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 1-24 are rejected.
Response to Arguments
Claim Rejections - 35 USC § 101
Applicant's arguments filed 3/4/26 have been fully considered but they are not persuasive.
Applicant asserts that the claims meet the example xiv criteria of improving system performance (a medical system’s classification and detection performance) based upon adjustments to parameters (filter parameters) of a machine learning model associated with tasks or workstreams. However, the Examiner disagrees. The limitations are directed to the abstract idea, because they are choices about how to do the data analysis rather than something about how the AI itself is configured or coded.
Applicant further asserts that in view of Desjardins, Applicant’s claims similarly impact how the machine learning model itself would function in operation and are therefore not subsumed in the mathematical calculation. However, the Examiner disagrees. The limitations are directed to the abstract idea, because they are choices about how to do the data analysis rather than something about how the AI itself is configured or coded.
Claim Rejections - 35 USC § 103
Applicant’s arguments with respect to claims 1-24 have been considered but are moot in view of the new ground of rejection. Applicant asserts that none of the applied references teach to derive a filter from prior cardiac EGM data of the patient, based on the feature set of the patient, wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data. Newly applied reference US 20200357518 teaches these limitations. See the rejection below for further details.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 3/4/26 is being considered by the examiner.
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 1-24 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception, specifically an abstract idea without significantly more.
Step 1
The claimed invention in claims 1-24 are directed to statutory subject matter as the claims recite a medical system, method, and non-transitory computer-readable storage medium for indicating a positive detection of the cardiac arrhythmia.
Step 2A, Prong One
Regarding claims 1, 17, 20, and 23, the recited steps are directed to certain methods of organizing human activity and a mental process of performing concepts in a human mind or by a human using a pen and paper (see MPEP 2106.04(a)(2) subsections (II) and (III)).
Regarding claims 1, 17, 20, and 23, the limitations of “generate signal data to represent the cardiac activity of the patient, at least one filter tailored to a feature set of the patient and configured for application to at least one portion of signal data representative of the sensed cardiac activity of the patient, the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient, wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data, detect a cardiac arrhythmia, and generate output data” are a process, as drafted, covers performance of the limitation that can be performed by a human mind (including an observation, evaluation, judgment, opinion) under the broadest reasonable standard. For example, these limitations are nothing more than a medical professional receiving printouts of cardiac activity data, evaluating the specific application of analysis for the patient cardiac activity data based on the patient’s prior cardiac electrogram (EGM) data, using data from a second patient with similar characteristics to the patient, evaluating the classification data, using judgment to determine the presence of a cardiac arrhythmia, and writing down the confirmation of a cardiac arrhythmia.
Regarding claims 1, 17, 20, and 23, the limitation of “generate output data” can also be interpreted as organizing human activity of managing personal behavior or relationships or interactions between people, (including social activities, teaching, and following rules or instructions) since this limitation is nothing more than a medical professional communicating that a patient has a cardiac arrhythmia.
Step 2A, Prong Two
For claims 1, 17, 20, and 23, the judicial exception is not integrated into a practical application. In particular, claims 1, 17, 20, and 23 recite “one or more sensors, sensing circuitry, a storage device, processing circuitry, and a machine learning model.” The one or more sensors and sensing circuitry amount to nothing more than pre-solution activity of data gathering. The storage device and processing circuitry are recited at a high-level of generality and amounts to nothing more than parts of a generic computer. Additionally, Applicant includes a machine learning model which is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting. Merely including instructions to implement an abstract idea on a computer does not integrate a judicial exception into practical application.
Step 2B
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into
a practical application, the additional elements of one or more sensors and sensing circuitry amount to no more than mere pre-solution activity of data gathering, which does not amount to an inventive concept. Moreover, the one or more sensors and sensing circuitry are recited at a high level of generality and are well-understood routine, and conventional structures as evidenced by the following documents as cited in the IDS: US 20180116626 (¶51; ¶53), US 9826939 (col. 1 and line 67-physiologic sensors; col. 8 and lines 29-30-sensing circuit), and US 20190343415 (¶48-sensors; ¶49-sensing circuit). 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 idea 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.
Regarding dependent claims 2-16, 18-19, 21-22, and 24, the limitations of claims 1, 17, 20, and 23 further define the limitations already indicated as being directed to the abstract idea.
Claims 2-4, 6-11, 15-16, 18-19, 22, and 24 further define the machine learning model which is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting.
Claims 5 and 12 further define the abstract idea and the machine learning model which is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting.
Claims 13-14 further define the abstract idea.
Claim 21 further defines the data gathering. Moreover, wherein the one or more sensors including a plurality of electrodes is recited at a high level of generality and is a well-understood routine, and conventional structure as evidenced by NPL “Biopotential Electrodes” (Table 48.4-Examples of Application of Biopotential Electrodes: Cardiac electrograms), see the attached reference.
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 1, 17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Darbari (US 20180116626 filed on 11/2/17) in view of Eshel (US 20220215930 filed on 5/12/20) and Musgrove (US 20200357518 published on 11/12/20).
Regarding claim 1, Darbari teaches a medical system comprising: one or more sensors configured to sense cardiac activity of a patient (¶51-the heart activity detector is further provided with activity indicator lights 1403 which indicate the sensors are actively picking up signals from the heart); sensing circuitry configured to generate signal data to represent the cardiac activity of the patient (¶53-sensing devices…capture electric signals from the heart; ¶51); processing circuitry (¶34-processing block 23) configured to: apply the signal data to the machine learning model to determine a classification of the cardiac activity (Fig. 2 shows sensor data being put into the classifier for classification; ¶34); detect a cardiac arrhythmia for the patient based on the classification of the cardiac activity indicating a cardiac arrhythmia (¶34-classifier; ¶49-CNN, DNN, artificial neural network; ¶37-detection of arrhythmia; ¶44); and generate output data indicative of a positive detection of the cardiac arrhythmia (¶43-the output feature vectors are then transmitted to a feature scoring block 66 to determine a scoring value for heart diseases and other heart conditions, output into classification results 65; ¶34). While Darbari teaches features being fed into an artificial neural network (¶49), Darbari does not teach a storage device configured to store a machine learning model comprising at least one filter tailored to a feature set of the patient and configured for application to at least one portion of the signal data, the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient, wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data.
Eshel relates generally to using a learning personalized model and a training procedure (¶35). Eshel further teaches the invention using the following steps:
a storage device configured to store a machine learning model comprising at least one filter tailored to a feature set of the patient and configured for application to at least one portion of the signal data (¶300-a local storage unit 120 which comprises an database 122 configured to store set of personalized machine learning parameter values and/or set of personalized filter parameter values; Abstract-produce data indicative of estimates of unknown variables utilizing a stored set of personalized filter parameter values that characterize the subject, and inputting to a machine learning system and processing the data indicative of the estimates of unknown variable utilizing a stored set of personalized machine learning parameter values that characterize the subject).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Darbari to include a storage device configured to store a machine learning model comprising at least one filter tailored to a feature set of the patient and configured for application to at least one portion of the signal data of Eshel in order to produce estimates at desired accuracy for a particular subject (Eshel, ¶321).
While the combination of Darbari and Eshel teaches personalized filter parameter values that were utilized in said filtering and which characterize the subject (Eshel, ¶92), the combination does not teach the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient, wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data.
Musgrove generally relates to health monitoring and, more particularly, to monitoring cardiac health (¶2). Musgrove further teaches the invention using the following steps:
the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient (¶116-the AI system may learn the convolution kernel/filter parameters from the data directly; ¶133-re-filter and/or transform the signal of the cardiac EGM strip to match the input characteristics of deep learning model 454 prior to applying the deep learning model to the cardiac EGM strip; ¶40-one or more features derived from a raw electromyogram of patient 14), wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data (¶94-preprocessing unit 452 preprocesses the one or more cardiac EGM strips to conform to one or more characteristics of cardiac EGM strips on which deep learning model 454 was trained; ¶83-AI system 451 may further train deep learning model 454 with patient data specific to patient 14 or a smaller cohort of patients; ¶84-the training process may be used to further fine-tune deep learning model 454 that is trained using population-based data to generate more accurate data for a particular individual; ¶126).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Darbari to include the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient, wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data of Musgrove in order to generate more accurate data for a particular individual (Musgrove, ¶84).
Regarding claim 17, Darbari teaches a method comprising: generating, by sensing circuitry coupled to one or more sensors (¶51-the heart activity detector is further provided with activity indicator lights 1403 which indicate the sensors are actively picking up signals from the heart), signal data to represent cardiac activity of a patient (¶53-sensing devices…capture electric signals from the heart; ¶51); apply, by processing circuitry, the signal data to the machine learning model to determine a classification of the signal data (Fig. 2 shows sensor data being put into the classifier for classification; ¶34); detecting, by the processing circuitry (¶34-processing block 23), a cardiac arrhythmia for the patient based on the classification of the signal data indicating a cardiac arrhythmia (¶34-classifier; ¶49-CNN, DNN, artificial neural network; ¶37-detection of arrhythmia; ¶44); and generating, by the processing circuitry, output data indicative of a positive detection of the cardiac arrhythmia (¶43-the output feature vectors are then transmitted to a feature scoring block 66 to determine a scoring value for heart diseases and other heart conditions, output into classification results 65; ¶34).
While Darbari teaches features being fed into an artificial neural network (¶49), Darbari does not teach storing, by a storage device, a machine learning model comprising at least one filter tailored to a feature set of the patient and configured for application to at least one portion of the signal data, the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient, wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data.
Eshel teaches storing, by a storage device, a machine learning model comprising at least one filter tailored to a feature set of the patient and configured for application to at least one portion of the signal data (¶300-a local storage unit 120 which comprises an database 122 configured to store set of personalized machine learning parameter values and/or set of personalized filter parameter values; Abstract-produce data indicative of estimates of unknown variables utilizing a stored set of personalized filter parameter values that characterize the subject, and inputting to a machine learning system and processing the data indicative of the estimates of unknown variable utilizing a stored set of personalized machine learning parameter values that characterize the subject).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Darbari to include storing, by a storage device, a machine learning model comprising at least one filter tailored to a feature set of the patient and configured for application to at least one portion of the signal data of Eshel in order to produce estimates at desired accuracy for a particular subject (Eshel, ¶321).
While the combination of Darbari and Eshel teaches personalized filter parameter values that were utilized in said filtering and which characterize the subject (Eshel, ¶92), the combination does not teach the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient, wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data.
Musgrove teaches the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient (¶116-the AI system may learn the convolution kernel/filter parameters from the data directly; ¶133-re-filter and/or transform the signal of the cardiac EGM strip to match the input characteristics of deep learning model 454 prior to applying the deep learning model to the cardiac EGM strip; ¶40-one or more features derived from a raw electromyogram of patient 14), wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data (¶94-preprocessing unit 452 preprocesses the one or more cardiac EGM strips to conform to one or more characteristics of cardiac EGM strips on which deep learning model 454 was trained; ¶83-AI system 451 may further train deep learning model 454 with patient data specific to patient 14 or a smaller cohort of patients; ¶84-the training process may be used to further fine-tune deep learning model 454 that is trained using population-based data to generate more accurate data for a particular individual; ¶126).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Darbari to include the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient, wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data of Musgrove in order to generate more accurate data for a particular individual (Musgrove, ¶84).
Regarding claim 20, Darbari teaches a non-transitory computer-readable storage medium comprising program instructions that, when executed by processing circuitry of a medical system, cause the processing circuitry (¶34-processing block 23) to: generate patient data corresponding to at least one physiological parameter of the patient (¶45-an electrode 71 is provided to capture electrical signals from the heart), wherein the patient data comprises signal data to represent electronic activity of a heart of the patient (¶51-the heart activity detector is further provided with activity indicator lights 1403 which indicate the sensors are actively picking up signals from the heart), wherein the medical system comprises one or more sensors configured to sense the electrical activity and sensing circuitry (¶53-sensing devices…capture electric signals from the heart; ¶51), coupled to the one or more sensors, configured to generate the signal data; apply the signal data to the machine learning model to determine a classification of the patient data (Fig. 2 shows sensor data being put into the classifier for classification; ¶34); detect a cardiac arrhythmia for the patient based on the classification of the patient data indicating a cardiac arrhythmia (¶34-classifier; ¶49-CNN, DNN, artificial neural network; ¶37-detection of arrhythmia; ¶44); and generate output data indicative of a positive detection of the cardiac arrhythmia (¶43-the output feature vectors are then transmitted to a feature scoring block 66 to determine a scoring value for heart diseases and other heart conditions, output into classification results 65; ¶34).
While Darbari teaches features being fed into an artificial neural network (¶49), Darbari does not teach to store a machine learning model comprising a plurality of filters tailored to a feature set indicative of a respective physiological parameter of the patient of which at least one filter is configured to be applied, based on the patient data, to at least one portion of the signal data, the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient, wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data.
Eshel teaches to store a machine learning model comprising a plurality of filters tailored to a feature set indicative of a respective physiological parameter of the patient of which at least one filter is configured to be applied, based on the patient data, to at least one portion of the signal data (¶300-a local storage unit 120 which comprises an database 122 configured to store set of personalized machine learning parameter values and/or set of personalized filter parameter values; Abstract-produce data indicative of estimates of unknown variables utilizing a stored set of personalized filter parameter values that characterize the subject, and inputting to a machine learning system and processing the data indicative of the estimates of unknown variable utilizing a stored set of personalized machine learning parameter values that characterize the subject).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Darbari to include storing a machine learning model comprising a plurality of filters tailored to a feature set indicative of a respective physiological parameter of the patient of which at least one filter is configured to be applied, based on the patient data, to at least one portion of the signal data of Eshel in order to produce estimates at desired accuracy for a particular subject (Eshel, ¶321).
While the combination of Darbari and Eshel teaches personalized filter parameter values that were utilized in said filtering and which characterize the subject (Eshel, ¶92), the combination does not teach the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient, wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data.
Musgrove teaches the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient (¶116-the AI system may learn the convolution kernel/filter parameters from the data directly; ¶133-re-filter and/or transform the signal of the cardiac EGM strip to match the input characteristics of deep learning model 454 prior to applying the deep learning model to the cardiac EGM strip; ¶40-one or more features derived from a raw electromyogram of patient 14), wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data (¶94-preprocessing unit 452 preprocesses the one or more cardiac EGM strips to conform to one or more characteristics of cardiac EGM strips on which deep learning model 454 was trained; ¶83-AI system 451 may further train deep learning model 454 with patient data specific to patient 14 or a smaller cohort of patients; ¶84-the training process may be used to further fine-tune deep learning model 454 that is trained using population-based data to generate more accurate data for a particular individual; ¶126).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Darbari to include the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient, wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data of Musgrove in order to generate more accurate data for a particular individual (Musgrove, ¶84).
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Darbari in view of Eshel and Musgrove as applied to claim 1 above, and further in view of Ravuna (US 20220051091 filed on 8/12/20).
Regarding claim 2, the combination of Darbari, Eshel, and Musgrove teaches the medical system of claim 1, wherein the prior cardiac EGM data of the patient is first cardiac EGM data (Eshel, page 4, Section 2.1.1. ¶2-the training dataset consisted of the remaining four plates (395 control and 367 CBX electrograms)). However, the combination of Darbari, Eshel, and Musgrove does not teach and wherein the at least one filter is further derived from second cardiac EGM data of at least one second patient, wherein the at least one second patient corresponds to the feature set of the patient.
Ravuna teaches and wherein the at least one filter is further derived from second cardiac EGM data of at least one second patient (¶40- filters (i.e., kernels) to flatten and smoothen the EGM signals, and to emphasize the required features of EGM signals, and thus to be able to accurately determine a presence of activation-indicative features that are present on both bipolar and unipolar signals simultaneously; ¶71-training of the preprocessing step, e.g., by optimizing convolution kernels applied to time-windowed (303, 305) EGM signals (93, 95), namely, to unipolar signal 302 (e.g., V22a of FIG. 1) and bipolar signal 304 (e.g., V22a-V22b of FIG. 1); ¶7-collecting a plurality of bipolar electrograms and respective unipolar electrograms of patients), wherein the at least one second patient corresponds to the feature set of the patient (¶40- filters (i.e., kernels) to flatten and smoothen the EGM signals, and to emphasize the required features of EGM signals; ¶7-collecting a plurality of bipolar electrograms and respective unipolar electrograms of patients).
Ravuna relates generally to analysis of intracardiac electrophysiological signals, and specifically to evaluation of electrical propagation in the heart using machine leaning (ML) (¶1).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Darbari to include and wherein the at least one filter is further derived from second cardiac EGM data of at least one second patient, wherein the at least one second patient corresponds to the feature set of the patient of Ravuna in order to detect an occurrence of an activation in a given bipolar electrogram within the window-of-interest (Ravuna, ¶7) to see an identified irregularity (Ravuna, ¶56).
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Darbari in view of Eshel and Musgrove and further in view of Ravuna as applied to claim 2 above, and further in view of Javadi (NPL “Improving ECG Classification Accuracy Using an Ensemble of Neural Network Modules” as cited in the IDS and published 10/26/11).
Regarding claim 3, the combination of Darbari, Eshel, Musgrove, and Ravuna teaches the medical system of claim 2. However, the combination of Darbari, Eshel, Musgrove, and Ravuna does not teach wherein the at least one filter comprises pattern information of at least one decomposition layer of the second cardiac EGM data.
Javadi teaches wherein the at least one filter comprises pattern information of at least one decomposition layer of the second cardiac EGM data (Table 3, ¶1-pattern; Fig. 4-decomposition of three levels, H(z)…decomposition high pass filter; Fig. 2, ¶1-2-ECG signals, arrhythmia database).
Javadi relates generally to a new combination method for classifying normal heartbeats, Premature Ventricular Contraction (PVC) and other abnormalities (¶4). Javadi further teaches a new combining method for classification of the ECG beats based on Stacked Generalization (Table 6, ¶1).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to modify the invention of Darbari to include wherein the at least one filter comprises pattern information of at least one decomposition layer of the second cardiac EGM data of Javadi in order to increase the knowledge of the combiner to help it make a better decision according to the base classifiers' decisions (Javadi, Table 6 ¶1).
Claims 4 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Darbari in view of Eshel and Musgrove as applied to claims 1 and 17 above, and further in view of DeMazumder (US 20210272696 filed on 3/2/20), hereinafter referred to as DeMaz.
Regarding claim 4, the combination of Darbari, Eshel, and Musgrove teaches the medical system of claim 1. However, the combination of Darbari, Eshel, and Musgrove does not teach wherein the feature set comprises at least one of a patient group, a disease group, a device group, an implant location, or an implant orientation of the patient.
DeMaz teaches wherein the feature set comprises at least one of a patient group, a disease group, a device group, an implant location, or an implant orientation of the patient (DeMaz, ¶109-a training set for a relevant group (e.g., gender, race, disease group) as well as from asymptomatic “healthy” individuals with little or no disease).
DeMaz relates to a method for assessing the likelihood of an individual for experiencing a condition (which may be an illness, an improvement from illness, or an improvement in athletic conditioning) by obtaining one or more time-varying signals from continuous monitoring of the individual or the individual's environment, processing the signals to develop signatures for those signals, and calculating an integrated likelihood of experiencing the condition which can be provided to an individual and/or a trainer, supervising authority, or health-care provider for the individual, and updated on a time schedule (¶13).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Darbari to include wherein the feature set comprises at least one of a patient group, a disease group, a device group, an implant location, or an implant orientation of the patient of DeMaz in order to achieve an even higher order of information retrieval and automated evolution that markedly increases this predictive accuracy in the individual, and more broadly, in groups comprised of the individual (e.g., gender, ethnicity, preexisting disease) (DeMaz, ¶41).
Regarding claim 19, the combination of Darbari, Eshel, and Musgrove teaches the method of claim 17. However, the combination of Darbari, Eshel, and Musgrove does not teach wherein the feature set comprises at least one of a patient group, a disease group, a device group, an implant location, or an implant orientation of the patient.
DeMaz teaches wherein the feature set comprises at least one of a patient group, a disease group, a device group, an implant location, or an implant orientation of the patient (DeMaz, ¶109-a training set for a relevant group (e.g., gender, race, disease group) as well as from asymptomatic “healthy” individuals with little or no disease).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Darbari to include wherein the feature set comprises at least one of a patient group, a disease group, a device group, an implant location, or an implant orientation of the patient of DeMaz in order to achieve an even higher order of information retrieval and automated evolution that markedly increases this predictive accuracy in the individual, and more broadly, in groups comprised of the individual (e.g., gender, ethnicity, preexisting disease) (DeMaz, ¶41).
Claims 5-8 are rejected under 35 U.S.C. 103 as being unpatentable over Darbari in view of Eshel and Musgrove as applied to claim 1 above, and further in view of Kaur (NPL “On the detection of Cardiac Arrhythmia with Principal Component Analysis” and published in 2017).
Regarding claim 5, the combination of Darbari, Eshel, and Musgrove teaches the medical system of claim 1. However, the combination of Darbari, Eshel, and Musgrove does not teach wherein to detect a cardiac arrhythmia, the processing circuitry is configured to identify at least one decomposition layer in the signal data based on an application of the at least one filter and detect the cardiac arrhythmia based, at least in part, on the identified at least one decomposition layer.
Kaur teaches wherein to detect a cardiac arrhythmia, the processing circuitry is configured to identify at least one decomposition layer in the signal data based on an application of the at least one filter (Fig. 2-two-level wavelet decomposition; Introduction, ¶3-detection of QRS complex, R-peak and heart rate for arrhythmia detection) and detect the cardiac arrhythmia based, at least in part, on the identified at least one decomposition layer (bottom of page 5503 to the top of page 5504-detect arrhythmia from ECG on the basis of calculated HR and its characteristics; Fig. 2).
Kaur relates generally to different types of arrhythmias being detected on the basis of heart rate and morphological characteristics of ECG waveform (Abstract). Kaur further teaches three different prevailing tools, i.e. EKF, DWT and PCA for denoising, extraction of constituent components, prominent peaks of the ECG signal, detection of heart rate, arrhythmia and achieving superior results in comparison to other techniques (¶3).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to modify the invention of Darbari to include wherein to detect a cardiac arrhythmia, the processing circuitry is configured to identify at least one decomposition layer in the signal data based on an application of the at least one filter and detect the cardiac arrhythmia based, at least in part, on the identified at least one decomposition layer of Kaur in order to adopt the three different prevailing tools, i.e. EKF, DWT and PCA for denoising, extraction of constituent components, prominent peaks of the ECG signal, detection of heart rate, arrhythmia and achieving superior results in comparison to other techniques (Kaur, ¶3).
Regarding claim 6, the combination of Darbari, Eshel, and Musgrove teaches the medical system of claim 1. However, the combination of Darbari, Eshel, and Musgrove does not teach wherein the processing circuitry is further configured to update the at least one filter based on at least one decomposition layer of the signal data.
Kaur teaches wherein the processing circuitry is further configured to update the at least one filter based on at least one decomposition layer of the signal data (PCA section-row feature vector is adjusted to drive new data set; Section 3.1-decomposition).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to modify the invention of Darbari to include wherein the processing circuitry is further configured to update the at least one filter based on at least one decomposition layer of the signal data of Kaur in order to adopt the three different prevailing tools, i.e. EKF, DWT and PCA for denoising, extraction of constituent components, prominent peaks of the ECG signal, detection of heart rate, arrhythmia and achieving superior results in comparison to other techniques (Kaur, ¶3).
Regarding claim 7, the combination of Darbari, Eshel, and Musgrove teaches the medical system of claim 1. However, the combination of Darbari, Eshel, and Musgrove does not teach wherein the processing circuitry is further configured to modify wavelet data or principal component data to identify at least one decomposition layer of the signal data.
Kaur teaches wherein the processing circuitry is further configured to modify wavelet data or principal component data to identify at least one decomposition layer of the signal data (3.1 Denoising and Wave Detection section-The ECG signal is decomposed using PCA, decomposition).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to modify the invention of Darbari to include wherein the processing circuitry is further configured to modify wavelet data or principal component data to identify at least one decomposition layer of the signal data of Kaur in order to adopt the three different prevailing tools, i.e. EKF, DWT and PCA for denoising, extraction of constituent components, prominent peaks of the ECG signal, detection of heart rate, arrhythmia and achieving superior results in comparison to other techniques (Kaur, ¶3).
Regarding claim 8, the combination of Darbari, Eshel, and Musgrove teaches the medical system of claim 1. However, the combination of Darbari, Eshel, and Musgrove does not teach wherein the machine learning model comprises, for each of a plurality of decomposition layers, a set of one or more filters derived from data associated with that respective one of the plurality of decomposition layers.
Kaur teaches wherein the machine learning model comprises, for each of a plurality of decomposition layers (Fig. 2-two-level wavelet decomposition), a set of one or more filters derived from data associated with that respective one of the plurality of decomposition layers (¶3-detection of QRS complex, R-peak and heart rate for arrhythmia detection).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to modify the invention of Darbari to include wherein the machine learning model comprises, for each of a plurality of decomposition layers, a set of one or more filters derived from data associated with that respective one of the plurality of decomposition layers of Kaur in order to adopt the three different prevailing tools, i.e. EKF, DWT and PCA for denoising, extraction of constituent components, prominent peaks of the ECG signal, detection of heart rate, arrhythmia and achieving superior results in comparison to other techniques (Kaur, ¶3).
Claims 9 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Darbari in view of Eshel and Musgrove as applied to claim 1 above, and further in view of Acharya (NPL “Novel deep genetic ensemble of classifiers for arrhythmia detection using ECG signals” as cited in the IDS).
Regarding claim 9, the combination of Darbari, Eshel, and Musgrove teaches the medical system of claim 1. However, the combination of Darbari, Eshel, and Musgrove does not teach wherein the machine learning model further comprises an ensemble configured to generate the positive detection for the cardiac arrhythmia based on output data from component models.
Acharya teaches wherein the machine learning model further comprises an ensemble (page 11144, right col.-ensemble of classifiers) configured to generate the positive detection for the cardiac arrhythmia based on output data from component models (Evaluation criteria section-positive; 3.1.3 Third layer section-positive predictive value; Conclusion section-effective classification of cardiac arrhythmias; Section 4.3-outputs of all component classifiers).
Acharya relates generally to new methods to support the medical diagnosis early and more effectively diagnose the heart disorders through reducing the computational complexity of the developed algorithms in the context of implementing our solution in cloud computing or mobile devices to monitor the health of patients in real time (1.1 Heart diseases section, ¶4). Acharya further teaches a new ML method, focusing on EC and also EL and DL approach which enables the effective classification of cardiac arrhythmias (17 classes: normal sinus rhythm, 15 types of arrhythmias and pacemaker rhythm) using ECG signal segments (10-s) with the design of a novel three-layer genetic ensemble of classifiers (Acharya, Conclusion section).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to modify the invention of Darbari include the ensemble configured to generate the positive detection for the cardiac arrhythmia based on output data from component models of Acharya in order to develop a new ML method, focusing on EC and also EL and DL approach which enables the effective classification of cardiac arrhythmias (17 classes: normal sinus rhythm, 15 types of arrhythmias and pacemaker rhythm) using ECG signal segments (10-s) with the design of a novel three-layer genetic ensemble of classifiers (Acharya, Conclusion section).
Regarding claim 15, the combination of Darbari, Eshel, and Musgrove teaches the medical system of claim 1. However, the combination of Darbari, Eshel, and Musgrove does not teach wherein the machine learning model comprises an ensemble configured to generate the positive detection for the cardiac arrhythmia based on output data from at least two depth levels of the machine learning model.
Acharya teaches wherein the machine learning model comprises an ensemble (page 11144, right col.-ensemble of classifiers) configured to generate the positive detection for the cardiac arrhythmia based on output data from at least two depth levels of the machine learning model (Evaluation criteria section-positive; 3.1.3 Third layer section-positive predictive value; Conclusion section-effective classification of cardiac arrhythmias; page 11144, left col.-Multilayered (depth)…above two layers are considered as deep).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to modify the invention of Darbari include the ensemble and at least two depth levels of Acharya in order to develop a new ML method, focusing on EC and also EL and DL approach which enables the effective classification of cardiac arrhythmias (17 classes: normal sinus rhythm, 15 types of arrhythmias and pacemaker rhythm) using ECG signal segments (10-s) with the design of a novel three-layer genetic ensemble of classifiers (Acharya, Conclusion section).
Claims 10-11 are rejected under 35 U.S.C. 103 as being unpatentable over Darbari in view of Eshel and Musgrove and further in view of Acharya as applied to claim 9 above, and further in view of Kaur.
Regarding claim 10, the combination of Darbari, Eshel, Musgrove, and Acharya teaches the medical system of claim 9 and the ensemble (Acharya, page 11144, right col.-ensemble of classifiers). However, the combination of Darbari, Eshel, Musgrove, and Acharya does not teach component models for respective ones of a plurality of decomposition layers, wherein each component model comprises a set of filters corresponding to the respective decomposition layer.
Kaur teaches component models for respective ones of a plurality of decomposition layers (Introduction, ¶3-constituent component, PCA), wherein each component model comprises a set of filters corresponding to the respective decomposition layer (Introduction, ¶3-application of Principal Component Analysis (PCA) along with thresholding for detection of QRS complex, R-peak and heart rate for arrhythmia detection; Fig. 2).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to modify the invention of Darbari to include component models for respective ones of a plurality of decomposition layers, wherein each component model comprises a set of filters corresponding to the respective decomposition layer of Kaur in order to adopt the three different prevailing tools, i.e. EKF, DWT and PCA for denoising, extraction of constituent components, prominent peaks of the ECG signal, detection of heart rate, arrhythmia and achieving superior results in comparison to other techniques (Kaur, ¶3).
Regarding claim 11, the combination of Darbari, Eshel, Musgrove, and Acharya teaches the medical system of claim 9. However, the combination of Darbari, Eshel, Musgrove, and Acharya does not teach wherein the ensemble further comprises component models for respective arrhythmia types, wherein each component model comprises one or more filters configured to identify the respective arrhythmia type from the signal data.
Kaur teaches wherein the ensemble further comprises component models for respective arrhythmia types, wherein each component model comprises one or more filters configured to identify the respective arrhythmia type from the signal data (Principal Component Analysis section-feature extraction is a recent application of PCA; Introduction, ¶3-application of Principal Component Analysis (PCA) along with thresholding for detection of QRS complex, R-peak and heart rate for arrhythmia detection; Table 3-Arrhythmia detected for different ECG records).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to modify the invention of Darbari to include wherein the ensemble further comprises component models for respective arrhythmia types, wherein each component model comprises one or more filters configured to identify the respective arrhythmia type from the signal data of Kaur in order to adopt the three different prevailing tools, i.e. EKF, DWT and PCA for denoising, extraction of constituent components, prominent peaks of the ECG signal, detection of heart rate, arrhythmia and achieving superior results in comparison to other techniques (Kaur, ¶3).
Claims 12-13 are rejected under 35 U.S.C. 103 as being unpatentable over Darbari in view of Eshel and Musgrove as applied to claim 1 above, and further in view of Saha (US 20190343415 filed on 4/18/19 as cited in the IDS).
Regarding claim 12, the combination of Darbari, Eshel, and Musgrove teaches the medical system of claim 1. However, the combination of Darbari, Eshel, and Musgrove does not teach wherein the machine learning model comprises at least one criterion directed to determining whether at least one of pulse oximeter data or accelerometer data is indicative of the cardiac arrhythmia.
Saha teaches wherein the machine learning model comprises at least one criterion directed to determining whether at least one of pulse oximeter data or accelerometer data is indicative of the cardiac arrhythmia (¶54-detection algorithms; ¶65-detecting atrial tachyarrhythmia such as an atrial fibrillation or atrial tachycardia episode, the baseline cardiac characteristic may include a baseline ventricular rate variability metric, ventricular rates may be detected using…heart sound signal sensed using an accelerometer; ¶63-detection criterion, arrhythmia; ¶61).
Saha relates generally to medical devices, and more particularly, to systems, devices and methods for detecting and managing cardiac arrhythmias (¶2). Saha further teaches the arrhythmia detection system detecting an arrhythmia episode using a physiologic signal sensed from the patient and the patient-specific arrhythmia detection threshold (¶44).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to modify the invention of Darbari to include wherein the machine learning model comprises at least one criterion directed to determining whether at least one of pulse oximeter data or accelerometer data is indicative of the cardiac arrhythmia of Saha in order for diagnosis of a disease condition (Saha, ¶45).
Regarding claim 13, the combination of Darbari, Eshel, and Musgrove teaches the medical system of claim 1. However, the combination of Darbari, Eshel, and Musgrove does not teach wherein the processing circuitry is further configured to generate, based on a determination of at least one criterion, output data indicative of a disease, a treatment side effect, a titrated treatment amount, or an implant location.
Saha teaches wherein the processing circuitry is further configured to generate, based on a determination of at least one criterion (¶44-determine a patient-specific criterion), output data indicative of a disease, a treatment side effect, a titrated treatment amount, or an implant location (¶45-diagnosis of a disease condition; ¶58-output the detected medical events).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to modify the invention of Darbari to include wherein the processing circuitry is further configured to generate, based on a determination of at least one criterion, output data indicative of a disease, a treatment side effect, a titrated treatment amount, or an implant location of Saha in order for diagnosis of a disease condition (Saha, ¶45).
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Darbari in view of Eshel and Musgrove as applied to claim 1 above, and further in view of Javadi.
Regarding claim 14, the combination of Darbari, Eshel, and Musgrove teaches the medical system of claim 1. However, the combination of Darbari, Eshel, and Musgrove does not teach wherein to detect a cardiac arrhythmia, the processing circuitry is configured to modify at least one of an amplitude, a timing, or a morphology of principal component data or wavelet data of the at least a portion of the signal data.
Javadi teaches wherein to detect a cardiac arrhythmia, the processing circuitry is configured to modify at least one of an amplitude, a timing, or a morphology of principal component data or wavelet data of the at least a portion of the signal data (Introduction, ¶4-Undecimated Wavelet Transform…morphological characteristics of the waveform features; Fig. 4; Materials and Methods section, ¶1-detection and classification of PVC arrhythmias).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to modify the invention of Darbari to include wherein to detect a cardiac arrhythmia, the processing circuitry is configured to modify at least one of an amplitude, a timing, or a morphology of principal component data or wavelet data of the at least a portion of the signal data of Javadi in order to increase the knowledge of the combiner to help it make a better decision according to the base classifiers' decisions (Javadi, Table 6 ¶1).
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Darbari in view of Eshel and Musgrove as applied to claim 1 above, and further in view of Alfaras (NPL “A Fast Machine Learning Model for ECG-Based Heartbeat Classification and Arrhythmia Detection” as cited in the IDS).
Regarding claim 16, the combination of Darbari, Eshel, and Musgrove teaches the medical system of claim 1. However, the combination of Darbari, Eshel, and Musgrove does not teach wherein the machine learning model comprises an ensemble configured to generate the positive detection for the cardiac arrhythmia based on filtered datasets of the signal data.
Alfaras teaches wherein the machine learning model comprises an ensemble configured to generate the positive detection for the cardiac arrhythmia (Introduction, ¶6-ensemble of Echo State Networks (ESNs) as the classifier method; Section 2.2-positive predictive value (PPV) and true positives (TP); Discussion section, ¶1-detection of ventricular arrhythmia) based on filtered datasets of the signal data (2.4 Processing of the ECG and Feature Extraction-ECG filtering).
Alfaras relates generally to loosening the requirements for feature extraction, through an implementation fundamentally based on raw signals, single lead information and heart rates that aims at reducing computation time while achieving low error classification results (Introduction ¶4). Alfaras further relates to using an ensemble of Echo State Networks (ESNs) as the classifier method, using the raw ECG waveforms and time intervals between the heartbeats as the input features (Introduction ¶5-6).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to modify the invention of Darbari to include the ensemble based on filtered datasets of the signal data of Alfaras in order for a fast retraining of the classifier if new ECG data become available using an ensemble of Echo State Networks (ESNs) as the classifier method, using the raw ECG waveforms and time intervals between the heartbeats as the input features (Alfaras, Introduction ¶5-6).
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Darbari in view of Eshel and Musgrove as applied to claim 17 above, and further in view of Ravuna and Javadi.
Regarding claim 18, the combination of Darbari, Eshel, and Musgrove teaches the method of claim 17, wherein the prior cardiac EGM data of the patient is first cardiac EGM data (Eshel, page 4, Section 2.1.1. ¶2-the training dataset consisted of the remaining four plates (395 control and 367 CBX electrograms)). However, the combination of Darbari, Eshel, and Musgrove does not teach and wherein the at least one filter is further derived from second cardiac EGM data of at least one second patient, wherein the at least one second patient corresponds to the feature set of the patient, and wherein the at least one filter comprises pattern information of at least one decomposition layer of the first cardiac EGM data or the second cardiac EGM data.
Ravuna teaches and wherein the at least one filter is further derived from second cardiac EGM data of at least one second patient (¶40- filters (i.e., kernels) to flatten and smoothen the EGM signals, and to emphasize the required features of EGM signals, and thus to be able to accurately determine a presence of activation-indicative features that are present on both bipolar and unipolar signals simultaneously; ¶71-training of the preprocessing step, e.g., by optimizing convolution kernels applied to time-windowed (303, 305) EGM signals (93, 95), namely, to unipolar signal 302 (e.g., V22a of FIG. 1) and bipolar signal 304 (e.g., V22a-V22b of FIG. 1); ¶7-collecting a plurality of bipolar electrograms and respective unipolar electrograms of patients), wherein the at least one second patient corresponds to the feature set of the patient (¶40- filters (i.e., kernels) to flatten and smoothen the EGM signals, and to emphasize the required features of EGM signals; ¶7-collecting a plurality of bipolar electrograms and respective unipolar electrograms of patients).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Darbari to include and wherein the at least one filter is further derived from second cardiac EGM data of at least one second patient and wherein the at least one second patient corresponds to the feature set of the patient of Ravuna in order to detect an occurrence of an activation in a given bipolar electrogram within the window-of-interest (Ravuna, ¶7) to see an identified irregularity (Ravuna, ¶56).
While the combination of Darbari, Eshel, Musgrove, and Ravuna teaches convolutional filters (i.e., kernels) to flatten and smoothen the EGM signals, and to emphasize the required features of EGM signals (Ravuna, ¶40), the combination fails to teach wherein the at least one filter comprises pattern information of at least one decomposition layer of the first cardiac EGM data or the second cardiac EGM data.
Javadi teaches wherein the at least one filter comprises pattern information of at least one decomposition layer of the first cardiac EGM data or the second cardiac EGM data (Table 3, ¶1-pattern; Fig. 4-decomposition of three levels, H(z)…decomposition high pass filter; Fig. 2, ¶1-2-ECG signals, arrhythmia database).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to modify the invention of Darbari to include wherein the at least one filter comprises pattern information of at least one decomposition layer of the first cardiac EGM data or the second cardiac EGM data of Javadi in order to increase the knowledge of the combiner to help it make a better decision according to the base classifiers' decisions (Javadi, Table 6 ¶1).
Claim 21 is rejected under 35 U.S.C. 103 as being unpatentable over Darbari in view of Eshel and Musgrove as applied to claim 1 above, and further in view of Cantwell (NPL “Rethinking multiscale cardiac electrophysiology with machine learning and predictive modelling” published in 2018).
Regarding claim 21, the combination of Darbari, Eshel, and Musgrove teaches the medical system of claim 1. However, the combination of Darbari, Eshel, and Musgrove does not teach wherein the one or more sensors includes a plurality of electrodes, wherein the cardiac activity of the patient includes an EGM signal of the patient, wherein the plurality of electrodes are configured to sense the EGM signal of the patient, and wherein the prior cardiac electrogram (EGM) data of the patient was sensed via the plurality of electrodes.
Cantwell teaches wherein the one or more sensors includes a plurality of electrodes (Cantwell, page 4, Section 2.1.1, ¶1-electrogram recordings were acquired as previously described [49]. In brief, cell monolayers of neonatal rat ventricular myocytes (NRVMs) were seeded onto five microelectrode arrays (MEA), each consisting of 60 electrodes (MultiChannel Systems, Reutlingen, Germany)), wherein the cardiac activity of the patient includes an EGM signal of the patient (Cantwell, page 4, Section 2.1.1, ¶1-electrogram recordings were acquired as previously described [49]. In brief, cell monolayers of neonatal rat ventricular myocytes (NRVMs) were seeded onto five microelectrode arrays (MEA), each consisting of 60 electrodes (MultiChannel Systems, Reutlingen, Germany)), wherein the plurality of electrodes are configured to sense the EGM signal of the patient (Cantwell, page 13, Section 7.1, ¶1-the micro-electrode array electrogram data), and wherein the prior cardiac electrogram (EGM) data of the patient was sensed via the plurality of electrodes (Cantwell, page 4, left col., last ¶-each electrogram recording was represented by a fixed set of 27 time-, frequency- and morphological-based features, extracted from the signal using a custom-written algorithm (Matlab R2017b); page 4, right col., ¶1-the set of values from the selected electrogram characteristics form the feature vector for that electrogram. These feature vectors were subsequently used to train the classifier).
Cantwell relates generally to the ability to create personalised models which can be used on clinically relevant timescales (page 3, left col., Section 1.3). Cantwell further teaches the invention using the following step:
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Darbari to include wherein the one or more sensors includes a plurality of electrodes, wherein the cardiac activity of the patient includes an EGM signal of the patient, wherein the plurality of electrodes are configured to sense the EGM signal of the patient, and wherein the prior cardiac electrogram (EGM) data of the patient was sensed via the plurality of electrodes of Cantwell in order to produce more accurate diagnoses and robust personalised treatment (Cantwell, Abstract).
Claim 22 is rejected under 35 U.S.C. 103 as being unpatentable over Darbari in view of Eshel and Musgrove as applied to claim 1 above, and further in view of Bouguerra (US 20190374123 filed on 6/12/19).
Regarding claim 22, the combination of Darbari, Eshel, and Musgrove teaches the medical system of claim 1. However, the combination of Darbari, Eshel, and Musgrove does not teach the at least one filter includes a P- wave hunting filter.
Bouguerra teaches the at least one filter includes a P- wave hunting filter (¶31-a P-wave filter; ¶5-identifies candidate P-waves, filters the candidate P-waves, and extracts one or more high quality P-waves, while preserving high frequency components of the candidate P-waves).
Bouguerra relates to predicting atrial fibrillation or stroke (Abstract).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Darbari to include the at least one filter includes a P- wave hunting filter of Bouguerra in order for detecting atrial defects or determining an indication of the likelihood of the patient developing atrial fibrillation or stroke (Bouguerra, ¶23).
Claim 23 is rejected under 35 U.S.C. 103 as being unpatentable over Eshel in view of Musgrove.
Regarding claim 23, Eshel teaches a medical system comprising: one or more sensors configured to sense cardiac activity of a patient (¶187-additional biosensors may be employed for measuring additional physiological parameters such as heart rate (e.g. using a fitness watch)); and a storage device configured to store a machine learning model comprising at least one filter tailored to a feature set of the patient and configured for application to at least one portion of signal data representative of the sensed cardiac activity of the patient (¶300-a local storage unit 120 which comprises an database 122 configured to store set of personalized machine learning parameter values and/or set of personalized filter parameter values; Abstract-produce data indicative of estimates of unknown variables utilizing a stored set of personalized filter parameter values that characterize the subject, and inputting to a machine learning system and processing the data indicative of the estimates of unknown variable utilizing a stored set of personalized machine learning parameter values that characterize the subject). However, Eshel does not teach the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient, wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data.
Musgrove teaches the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient (¶116-the AI system may learn the convolution kernel/filter parameters from the data directly; ¶133-re-filter and/or transform the signal of the cardiac EGM strip to match the input characteristics of deep learning model 454 prior to applying the deep learning model to the cardiac EGM strip; ¶40-one or more features derived from a raw electromyogram of patient 14), wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data (¶94-preprocessing unit 452 preprocesses the one or more cardiac EGM strips to conform to one or more characteristics of cardiac EGM strips on which deep learning model 454 was trained; ¶83-AI system 451 may further train deep learning model 454 with patient data specific to patient 14 or a smaller cohort of patients; ¶84-the training process may be used to further fine-tune deep learning model 454 that is trained using population-based data to generate more accurate data for a particular individual; ¶126).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Darbari to include the at least one filter being derived, based on the feature set of the patient, from prior cardiac electrogram (EGM) data of the patient, wherein the feature set groups together the patient and at least one second patient based on one or more characteristics other than the prior cardiac EGM data of Musgrove in order to generate more accurate data for a particular individual (Musgrove, ¶84).
Claim 24 is rejected under 35 U.S.C. 103 as being unpatentable over Eshel in view of Musgrove as applied to claim 23 above, and further in view of Bouguerra.
Regarding claim 24, the combination of Eshel and Musgrove teaches the medical system of claim 23. However, the combination of Eshel and Musgrove does not teach wherein the at least one filter includes a P-wave hunting filter.
Bouguerra teaches wherein the at least one filter includes a P-wave hunting filter (¶31-a P-wave filter; ¶5-identifies candidate P-waves, filters the candidate P-waves, and extracts one or more high quality P-waves, while preserving high frequency components of the candidate P-waves).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Eshel to include wherein the at least one filter includes a P-wave hunting filter of Bouguerra in order for detecting atrial defects or determining an indication of the likelihood of the patient developing atrial fibrillation or stroke (Bouguerra, ¶23).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20200352466: computing system 24 may tailor machine learning system 150 to the specific use case (¶77) and the computing device applies the machine learning model to compare cardiac features coinciding with the episode of arrhythmia with cardiac features of past episodes of arrhythmia in the patient (¶8).
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 LAURA HODGE whose telephone number is (571) 272-7101. The examiner can normally be reached M-F: 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, UNSU JUNG can be reached at (571) 272-8506. 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.
/L.N.H./Examiner, Art Unit 3792
/AMANDA L STEINBERG/Examiner, Art Unit 3792
Prosecution Insights