim 1. These dependent claims only recite additional features of the machine learning model used for analyzing the data, template generation, and types of output, which is merely a recitation of a tool to perform an abstract data. Overall, these limitations encompass nothing more than a physician/human actor inputting data into a mathematical model and outputting a result from the model. These dependent claims recite a generic computer recited at a high level of generality and fail to discuss any additional elements beyond those discussed in independent claims and this for similar reasons as discussed in the independent claim, these dependent claims still recite an abstract idea without significantly more.
Therefore, these claims do not amount to significantly more than the abstract idea itself, and thus claims 1-10 are not patent eligible under 35 USC 101.
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 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.
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.
Claim(s) 1 and 5 is/are rejected under 35 U.S.C. 102(a)(1) as anticipated by or, in the alternative, under 35 U.S.C. 103 as obvious over Velo (US 2020/0100693 A1), hereinafter Velo.
Regarding claim 1, Velo discloses a system (user-wearable device 102) comprising: an electrocardiogram (ECG) sensor (ECG sensor 128), configured to obtain an ECG signal related to a user ([0057] “an ECG signal (obtained using the ECG sensor 128).”) ; a photoplethysmography (PPG) sensor (a PPG sensor 122), configured to obtain a PPG signal related to the user ([0057] “a PPG signal (obtained using the PPG sensor 122)”); and a processing circuit (processor 204), electrically connected to the ECG sensor and the PPG sensor (Figure 2, [0045] “a microcontroller 202 that includes a processor 204… The microcontroller 202 is shown as receiving signals from each of the aforementioned sensors 122, 124, 126, 128, 130 and 132”) and configured to generate a cardiac assessment result according to the PPG signal sensed during a first time period and the ECG signal sensed during a second time period (Figure 6, [0110] “The ECG and PPG signals can be used by a physiological engine, along with sleep metrics and physical activity levels, that works in conjunction with the arrhythmia statistic/machine learning analytical modules, to assist in the inference and or confirmation of an arrhythmic event.”), wherein the first time period ([0088] PPG monitoring period)is longer than the second time period ([0094] ECG monitoring period, [0075]-[0076] “"in order to obtain an ECG using a wrist worn user-wearable device, the wearer must touch an electrode on the device (e.g., the electrode 114 on the device) with a finger on the hand of the arm that is not wearing the device (to complete a circuit)...Accordingly, it is not practical for a wrist worn user-wearable device, such as the device 102, to monitor for arrhythmias over a prolonged period of time based on an ECG signal, since it is not practical for a wrist worn user-wearable device to substantially or pseudo continuously obtain an ECG signal....Wrist worn user-wearable devices, such as the device 102, which include an optical sensor (e.g., 122) capable of obtaining a PPG signal (also referred to as a PPG sensor 122), can be used to obtain a PPG signal for prolonged periods of time because there is no requirement that a user do anything other than wear the device on one of their wrists in order for the device to be capable of obtaining a PPG signal.”, emphasis added, Examiner would like to note that “prolonged periods of time” is necessarily longer than “not practical…over a prolonged period of time” ).
Alternatively, it would be obvious to one skilled in the art to have the first time period be longer than the second time period, as Velo states that PPG signals can be measured over prolonged periods of time ([0076]) whereas ECG is obtained occasionally and not over a prolonged period of time ([0075]) as it would not be practical, thus it would be obvious to one skilled in the art that a first time period would be longer than a second time period.
Additionally, it would have been obvious to try, by one of ordinary skill in the art before the effective filing date of the claimed invention, to choose to have the first time period be longer than the second time period and incorporate it into the system of Velo since there are a finite number of identified, predictable potential solutions (i.e., the first time period is the same as the second time period, the first time period is longer, and the second time period is longer) to the recognized need (data collection) and one of ordinary skill in the art would have pursued the known potential solutions with a reasonable expectation of success. Therefore, “When there is a design need or market pressure to solve a problem and there are a finite number of identified, predictable solutions, a person of ordinary skill has good reason to pursue the known options within his or her technical grasp. If this leads to the anticipated success, it is likely the product not of innovation but of ordinary skill and common sense. In that instance the fact that a combination was obvious to try might show that it was obvious under 103” KSR Int' l Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007).
Regarding claim 5, Velo discloses the system of claim 1 (as shown above), wherein the processing circuit is configured to recognize a plurality of R peaks in the ECG signal, calculate a plurality of RR intervals among the R peaks ([0065] “shown in FIG. 3 are various different intervals and segments that can be measured from an ECG signal, such as the ECG signal 302. These various intervals and segments are examples of features of an ECG signal. These include the PR interval, the QT interval, the RR interval, the PR segment, and the ST segment., and calculate a plurality of ECG features according to the RR intervals”, view Figure 3), and calculate a plurality of ECG features according to the RR intervals ([0065]” HR in beats per minute (bpm) can be determined by measuring a plurality of RR intervals, calculating an average RR interval, and dividing the number sixty (60) by the average RR interval. RR intervals can also be used to measure heart rate variability (HRV), which is the physiological phenomenon of variation in the time interval between heartbeats”)wherein the processing circuit is configured to detect a plurality of beats from the PPG signal, calculate a plurality of beat intervals according to the beats ([0068] “the present technology, various features of a PPG signal, such as the PPG signal 402, can be measured and used to monitor for cardiac arrhythmias. Exemplary features of a PPG signal can include an average peak to peak interval and a peak to peak interval variability. The peak to peak interval of a PPG signal is the period between peaks (maximums) in a PPG waveform, and is indicative of the heart rate (HR),… HR in beats per minute (bpm) can be determined by measuring a plurality of RR′ intervals, calculating an average RR′ interval, and dividing the number sixty (60) by the average RR′ interval.”, view Figure 4), and calculate a plurality of PPG features according to the beat intervals ([0052] “The HR detector 218 can use signals and/or data obtained from the PPG sensor 122 to detect HR. For example, the optical sensor 222 can be used to obtain a PPG signal from which peak-to-peak intervals can be detected, which can also be referred to as beat-to-beat intervals. The beat-to-beat intervals, which are intervals between heart beats, can be converted to HR using the equation HR=(1/beat-to-beat interval)*60, with beat-to-beat interval expressed in seconds and HR expressed in beats-per-minute (bpm).”), wherein the processing circuit is configured to input the ECG features and the PPG features into a machine learning model to generate the cardiac assessment result.”, [0040])
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over Velo as applied to claim 1 above, and further in view of Yoo (KR 2024/0141029 A), hereinafter Yoo.
Regarding claim 2, Velo discloses the system of claim 1 (as shown above). Velo fails to disclose wherein the processing circuit is configured to input the ECG signal into a first machine learning model to generate a first feature vector, wherein the processing circuit is configured to detect a plurality of beats from the PPG signal, calculate a plurality of beat intervals according to the beats, and input the beat intervals into a second machine learning model to generate a second feature vector, wherein the processing circuit is configured to input the first feature vector and the second feature vector into a third machine learning model to generate the cardiac assessment result.
However, Yoo teaches measuring the health status of a subject by a biosensor and analyzing the data using artificial intelligence to identify health risk factors of the subject wherein the processing circuit is configured to input the ECG signal into a first machine learning model to generate a first feature vector (Figure 10b, [0241] “feature vector extraction unit 1 (33a) extracts a feature vector from an ECG signal (69a)”, [0244] “The feature vectors of the above ECG signal (69a), PPG signal (68), and PCG signal (69b) can be extracted by a deep learning neural network”), wherein the processing circuit is configured to detect a plurality of beats from the PPG signal, calculate a plurality of beat intervals according to the beats, and input the beat intervals into a second machine learning model to generate a second feature vector ([0241] “feature vector extraction unit 2 (33b) extracts a feature vector from a PPG signal (68)”, [0244] “The feature vectors of the above ECG signal (69a), PPG signal (68), and PCG signal (69b) can be extracted by a deep learning neural network”), wherein the processing circuit is configured to input the first feature vector and the second feature vector into a third machine learning model to generate the cardiac assessment result (view Figure 10b: the output of the feature vector extraction units are transmitted to a classifier 21(a), [0239] “[Figures 10b to 10c are several examples of an artificial intelligence neural network (16) that measures blood pressure, cholesterol, blood sugar, and heart disease by a classifier (21a) using an ECG signal (69a), a PPG signal (68)”, [0251] “These feature vectors are input….into a classifier (21a) to calculate…heart disease”, [0252] “The classifier (21a) of the present invention may be a FCN (Fully Connected Network) or an SVM (Support Vector Machine)”)
It would have been prima facie obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Velo to incorporate the teachings of Yoo to have the processing circuit is configured to input the ECG signal into a first machine learning model to generate a first feature vector, wherein the processing circuit is configured to detect a plurality of beats from the PPG signal, calculate a plurality of beat intervals according to the beats, and input the beat intervals into a second machine learning model to generate a second feature vector, wherein the processing circuit is configured to input the first feature vector and the second feature vector into a third machine learning model to generate the cardiac assessment result, as these prior art references are directed to using ECG and PPG signals for cardiac health. One would be motivated to do this so the third machine learning model can be provided with more accurate/reduced data that is indicative of the cardiac condition allowing for an efficient and accurate analysis.
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Velo in view of Yoo as applied to claim 2 above, and further in view of Miao et al. (US 2018/0279891 A1), hereinafter Miao.
Regarding claim 3, Velo in view of Yoo teaches the system of claim 2 (as shown above). Velo and Yoo, alone or in combination, fail to teach wherein the first time period comprises a plurality of sub-periods, the processing circuit is configured to select the beats sensed in a time segment from each of the sub-periods, and calculate the beat intervals according to the selected beats.
However, Miao teaches a medical monitoring device and method for arrhythmia detection using PPG signals wherein “the method 200 divides the PPG signal samples into PPG signal segments. In one embodiments, the method 200 divides the PPG signal samples into PPG signal segments having a given time duration, such as t number of seconds” ([0055]) and “the method 200 extract inter-beat interval features in each PPG signal segment.” ([0057]).
It would have been prima facie obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Velo and Yoo to incorporate the teachings of Miao to have the first time period comprises a plurality of sub-periods, the processing circuit is configured to select the beats sensed in a time segment from each of the sub-periods, and calculate the beat intervals according to the selected beats, as these prior art references are directed to using PPG for predicting/detecting heart conditions. One would be motivated to do this as these short segments can be easily obtained and analyzed, additionally beat intervals better represent the characteristics of arrhythmias and result in significant improvement in detection performance, as recognized by Miao ([0034]).
Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Velo in view of Yoo as applied to claim 2 above, and further in view of Ravishankar et al. (US 2023/0238134 A1), hereinafter Ravishankar.
Regarding claim 4, Velo in view of Yoo teaches the system of claim 2 (as shown above). Velo and Yoo, alone or in combination, fail to teach wherein the first machine learning model is a convolutional neural network, the second machine learning model is a transformer, and the third machine learning model is a multilayer perceptron network.
However, Ravishankar teaches a method and system for predicting cardiac arrhythmias based on multi-modal patient monitoring data via deep learning wherein the first machine learning model is a convolutional neural network ([0043]-[0044] “the ECG data may be divided into segments obtained over a pre-determined duration, and each segment may be transformed into the frequency domain (e.g., via a Fourier transform) to generate two-dimensional (2D) spectrograms 314… The (concatenated) 2D spectrograms 314 may be input into the 2D CNN 316”), the second machine learning model is a transformer ([0047] “the temporally varying feature set 302 may comprise features describing the morphology and amplitude of the PPG waveform for each beat.”, [0040] “the transformer network 304 differentially weights a significance of each part of the input temporally varying feature set 302”), and the third machine learning model is a multilayer perceptron network ([0038] “The outputs of each of the three parallel neural network arms are combined and input into an MLP 320 (e.g., a fourth subnetwork) in series with the three parallel neural network arms, which determines whether or not the input data indicates that a cardiac arrhythmia is expected to occur.”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed inventions to have modified Velo and Yoo to substitute the machine learning models of Yoo with the machine learning models of Ravishankar to have the first machine learning model is a convolutional neural network, the second machine learning model is a transformer, and the third machine learning model is a multilayer perceptron network, as these prior art references are directed to using cardiac signals for cardiac condition assessment. One would be motivated to do this as a combination of these machine learning models allows for a more efficient and accurate analysis, as recognized by Ravishankar ([0045]).
Claim(s) 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over Velo as applied to claim 5 above in view of Jung (US 2023/0190167 A1), hereinafter Jung further in view of Arteaga-Falconi, Juan S., Hussein Al Osman, and Abdulmotaleb El Saddik. "ECG and fingerprint bimodal authentication." Sustainable cities and society 40 (2018): 274-283., hereinafter Arteaga-Falconi.
Regarding claim 6, Velo discloses the system of claim 5 (as shown above). Velo fails to disclose wherein the processing circuit is configured to recognize a plurality of cardiac cycles from the ECG signal, and align the cardiac cycles based on the R peaks to generate a template cycle, wherein the processing circuit is configured to recognize a template P peak, a template Q peak, a template R peak, a template S peak, and a template T peak in the template cycle, wherein the processing circuit is configured to calculate a time difference between the template R peak and one of the template P peak, the template Q peak, the template S peak and the template T peak as one of the ECG features.
However, Jung discloses wherein the processing circuit is configured to recognize a plurality of cardiac cycles from the ECG signal ([0129] “The biometric signal module (e.g., the biometric signal module 621 of FIG. 6) may segment the synchronized second biometric information S3 based on the peaks P of the first biometric information S1…By segmenting the second biometric information S3, the biometric signal module 621 may generate a plurality of electrocardiogram segments F1, F2, F3, and F4”), and align the cardiac cycles to generate a template cycle ([0130] “The biometric signal module 621 may align the plurality of electrocardiogram segments F1, F2, F3, and F4. For example, the biometric signal module 621 aligns the plurality of electrocardiogram segments F1, F2, F3, and F4 based on the peak P timing (or time stamp)… The biometric signal module 621 may generate an electrocardiogram template ST using the valid electrocardiogram segments F1, F2, and F3. The biometric signal module 621 may generate the electrocardiogram template ST by averaging the valid electrocardiogram segments F1, F2, and F3.”), wherein the processing circuit is configured to recognize a template P peak, a template Q peak, a template R peak, a template S peak, and a template T peak in the template cycle (view Figure 13, [0141] “An electrocardiogram template graph 1303 of FIG. 13 may be generated by averaging the electrocardiogram segments of the overlapping graph 1301. In the electrocardiogram template graph 1303, it can be seen that not only QRS complexes, but also the P wave and the T wave appear clearly.”, electrocardiogram template 299), wherein the processing circuit is configured to calculate a time difference between the template R peak and one of the template P peak, the template Q peak, the template S peak and the template T peak as one of the ECG features ([0067] “The electrocardiogram template 299 may include various health information. Abnormalities of each waveform included in the electrocardiogram template 299 may be derived from various diseases. For example, an abnormal P wave may occur due to an abnormality of the left atrium and/or the right atrium. In addition, the time interval between the respective waveforms may increase and/or decrease due to various diseases. For example, the time between the start point of the P wave and the start point of the QRS complex may increase due to atrioventricular block”)
It would have been prima facie obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Velo to incorporate the teachings of Jung to have the processing circuit is configured to recognize a plurality of cardiac cycles from the ECG signal, and align the cardiac cycles based on the R peaks to generate a template cycle, wherein the processing circuit is configured to recognize a template P peak, a template Q peak, a template R peak, a template S peak, and a template T peak in the template cycle, wherein the processing circuit is configured to calculate a time difference between the template R peak and one of the template P peak, the template Q peak, the template S peak and the template T peak as one of the ECG features, as these prior art references are directed to analyzing signals for cardiac assessment. One would be motivated to do this as these features can help determine irregularities in cardiac health, as recognized by Jung ([0067]).
Velo and Jung, alone or in combination, fail to teach aligning the cardiac cycles based on the R peaks to generate a template cycle.
However, Arteaga-Falconi teaches generating an ECG template (Figure 2) which teaches aligning the cardiac cycles based on the R peaks to generate a template cycle (pg. 277, 3.1. Fingerprint and ECG biometric algorithms: “2. Extract each complete heartbeat from the signal and align it around
a reference point, (in this case the R peak) (Fig. 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 substituted Jung’s alignment with Arteaga-Falconi’s alignment using R-peaks, as these prior art references are directed to generating ECG templates. One would be motivated to do this as the R-peak is relatively easy to detect compared to other fiducial points.
Note: Examiner would also like to make note of prior art reference: Lee, Seungmin, and Daejin Park. "Efficient template cluster generation for real-time abnormal beat detection in lightweight embedded ECG acquisition devices." IEEE Access 9 (2021): 70596-70605. which discloses generating a template cluster for abnormal beat detection wherein Figure 3 shows R-peak aligned segments for template generation.
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Velo as applied to claim 5 above in view of Jung in view of Arteaga-Falconi further in view of Keenan (US 2023/0218219 A1), hereinafter Keenan.
Regarding claim 7, Velo in view of Jung further in view of Arteaga-Falconi teaches the system of claim 6 (as shown above). Velo, Jung, and Arteaga-Falconi, alone or in combination, fail to explicitly teach wherein the processing circuit is configured to calculate an amplitude difference between a baseline amplitude and one of the template P peak, the template Q peak, the template R peak, the template S peak, and the template T peak as one of the ECG features.
However, Keena teaches a system and method for achieving optimal sensor placement and enhanced signal quality for monitoring biological data wherein “The calculated maternal or fetal ECG template is shown in FIG. 5, where each of the features such as the P wave amplitude, Q wave amplitude, R wave amplitude, S wave amplitude, T wave amplitude, PQ interval, PR interval, QRS interval, RR interval, P/QRS ratio, and T/QRS ratio, and the like may be calculated with the aid of an algorithmic waveform annotator.” ([0081]).
It would be prima facia obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Velo, Jung, and Arteaga-Falconi to incorporate the teachings of Keena to have the processing circuit is configured to calculate an amplitude difference between a baseline amplitude and one of the template P peak, the template Q peak, the template R peak, the template S peak, and the template T peak as one of the ECG features. One would be motivated to do this as these features can provide great insight to heart condition.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Velo in view of Jung in view of Arteaga-Falconi in view of Keena as applied to claim 7 above, and further in view of Kyal et al. (US 2014/0323888 A1), hereinafter Kyal.
Regarding claim 8, Velo in view of Jung in view of Arteaga-Falconi in view of Keena teaches the system of claim 7 (as shown above). Velo, Jung, Arteaga-Falconi, and Keena, alone or in combination, fail to teach wherein the first time period comprises a plurality of sub-periods, the processing circuit is configured to select the beats sensed in a time segment from each of the sub-periods, and concatenate the selected beats to calculate the beat intervals.
However, Kyal teaches a system and method for extracting photoplethysmographic (PPG) signal on a continuous basis to monitor cardiac function wherein “A time-series signal obtained from video images captured of a region of exposed skin where a photoplethysmographic (PPG) signal of a subject of interest can be registered. A sliding window is then used to define consecutive sequential segments of the time-series signal for processing. Then, each of the consecutive time-series signal segments is detrended such that low frequency variations and non-stationary components are removed… The processed PPG signal segments are stitched together to obtain a continuous PPG signal for the subject. The continuous PPG signal is analyzed for beat-to-beat intervals such that a cardiac arrhythmia for the subject can be detected” ([0008]).
It would have been prima facie obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Velo, Jung, Arteaga-Falconi, and Keena to incorporate the teachings of Kyal to have wherein the first time period comprises a plurality of sub-periods, the processing circuit is configured to select the beats sensed in a time segment from each of the sub-periods, and concatenate the selected beats to calculate the beat intervals, as these prior art references are directed to processing cardiac signals for determining heart conditions. One would be motivated to do this as to reliably extract the beat-to-beat intervals and effectively detect cardiac arrhythmia, as recognized by Kyal ([0007]).
Claim(s) 9-10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Velo as applied to claim 1 above, and further in view of Trayanova et al. (US 2025/0037874 A1), hereinafter Trayanova.
Regarding claim 9, Velo discloses the system of claim 1 (as shown above). Velo fails to disclose wherein the cardiac assessment result comprises a survival curve and a risk score, and the survival curve comprises a plurality of probabilities of not experiencing a heart failure on a time axis.
However, Trayanova teaches computer-implemented neural network techniques for predicting patient-specific arrhythmic sudden cardiac death survival wherein “System 100 includes a deep learning framework that incorporates multiple custom neural subnetworks, including convolutional subnetwork 110 and dense subnetwork 114, that accept different data types, and utilize statistical survival analysis, to predict patient-specific probabilities of SCDA at future time points…the survival probability data included two parameters: location (μ) and scale (σ), which fully characterize a log-logistic probability distribution 116 of the patient-specific time to SCDA. The survival probability data (e.g., μ and σ as estimated by each branch and then combined by ensembling subnetwork 120) are then used to generate arrhythmic sudden cardiac death survival prediction data, which may include, by way of non-limiting example, a patient-specific SCDA survival curve, a patient-specific probability distribution representing time of predicted SCDA, and/or a patient-specific probability of SCDA at a particular point in time.” ([0025], view Figure 1, emphasis added).
It would have been prima facie obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Velo to incorporate the teachings of Trayanova to have the cardiac assessment result comprises a survival curve and a risk score, and the survival curve comprises a plurality of probabilities of not experiencing a heart failure on a time axis, as these prior art references are directed to using machine learning models to analyze cardiac signals to output an assessment. One would be motivated to do this to transform clinical decision-making by offering accurate, generalizable, and interpretable predictions of patient-specific survival probabilities of arrhythmic death over time, as recognized by Trayanova ([0023]).
Regarding claim 10, Velo in view of Trayanova discloses the system of claim 9 (as shown above). Velo fails to disclose wherein the processing circuit is configured to generate the risk score according to the probability at a predetermined time on the time axis.
However, Trayanova teaches “The survival probability data (e.g., μ and σ as estimated by each branch and then combined by ensembling subnetwork 120) are then used to generate arrhythmic sudden cardiac death survival prediction data, which may include, by way of non-limiting example, a patient-specific SCDA survival curve, a patient-specific probability distribution representing time of predicted SCDA, and/or a patient-specific probability of SCDA at a particular point in time.” ([0025]) and “As shown in both charts 402, 404, the survival curves estimated by the reduction to practice accurately predicted the event probabilities: in the first case, the estimated survival probability crosses the 50% threshold close to the event time; in the censored case, the reduction to practice predicts >80% probability of survival at the time of the (non-SCDA) event. For the patient with SCDA, the reduction to practice curve crosses the 50% survival probability threshold significantly closer to the SCDA time, as compared to the alternative curves, highlighting the reduction to practice's high calibration. For the censored patient (whose data included no SCDA), the reduction to practice estimates higher survival probability at the time of non-SCDA event compared to a different representative Cox-based technique.” ([0038]).
It would have been prima facie obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Velo to incorporate the teachings of Trayanova to have the processing circuit is configured to generate the risk score according to the probability at a predetermined time on the time axis. One would be motivated to do this to transform clinical decision-making by offering accurate, generalizable, and interpretable predictions of patient-specific survival probabilities of arrhythmic death over time, as recognized by Trayanova ([0023]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Wong et al. (WO 2023/082402 A1) teaches separate analysis methods for ECG and PPG before a fusion of the vectors in a third machine learning model ([0032], [0085],[0087])
Lee, Seungmin, and Daejin Park. "Efficient template cluster generation for real-time abnormal beat detection in lightweight embedded ECG acquisition devices." IEEE Access 9 (2021): 70596-70605. which discloses generating a template cluster for abnormal beat detection wherein Figure 3 shows R-peak aligned segments for template generation.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ATTIYA SAYYADA HUSSAINI whose telephone number is (703)756-5921. The examiner can normally be reached Monday-Friday 8:00 am - 5:00 pm.
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, Niketa Patel can be reached at 5712724156. 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.
/ATTIYA SAYYADA HUSSAINI/Examiner, Art Unit 3792
/NIKETA PATEL/Supervisory Patent Examiner, Art Unit 3792