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 .
DETAILED ACTION
Status of Claims
The present Office Action is pursuant to Applicant’s communication on 08-15-2025; current application filed on 08-15-2025; Provisional application No. 63/684,432, filed on Aug. 18, 2024, provisional application No. 63/819,451, filed on Jun. 6, 2025.
Examiner’s Note
The rejections below group claims that may not be identical, but whose language and scope are so substantively similar as to lend themselves to grouping, in the interests of clarity and conciseness.
Information Disclosure Statement
The information disclosure statements (IDS) filed on 11-10-2025, 01-09-2026, have been acknowledged. The submissions are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement 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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more.
Claim 1 (Method)
Step 1: Statutory Category? Yes. Claim 1 is directed to a "method," which falls within the statutory category of processes.
Step 2A: Judicial Exception? Yes. The claim recites obtaining ECG signals, encoding them, processing them with a trained classifier to generate labels, displaying those labels in an interactive GUI, and receiving user input to verify or modify the labels. This core concept is directed to the abstract idea of collecting data, analyzing/classifying it, and displaying results for human review/verification. The specification confirms this focus on human-in-the-loop data validation:
Specification discloses generating a GUI for user verification/modification of ECG labels. [Page 118]: "generating an interactive graphical user interface (GUI) indicating the sample-level ECG labels for the at least some of the plurality of samples; and receiving user input via the interactive GUI, wherein the user input is indicative of a verification or a modification of a sample-level ECG label of the sample-level ECG labels." The steps of data gathering, mathematical/computational classification, and presenting results for human confirmation are well-established abstract concepts (mental processes/data analysis) under Alice and MPEP § 2106.04(a)(2).
Step 2B: Significantly More? No. The additional elements ("using at least one processor," "trained sample-level ECG classifier," "interactive GUI") are generic computer components performing routine functions. The specification treats these as standard implementation details:
Specification discloses using a processor and GUI for label output. [Page 118]: "In some embodiments, outputting the sample-level ECG labels comprises generating an interactive graphical user interface (GUI) indicating the predicted sample-level ECG labels." Using a generic processor to run a classifier and a standard GUI to display data for human review does not improve computer functionality, solve a technical problem, or apply the abstract idea in a meaningful way beyond conventional data processing and display. Thus, Claim 1 is rejected under § 101.
Claim 19 (CRM) & Claim 20 (System)
Step 1: Both claims are directed to statutory categories (non-transitory computer-readable storage medium and system/machine, respectively).
Step 2A: Both recite the exact same method steps as Claim 1. They are equally directed to the abstract idea of data collection, computational classification, and GUI-based human verification.
Step 2B: The recitation of "at least one processor" and "non-transitory computer-readable storage medium" in Claims 19 and 20 merely adds generic hardware to implement the abstract idea. As established in Alice and MPEP § 2106.05(f), simply implementing an abstract idea on a generic computer or storing instructions on a standard medium does not amount to significantly more. Both claims are rejected under § 101.
Dependent Claims: 2-18
The dependent claims add limitations that either further define the abstract data being processed, specify routine hardware parameters, or recite conventional display/reporting functions. None integrate the abstract idea into a practical application or provide significantly more.
Claims 2, 15, & 16 (Data Source & Hardware Parameters)
Step 1: Statutory (dependent on method/system/CRM).
Step 2A: These claims specify sampling rates (128–256 Hz), durations (10s–14 days), and device types (Holter monitor, smartwatch). This merely defines the source and format of the data being analyzed. The specification treats these as standard wearable device parameters:
Specification discloses wearable device measurement parameters. [Page 128]: "measuring the at least one ECG signal using a Holter monitor comprising at least three ECG leads, at a sampling rate of between 128 Hz and 256 Hz, and for a duration of between one and fourteen days." Specifying data acquisition parameters does not change the abstract nature of the underlying classification and human-verification concept.
Step 2B: Routine hardware configurations and standard sampling rates are well-understood, conventional activities in ECG monitoring. They do not amount to significantly more. Rejected under § 101.
Claims 3 & 4 (Data Modification & Report Generation)
Step 1: Statutory.
Step 2A: Claim 3 recifies modifying labels based on user input; Claim 4 recites generating a report. These are post-solution data manipulation and output steps. The specification notes:
Specification discloses modifying labels based on user input. [Page 119]: "Some embodiments further comprise when the user input is indicative of the modification of the sample-level ECG label, modifying the sample-level ECG label based on the user input."
Step 2B: Updating data fields and generating reports are routine computer functions and insignificant extra-solution activity. They do not transform the abstract idea into patent-eligible subject matter. Rejected under § 101.
Claims 5 & 6 (Denoising & Annotation Display)
Step 1: Statutory.
Step 2A: Claim 5 adds processing with a trained decoder to obtain a denoised signal; Claim 6 adds annotating the denoised signal and displaying it in the GUI. This remains within the abstract concept of data processing and visual presentation for human review.
Step 2B: Denoising via a generic decoder and overlaying annotations on a display are conventional signal processing and UI techniques. The specification describes this as standard output formatting:
Specification discloses annotating and displaying denoised signals. [Page 120]: "Some embodiments further comprise: annotating the at least one ECG signal using the sample-level ECG labels, wherein the interactive GUI indicating the sample-level ECG labels comprises a display indicating the at least one annotated ECG signal." These elements are routine and do not provide significantly more. Rejected under § 101.
Claims 7 & 8 (Label Types & Metric Calculation)
Step 1: Statutory.
Step 2A: Claim 7 limits labels to P-wave, QRS complex, or T-wave. Claim 8 recites calculating standard ECG metrics (peaks, intervals, durations). These are mathematical/data analysis steps applied to physiological data. The specification lists these as standard outputs:
Specification discloses determining standard ECG metrics. [Page 120]: "Some embodiments further comprise determining one or more metrics using the sample-level ECG labels, the one or more metrics comprising a P-wave peak, a Q-wave peak... an RR interval, a PR segment... and/or a T-wave absence."
Step 2B: Specifying the type of data classified and calculating standard mathematical/physiological intervals are abstract mental processes/mathematical concepts. They do not integrate the exception into a practical application. Rejected under § 101.
Claims 9 & 11 (GUI Display Features)
Step 1: Statutory.
Step 2A/2B: These claims merely specify that the GUI displays the calculated metrics (Claim 9) or wave boundaries (Claim 11). Presenting data on a screen is a conventional output function. The specification confirms this is standard UI behavior:
Specification discloses GUI display of metrics and boundaries. [Page 120-121]: "In some embodiments, the interactive GUI further indicates the one or more metrics." and "In some embodiments, the interactive GUI further indicates the boundaries of the at least some of the plurality of ECG waves." Routine display features do not amount to significantly more. Rejected under § 101.
Claims 10 & 12 (Boundary Derivation & Classifier Architecture)
Step 1: Statutory.
Step 2A: Claim 10 recites deriving wave boundaries from labels; Claim 12 specifies the classifier uses convolutional, encoder, and decoder layers. Both describe data manipulation and standard neural network architectures. The specification notes:
Specification discloses classifier architecture. [Page 121]: "In some embodiments, the trained sample-level ECG classifier is a classification head comprising one or more convolutional layers, one or more encoder layers, and one or more decoder layers."
Step 2B: Deriving boundaries from classified data is a mathematical/data analysis step. Specifying a standard CNN/encoder-decoder architecture is a well-known, conventional AI implementation. Neither integrates the abstract idea into a practical application nor provides significantly more. Rejected under § 101.
Claims 13 & 14 (Data Acquisition via Sensors/Wearables)
Step 1: Statutory.
Step 2A/2B: These claims recite measuring the ECG signal using sensors or a wearable device. Data gathering is a well-known abstract concept. The specification treats this as standard input collection:
Specification discloses sensor-based data acquisition. [Page 120]: "Some embodiments further comprise measuring the at least one ECG signal using the ECG sensors." Using generic sensors or wearables to collect data is insignificant extra-solution activity and does not overcome the abstract idea rejection. Rejected under § 101.
Claims 17 & 18 (Encoder Architecture & Latent Mapping)
Step 1: Statutory.
Step 2A: Claim 17 specifies a convolutional neural network encoder; Claim 18 recites mapping high-dimensional data to a lower-dimensional latent representation. These are mathematical transformations and standard deep learning techniques. The specification states:
Specification discloses latent space mapping via CNNs. [Page 139]: "In some embodiments, the encoder is configured to map an input ECG signal from a high-dimensional space into a lower-dimensional latent representation, using multiple convolutional layers with non-linear activation functions."
Step 2B: Mathematical dimensionality reduction and standard CNN architectures are well-understood, routine, and conventional in machine learning. They do not amount to significantly more. Rejected under § 101.
Conclusion
All claims (1–20) are directed to the abstract idea of collecting physiological data, computationally classifying/processing it, and displaying results for human verification/modification. The additional elements recited across independent and dependent claims consist of generic computer components, standard neural network architectures, routine data acquisition parameters, and conventional GUI display/reporting functions. Under the Alice/Mayo framework, these elements neither integrate the abstract idea into a practical application nor amount to significantly more. Therefore, 35 U.S.C. § 101 rejections are appropriate for all claims.
Thus, taken alone, the additional elements do not amount to significantly more than the abstract idea identified above. Furthermore, looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually, and there is no indication that the combination of elements improves the functioning of a computer or improves any other technology, and their collective functions merely provide conventional computer implementation.
Therefore, whether taken individually or as an ordered combination, claim(s) 1-20 is/are nonetheless rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
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 for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-20 are rejected under 35 U.S.C. § 103 as being unpatentable over Pedalty et al. (US 2020/0352462), hereinafter Pedalty in view of Nenadovic et al. (US 2019/0038203), hereinafter Nenadovic.
Claim 1 (Method)
Complete Claim Limitations:
A method for labelling at least one electrocardiogram (ECG) signal comprising a plurality of samples, wherein a sample is an ECG measurement at a single time point, the method comprising:
(a) using at least one processor to perform:
(b) obtaining the at least one ECG signal, the at least one ECG signal having been previously measured using ECG sensors;
(c) encoding the at least one ECG signal to obtain a numeric encoding of the at least one ECG signal;
(d) processing the numeric encoding of the at least one ECG signal using a trained sample-level ECG classifier to obtain sample-level ECG labels for at least some of the plurality of samples, wherein a sample-level ECG label for a particular sample of the at least some of the plurality of samples is indicative of a respective portion of an ECG waveform to which the particular sample corresponds;
(e) generating an interactive graphical user interface (GUI) indicating the sample-level ECG labels for the at least some of the plurality of samples; and
(f) receiving user input via the interactive GUI, wherein the user input is indicative of a verification or a modification of a sample-level ECG label of the sample-level ECG labels.
Limitation (a) – "using at least one processor to perform":
Pedalty discloses a computing device comprising processing circuitry configured to perform the described operations. [0061]: "Processing circuitry 402, in one example, is configured to implement functionality and/or process instructions for execution within computing device 400. For example, processing circuitry 402 may be capable of processing instructions stored in storage device 408. Examples of processing circuitry 402 may include, any one or more of a microprocessor, a controller, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or equivalent discrete or integrated logic circuitry."
Limitation (b) – "obtaining the at least one ECG signal, the at least one ECG signal having been previously measured using ECG sensors":
Pedalty discloses receiving cardiac electrogram data sensed by a medical device (IMD 10) via electrodes. [0042]: "computing system 24 receives cardiac electrogram data sensed by a medical device, such as one of IMD 10 and external device 12. Computing system 24 applies a machine learning model of machine learning system 150, trained using cardiac electrogram data for a plurality of patients, to the received cardiac electrogram data to determine, based on the machine learning model, that an episode of arrhythmia has occurred in patient 4." [0047]: "Sensing circuitry 52 may monitor signals from electrodes 16A, 16B in order to monitor electrical activity of a heart of patient 4 of FIG. 1 and produce cardiac electrogram data for patient 4." [0080]: "IMD 10 senses cardiac electrogram data of patient 4. The cardiac electrogram data can be, e.g., an episodic ECG of patient 4 or a full-disclosure ECG of patient 4."
Limitation (c) – "encoding the at least one ECG signal to obtain a numeric encoding of the at least one ECG signal":
Pedalty discloses converting cardiac electrogram data into a numeric/intermediate representation for processing by the machine learning model. [0070]: "Machine learning system 450 may operate to convert the training data into vectors and tensors (e.g., multi-dimensional arrays) upon which machine learning system 450 may apply mathematical operations, such as linear algebraic, nonlinear, or alternative computation operations." [0076]: "processing circuitry 402 may generate, from the cardiac electrogram data, an intermediate representation of the cardiac electrogram data. For example, processing circuitry 402 may apply one or more signal processing, signal decomposition, wavelet decomposition, filtering, or noise reduction operations to the cardiac electrogram data to generate the intermediate representation of the cardiac electrogram data."
Limitation (d) – "processing the numeric encoding of the at least one ECG signal using a trained sample-level ECG classifier to obtain sample-level ECG labels for at least some of the plurality of samples, wherein a sample-level ECG label for a particular sample of the at least some of the plurality of samples is indicative of a respective portion of an ECG waveform to which the particular sample corresponds":
Pedalty discloses applying a trained machine learning model to cardiac electrogram data to classify arrhythmia at a per-timestamp (sample-level) granularity using class activation mapping. [0073]: "machine learning system 450 may process the cardiac electrogram data to derive a classification of the episode of arrhythmia (e.g., bradycardia, tachycardia, atrial fibrillation, ventricular fibrillation, or AV Block). Further, machine learning system 450 may determine, for each of arrhythmia type classification, class activation data indicating varying likelihoods of the classification over the period of time. For a given arrhythmia type, an amplitude of such likelihood values at different times corresponds to a probability that an arrhythmia is occurring at that time, with higher values corresponding to higher probability." [0074]: "Computing device 400 may use class activation mapping to identify regions of an input time series, e.g., of cardiac EGM data, that constitute the reason for the time series being given a particular classification by the machine learning model of machine learning system 450. A class activation map for a given classification may be a univariate time series where each element (e.g., at each timestamp at the sampling frequency of the input time series) may be a weighted sum or other value derived from the outputs of an intermediate layer of a neural network or other machine learning model." [0081]: "Machine learning system 150 of computing system 24 applies a machine learning model to the received cardiac electrogram data to detect an episode of arrhythmia in patient 4 (504). In some examples, the machine learning model is trained with a plurality of ECG episodes annotated by a clinician or a monitoring center for arrhythmias of several different types. In one example, machine learning system 150 applies the machine learning model to one or several subsegments of a normalized input ECG signal and generates arrhythmia labels and a likelihood of an occurrence of the arrhythmia."
Limitation (e) – "generating an interactive graphical user interface (GUI) indicating the sample-level ECG labels for the at least some of the plurality of samples":
Pedalty discloses generating a graphical display showing ECG data with color-coded annotations indicating the classification (labels) at different time segments. [0083]: "computing system 24 may apply color coding to indicate results (e.g., 'green' for low confidence than an episode of arrhythmia has occurred, 'yellow' for medium confidence than an episode of arrhythmia has occurred, or 'red' for a high confidence than an episode of arrhythmia has occurred)." [0119]: "FIG. 10C depicts display 1003 presenting advanced cardiac information. For example, display 1003 includes cardiac electrogram data 1010 and further depicts, for a plurality of segments of cardiac electrogram data 1010, a likelihood that an episode of cardiac arrhythmia of one or more types has occurred. For example, display 1003 colors segments for which computing system 24 has determined a high likelihood that atrial fibrillation has occurred in patient 4 in green (1012), segments for which computing system 24 has made an uncertain determination of whether atrial fibrillation has occurred in patient 4 in yellow (1014), and segments for which computing system 24 has determined a low likelihood that atrial fibrillation has occurred in patient 4 in red (1016)." [0084]: "In some examples, computing system 24 presents an ECG waveform and an annotation to the waveform to indicate where the episode of arrhythmia has occurred. In some examples, the annotation includes highlighting a section of the ECG, indicating a start and/or stop time of the episode of arrhythmia, or applying a graphical icon or text to the section of the ECG."
Limitation (f) – "receiving user input via the interactive GUI, wherein the user input is indicative of a verification or a modification of a sample-level ECG label of the sample-level ECG labels":
Pedalty discloses receiving user input to verify or modify the classification/label of an arrhythmia episode, which is then used to update the model. [0095]: "In another example, computing system 24 receives, from a user, a classification of an episode of arrhythmia as being of a particular type of arrhythmia. Machine learning system 150 uses the received classification to train or update the machine learning model or the arrhythmia threshold to increase the accuracy and performance of machine learning model 150." [0092]: "Computing system 24 receives, from a user, a selection of a type of arrhythmia (605) for the specific patient. For example, computing system may receive, as an input from a user via an interface of computing system 24, a selection of an arrhythmia such as bradycardia, tachycardia, atrial fibrillation, ventricular fibrillation, or AV Block."
However, Pedalty does not explicitly disclose the "interactive" nature of the GUI in the sense of a user directly verifying or modifying individual sample-level labels in real-time through the interface. Nenadovic discloses an interactive interface with user feedback for refining processing. [0093]: "Feedback data received in response to the display on display device 106 of the visualizations of the brainwave data from the sensors 102 may also be used to refine collector device 104 processes, for example." [0102]: "In some embodiments, the display device 106 provides feedback data to refine or update the processing by the server system 100." [0123]: "At 310, the server system 100 may receive feedback from display device 106 or other computing device to refine the processing to create individual thresholds or population based thresholds."
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to incorporate the interactive user feedback mechanism of Nenadovic into the ECG arrhythmia detection and visualization system of Pedalty, because both systems involve real-time physiological signal processing with graphical display and user interaction. Nenadovic states: "In some embodiments, the server system 100 implements machine learning to compute the brain value index based on historical data for the patient or other patients. In a first step, a classifier algorithm is created. Each patient has a series of Functionality Index values and a known outcome (e.g. A dichotomous outcome of panic or no panic). The output from the training set is used with a test set of new patient data in order to identify the anxiety state." The motivation is to allow a user to verify or correct the machine learning classification output, which is a well-known technique in medical signal processing to improve model accuracy.
Claim 19 (Computer-Readable Storage Medium)
Claim 19 is rejected under 35 U.S.C. § 103 as being unpatentable over Pedalty et al. (US 2020/0352462 A1) [Pedalty], in view of Nenadovic et al. (US 2019/0038203 A1) [Nenadovic].
Claim 19 recites a non-transitory computer-readable storage medium storing processor-executable instructions that perform the same method as Claim 1. The same limitation-by-limitation mapping applies as set forth above for Claim 1.
Pedalty discloses the storage of instructions on a computer-readable medium. [0151]: "If implemented in software, the functions may be stored as one or more instructions or code on a computer-readable medium and executed by a hardware-based processing unit. Computer-readable media may include non-transitory computer-readable media, which corresponds to a tangible medium such as data storage media (e.g., RAM, ROM, EEPROM, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer)." [0062]: "One or more storage devices 408 may be configured to store information within computing device 400 during operation. Storage device 408, in some examples, is described as a computer-readable storage medium."
The remaining limitations (obtaining ECG, encoding, processing with trained classifier, generating GUI, receiving user input) are mapped identically to Claim 1 as set forth above.
Claim 20 (System)
Claim 20 is rejected under 35 U.S.C. § 103 as being unpatentable over Pedalty et al. (US 2020/0352462 A1) [Pedalty], in view of Nenadovic et al. (US 2019/0038203 A1) [Nenadovic].
Claim 20 recites a system comprising a processor and a non-transitory computer-readable storage medium performing the same method as Claim 1. The same limitation-by-limitation mapping applies.
Pedalty discloses a computing device (system) comprising processing circuitry and a storage medium. [0012]: "this disclosure describes a computing device comprising: a storage medium; and processing circuitry operable coupled to the storage medium and configured to: receive cardiac electrogram data sensed by a medical device; apply a machine learning model, trained using cardiac electrogram data for a plurality of patients, to the received cardiac electrogram data to: determine, based on the machine learning model, that an episode of arrhythmia has occurred in the patient; and determine a level of confidence in the determination that the episode of arrhythmia has occurred in the patient; determine that the level of confidence in the determination that the episode of arrhythmia has occurred in the patient is greater than a predetermined threshold; and in response to determining that the level of confidence is greater than the predetermined threshold, output, for display to a user, at least a portion of the cardiac electrogram data, a first indication that the episode of arrhythmia has occurred in the patient, and a second indication of the level of confidence that the episode of arrhythmia has occurred in the patient." [0059]: "computing device 400 includes processing circuitry 402, one or more input devices 404, communication circuitry 406, one or more storage devices 408, user interface (UI) device(s) 410, and one or more output devices 412."
The remaining limitations are mapped identically to Claim 1 as set forth above.
II. REJECTION OF DEPENDENT CLAIMS 2–18
Claims 2 (Sampling Rate and Duration)
Complete Claim Limitation:
The method of claim 1, wherein the at least one ECG signal was previously measured at a sampling rate of between 128 Hz and 256 Hz and for a duration of between 10 seconds and fourteen days.
Pedalty discloses ECG data acquisition from an implantable medical device with configurable sampling and duration. [0080]: "IMD 10 senses cardiac electrogram data of patient 4. The cardiac electrogram data can be, e.g., an episodic ECG of patient 4 or a full-disclosure ECG of patient 4. Further, the cardiac electrogram data of patient 4 may be from a single-channel or multi-channel system." [0030]: "In some examples, IMD 10 may take the form of a Reveal LINQ™ Insertable Cardiac Monitor (ICM) or a Holter Heart Monitor, both available from Medtronic plc, of Dublin, Ireland."
Nenadovic discloses specific sampling rates and recording durations for physiological signal acquisition. [0126]: "The acquisition rate or sampling frequency may vary from 200 to 625 Hz. The sampling frequency is addressed in the algorithm used to calculate the phase synchrony. The prototype device has a default setting of 500 Hz acquisition rate. The duration of the recordings may vary from 2 minutes to 55 minutes." [0064]: "In some embodiments, the system includes a wearable device with particular sensor 102 or electrode placements to standardize the positioning of sensors 102 or electrodes to access brainwave signal data at specific brain locations that serve specific brain functions."
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to configure the ECG acquisition system of Pedalty with a sampling rate in the range of 128–256 Hz and a recording duration of 10 seconds to 14 days, as Nenadovic demonstrates that sampling rates and durations are configurable parameters in physiological signal monitoring systems. A sampling rate of 128–256 Hz is a well-known standard for ECG acquisition1 (e.g., Holter monitors), and a duration of 10 seconds to 14 days encompasses both short episodic recordings and long-term Holter monitoring, both of which are known in the art.
Claim 3 (Modifying Label Based on User Input)
Complete Claim Limitation:
The method of claim 1, further comprising: when the user input is indicative of the modification of the sample-level ECG label, modifying the sample-level ECG label based on the user input.
Pedalty discloses that user input (a classification of an arrhythmia) is used to modify/update the machine learning model's labels and thresholds. [0095]: "In another example, computing system 24 receives, from a user, a classification of an episode of arrhythmia as being of a particular type of arrhythmia. Machine learning system 150 uses the received classification to train or update the machine learning model or the arrhythmia threshold to increase the accuracy and performance of machine learning model 150. This may allow for increasing the accuracy and performance of machine learning system 150 in detecting and classifying episodes of arrhythmias of types that are difficult to detect, episodes of arrhythmias of types that are dependent on a unique medical diagnosis particular to a particular patient, or episodes of arrhythmias of types for which data is scarce, uncommon, or of low prevalence, or of arrhythmias whose detection performance in a specific patient might be sub-optimal due to factors such as device position, change in physiological state, etc."
Claim 4 (Generating a Report)
Complete Claim Limitation:
The method of claim 1, further comprising: after receiving the user input, generating a report indicating the sample-level ECG labels.
Pedalty discloses outputting/displaying the ECG data with annotations and confidence levels, which constitutes a report. [0083]: "In response to determining that the level of confidence is greater than the predetermined threshold (e.g., 'YES' block of 510), computing system 24 outputs the cardiac electrogram data for review by a clinician. In some examples, computing system 24 outputs a portion of the cardiac electrogram data, a first indication that the episode of arrhythmia has occurred in patient 4, and a second indication of the level of certainty in the determination that the episode of arrhythmia has occurred in patient 4 (512)." [0085]: "In one example, computing system 24 displays an indication that the episode of arrhythmia has occurred in the patient and one or more of the cardiac features that coincide with the episode of arrhythmia. In some examples, computing system 24 displays a classification of the episode of arrhythmia as a particular type of arrhythmia."
Claim 5 (Denoised ECG via Trained Decoder)
Complete Claim Limitation:
The method of claim 1, further comprising processing the numeric encoding of the at least one ECG signal using a trained decoder to obtain at least one denoised ECG signal.
Pedalty discloses generating an intermediate representation from cardiac electrogram data using signal processing operations. [0076]: "In further examples, processing circuitry 402 may generate, from the cardiac electrogram data, an intermediate representation of the cardiac electrogram data. For example, processing circuitry 402 may apply one or more signal processing, signal decomposition, wavelet decomposition, filtering, or noise reduction operations to the cardiac electrogram data to generate the intermediate representation of the cardiac electrogram data. In this example, machine learning system 450 processes such an intermediate representation of the cardiac electrogram data to detect and classify an episode of arrhythmia in patient 4."
Nenadovic discloses pre-processing of raw sensor data for noise filtering and artifact reduction. [0068]: "The collector device 104 is configured to pre-process the sensor data, such as by filtering out noise, to generate filtered brainwave signal data. As further examples, the collector device 104 may implement pre-processing for artifact reduction, reduction of volume conduction and reference electrode removal, for example." [0119]: "collector device 104 may pre-process the raw brainwave signal data for noise filtering, artifact reduction, reduction of volume conduction and reference electrode removal, for example."
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to incorporate a trained decoder (as a denoising step) into the ECG processing pipeline of Pedalty, because Nenadovic demonstrates that pre-processing for noise filtering and artifact reduction is a standard step in physiological signal processing. The use of a trained decoder to denoise encoded signals is a well-known technique in deep learning (autoencoders), and combining this with Pedalty's intermediate representation generation would be an obvious improvement.
Claim 6 (Annotating Denoised ECG in GUI)
Complete Claim Limitation:
The method of claim 5, further comprising annotating the at least one denoised ECG signal using the sample-level ECG labels, wherein the interactive GUI indicating the sample-level ECG labels comprises a display indicating the at least one annotated denoised ECG signal.
Pedalty discloses displaying an ECG waveform with annotations indicating where arrhythmia has occurred. [0084]: "In some examples, computing system 24 presents an ECG waveform and an annotation to the waveform to indicate where the episode of arrhythmia has occurred. In some examples, the annotation includes highlighting a section of the ECG, indicating a start and/or stop time of the episode of arrhythmia, or applying a graphical icon or text to the section of the ECG. Computing system 24 may use a wide variety of different visualization techniques, such as color-coding, hatching, images or icons, shapes, indicators of different size, light, sound, textual notifications, etc. to simply the information conveyed to the user." [0118]: "FIG. 10B depicts display 1002 presenting basic cardiac information, e.g., ECG segment 1020 of cardiac electrogram data 1010 during which computing system 24 has determined that an episode of arrhythmia in patient 4 has occurred."
Claim 7 (P-wave, QRS, T-wave Labels)
Complete Claim Limitation:
The method of claim 1, wherein each of at least some of the sample-level ECG labels is selected from among: a P-wave label, a QRS complex label, and/or a T-wave label.
Pedalty explicitly discloses ECG features including P-waves, QRS complexes, and T-waves as features used in arrhythmia detection and classification. [0053]: "For example, feature delineation may be used to identify features such as R-waves, QRS complexes, P-waves, T-waves, rates of such features, intervals between such features, feature morphology, widths or amplitudes of such features, or other or other types of cardiac features or characteristics of such features not expressly described herein." [0101]: "For example, for an electrophysiologist or subject matter expert, computing system 24 may display, e.g. for an episode of AF, a start and stop time of each episode of arrhythmia presented along with a mean RR during each AF segment contrasted against a mean RR baseline, an RR variation during each AF segment contrasted against an RR variation baseline, P-wave evidence during the AF segment contrasted with a P-wave baseline, and morphology variation." [0115]: "FIG. 9C depicts an example graphical illustration 920 of a likelihood that machine learning system 150 detects atrial fibrillation (AF). The example of FIG. 9C depicts a likelihood that machine learning system 150 detects AF a function of mean heartrate, RR variability and P-waves."
Claim 8 (Determining Metrics from Labels)
Complete Claim Limitation:
The method of claim 1, further comprising determining one or more metrics using the sample-level ECG labels, the one or more metrics comprising a P-wave peak, a Q-wave peak, an R-wave peak, an S-wave peak, a T-wave peak, an RR interval, a PR segment, a PR interval, a QRS interval, a QT interval, an ST segment, a P-wave duration, a T-wave duration, a QT corrected (QTc) interval, a P-wave amplitude, a T-wave amplitude, a P-wave absence, and/or a T-wave absence.
Pedalty discloses determining cardiac metrics including RR intervals, P-wave evidence, and morphology variation from the ECG data. [0101]: "For example, for an electrophysiologist or subject matter expert, computing system 24 may display, e.g. for an episode of AF, a start and stop time of each episode of arrhythmia presented along with a mean RR during each AF segment contrasted against a mean RR baseline, an RR variation during each AF segment contrasted against an RR variation baseline, P-wave evidence during the AF segment contrasted with a P-wave baseline, and morphology variation." [0072]: "The cardiac features may include, e.g., one or more of a mean heartrate of the patient, a minimum heartrate of the patient, a maximum heartrate of the patient, a PR interval of a heart of the patient, a variability of heartrate of the patient, one or more amplitudes of one or more features of an electrocardiogram (ECG) of the patient, or an interval between the or more features of the ECG of the patient, a T-wave alternans, QRS morphology measures, or other types of cardiac features not expressly described herein." [0121]: "FIG. 10D depicts display 1004 presenting advanced cardiac information. For example, display 1004 depicts information substantially similar to display 1003 of FIG. 10C. Further, display 1004 further depicts reference cardiac electrogram data 1054 that depicts a baseline ECG signal (e.g., where no AF is present) and reference cardiac electrogram data 1052 that depicts an ECG signal during an episode of AF. Furthermore, display 1004 includes RR interval diagram 1050, which displays RR intervals of patient 4 over the duration of cardiac electrogram data 1010."
Claim 9 (GUI Indicates Metrics)
Complete Claim Limitation:
The method of claim 8, wherein the interactive GUI further indicates the one or more metrics.
Pedalty discloses displaying cardiac metrics (RR intervals, P-wave evidence, morphology) on the graphical interface. [0121]: "display 1004 includes RR interval diagram 1050, which displays RR intervals of patient 4 over the duration of cardiac electrogram data 1010. RR interval diagram 1050 demonstrates high, un-patterned RR variability during the presence of AF (e.g., from time t0 to about time t100) and patterned beats during a lack of AF (e.g., from time t150 to time t250)." [0101]: "computing system 24 may display, e.g. for an episode of AF, a start and stop time of each episode of arrhythmia presented along with a mean RR during each AF segment contrasted against a mean RR baseline, an RR variation during each AF segment contrasted against an RR variation baseline, P-wave evidence during the AF segment contrasted with a P-wave baseline, and morphology variation."
Claim 10 (Deriving Boundaries of ECG Waves)
Complete Claim Limitation:
The method of claim 1, wherein the at least one ECG signal comprises a plurality of ECG waves, the method further comprising deriving boundaries of at least some of the plurality of ECG waves using the sample-level ECG labels, wherein the plurality of ECG waves comprise one or more P-waves, one or more Q-waves, one or more R-waves, one or more S-waves, and/or one or more T-waves.
Pedalty discloses identifying and delineating ECG wave features (P-waves, QRS complexes, T-waves, R-waves) and their boundaries. [0053]: "For example, feature delineation may be used to identify features such as R-waves, QRS complexes, P-waves, T-waves, rates of such features, intervals between such features, feature morphology, widths or amplitudes of such features, or other or other types of cardiac features or characteristics of such features not expressly described herein. Feature delineation may include feature extraction, signal filtering, peak detection, refractory analysis, or other types of signal processing, feature engineering, or detection rule development." [0086]: "In some examples, computing system 24 displays a subsection of the cardiac electrogram data obtained from patient 4 that coincides with the episode of arrhythmia. For example, computing system 24 may identify a subsection of the cardiac electrogram data of patient 4, wherein the subsection comprises cardiac electrogram data for a first time period prior to the episode of arrhythmia (e.g., typically less than 10 minutes prior to the onset of the episode of arrhythmia), a second time period during the occurrence of the episode of arrhythmia, and a third time period after the episode of arrhythmia (e.g., typically less than 10 minutes after the cessation of the episode of arrhythmia)."
Claim 11 (GUI Indicates Boundaries)
Complete Claim Limitation:
The method of claim 10, wherein the interactive GUI further indicates the boundaries of the at least some of the plurality of ECG waves.
Pedalty discloses displaying ECG waveforms with annotations indicating start/stop times and highlighting sections. [0084]: "In some examples, computing system 24 presents an ECG waveform and an annotation to the waveform to indicate where the episode of arrhythmia has occurred. In some examples, the annotation includes highlighting a section of the ECG, indicating a start and/or stop time of the episode of arrhythmia, or applying a graphical icon or text to the section of the ECG." [0119]: "display 1003 colors segments for which computing system 24 has determined a high likelihood that atrial fibrillation has occurred in patient 4 in green (1012), segments for which computing system 24 has made an uncertain determination of whether atrial fibrillation has occurred in patient 4 in yellow (1014), and segments for which computing system 24 has determined a low likelihood that atrial fibrillation has occurred in patient 4 in red (1016)."
Claim 12 (Classifier with Convolutional, Encoder, and Decoder Layers)
Complete Claim Limitation:
The method of claim 1, wherein the trained sample-level ECG classifier is a classification head comprising one or more convolutional layers, one or more encoder layers, and one or more decoder layers.
Pedalty discloses a machine learning model (neural network) for ECG classification. [0033]: "In some examples, computing system 24 may include one or more devices that implement a machine learning system 150, such as neural network, a deep learning system, or other type of predictive analytics system." [0070]: "Machine learning system 450 may operate to convert the training data into vectors and tensors (e.g., multi-dimensional arrays) upon which machine learning system 450 may apply mathematical operations, such as linear algebraic, nonlinear, or alternative computation operations." [0074]: "A class activation map for a given classification may be a univariate time series where each element (e.g., at each timestamp at the sampling frequency of the input time series) may be a weighted sum or other value derived from the outputs of an intermediate layer of a neural network or other machine learning model. The intermediate layer may be a global average pooling layer and/or last layer prior to the output layer neurons for each classification."
Nenadovic discloses a processing system with encoder/decoder architecture for signal processing. [0107]: "Processing unit 232 interacts with phase synchronization unit 218 and index unit 220 to transform raw sensor data to generate and update connectivity matrix data (and connectivity map) and brain value index data." [0119]: "Real-time processing may be achieved by implementing data analysis processes in a high-performance programming language such as C, C++, or Java."
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to implement the machine learning model of Pedalty using a convolutional neural network architecture with encoder and decoder layers, because Nenadovic demonstrates the use of multi-stage processing (pre-processing/encoding → analysis → output/decoding) in physiological signal processing, and convolutional neural networks with encoder-decoder architectures are well-known in the art for time-series classification tasks.
Claim 13 (Measuring ECG Using Sensors)
Complete Claim Limitation:
The method of claim 1, further comprising measuring the at least one ECG signal using the ECG sensors.
Pedalty discloses measuring cardiac electrogram data using electrodes/sensors on an implantable medical device. [0047]: "Sensing circuitry 52 may monitor signals from electrodes 16A, 16B in order to monitor electrical activity of a heart of patient 4 of FIG. 1 and produce cardiac electrogram data for patient 4. Sensing circuitry 52 may produce a digitized version of the cardiac electrogram as well as indications of the timing of depolarizations." [0080]: "IMD 10 senses cardiac electrogram data of patient 4."
Claim 14 (Wearable Device with ECG Sensors)
Complete Claim Limitation:
The method of claim 13, wherein measuring the at least one ECG signal using the ECG sensors comprises measuring the at least one ECG signal using a wearable device comprising the ECG sensors.
Pedalty discloses wearable devices for ECG monitoring. [0031]: "In some examples, the example techniques and systems described herein may be used with an external medical device in addition to, or instead of IMD 10. In some examples, the external medical device is a wearable electronic device, such as the SEEQ™ Mobile Cardiac Telemetry (MCT) system available from Medtronic plc, of Dublin, Ireland, or another type of wearable 'smart' electronic apparel, such as a 'smart' watch, 'smart' patch, or 'smart' glasses. Such an external medical device may be positioned externally to patient 4 (e.g., positioned on the skin of patient 4) and may carry out any or all of the functions described herein with respect to IMD 10." [0038]: "In some such examples, external device 12, and/or any other device of medical device system 2, may be a wearable device, (e.g., in the form of a watch, necklace, or other wearable item)."
Claim 15 (Holter Monitor, ≥3 Leads, 128–256 Hz, 1–14 Days)
Complete Claim Limitation:
The method of claim 14, wherein measuring the at least one ECG signal using the wearable device comprises: measuring the at least one ECG signal using a Holter monitor comprising at least three ECG leads, at a sampling rate of between 128 Hz and 256 Hz, and for a duration of between one and fourteen days.
Pedalty discloses a Holter Heart Monitor for ECG monitoring. [0030]: "In some examples, IMD 10 may take the form of a Reveal LINQ™ Insertable Cardiac Monitor (ICM) or a Holter Heart Monitor, both available from Medtronic plc, of Dublin, Ireland." [0055]: "the techniques may be implemented with… an insertable cardiac monitor, such as the Reveal LINQ™ ICM, also commercially available from Medtronic PLC, a neurostimulator, a drug delivery device, a medical device external to patient 4, a wearable device such as a wearable cardioverter defibrillator, a fitness tracker, or other wearable device, a mobile device, such as a mobile phone, a 'smart' phone, a laptop, a tablet computer, a personal digital assistant (PDA), or 'smart' apparel such as 'smart' glasses, a 'smart' patch, or a 'smart' watch."
Nenadovic discloses specific sampling rates and recording durations. [0126]: "The acquisition rate or sampling frequency may vary from 200 to 625 Hz. The sampling frequency is addressed in the algorithm used to calculate the phase synchrony. The prototype device has a default setting of 500 Hz acquisition rate. The duration of the recordings may vary from 2 minutes to 55 minutes." [0064]: "In some embodiments, the system includes a wearable device with particular sensor 102 or electrode placements to standardize the positioning of sensors 102 or electrodes to access brainwave signal data at specific brain locations that serve specific brain functions."
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to configure the Holter monitor of Pedalty with at least three ECG leads, a sampling rate of 128–256 Hz, and a recording duration of 1–14 days, because Nenadovic demonstrates that sampling rates and durations are configurable parameters, and multi-lead Holter monitoring (≥3 leads) is a well-known standard in the art for comprehensive ECG recording.
Claim 16 (Smartwatch, 1 Lead, 128–256 Hz, 10 sec–24 hrs)
Complete Claim Limitation:
The method of claim 14, wherein measuring the at least one ECG signal using the wearable device comprises: measuring the at least one ECG signal using a smartwatch comprising one ECG lead, at a sampling rate of between 128 Hz and 256 Hz, and for a duration of between 10 seconds and 24 hours.
Pedalty discloses a smartwatch as a wearable device for ECG monitoring. [0031]: "In some examples, the external medical device is a wearable electronic device, such as the SEEQ™ Mobile Cardiac Telemetry (MCT) system available from Medtronic plc, of Dublin, Ireland, or another type of wearable 'smart' electronic apparel, such as a 'smart' watch, 'smart' patch, or 'smart' glasses." [0055]: "a wearable device such as a wearable cardioverter defibrillator, a fitness tracker, or other wearable device, a mobile device, such as a mobile phone, a 'smart' phone, a laptop, a tablet computer, a personal digital assistant (PDA), or 'smart' apparel such as 'smart' glasses, a 'smart' patch, or a 'smart' watch."
Nenadovic discloses configurable sampling rates and short-duration recordings. [0126]: "The acquisition rate or sampling frequency may vary from 200 to 625 Hz… The duration of the recordings may vary from 2 minutes to 55 minutes." [0064]: "In some embodiments, the system includes a wearable device with particular sensor 102 or electrode placements to standardize the positioning of sensors 102 or electrodes to access brainwave signal data at specific brain locations that serve specific brain functions."
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use a smartwatch with a single ECG lead for short-duration (10 seconds to 24 hours) ECG recording at 128–256 Hz, because Pedalty already discloses smartwatch-based ECG monitoring and Nenadovic demonstrates that sampling rates and durations are configurable. Single-lead smartwatch ECG (e.g., Apple Watch ECG) is a well-known consumer medical device.
Claim 17 (Encoder is a Convolutional Neural Network)
Complete Claim Limitation:
The method of claim 1, wherein encoding the at least one ECG signal to obtain a numeric encoding of the at least one ECG signal comprises encoding the at least one ECG signal using an encoder, wherein the encoder is a convolutional neural network (i.e., a deep network).
Pedalty discloses using a neural network (deep learning system) to process cardiac electrogram data, which inherently involves encoding the input signal. [0033]: "In some examples, computing system 24 may include one or more devices that implement a machine learning system 150, such as neural network, a deep learning system, or other type of predictive analytics system." [0070]: "Machine learning system 450 may operate to convert the training data into vectors and tensors (e.g., multi-dimensional arrays) upon which machine learning system 450 may apply mathematical operations, such as linear algebraic, nonlinear, or alternative computation operations. Machine learning system 450 uses the training data 104 to teach the machine learning model to weigh different features depicted in the cardiac electrogram data." [0074]: "A class activation map for a given classification may be a univariate time series where each element (e.g., at each timestamp at the sampling frequency of the input time series) may be a weighted sum or other value derived from the outputs of an intermediate layer of a neural network or other machine learning model."
Claim 18 (Encoder Maps to Lower-Dimensional Latent Representation)
Complete Claim Limitation:
The method of claim 17, wherein the encoder is configured to map an input ECG signal from a high-dimensional space into a lower-dimensional latent representation, using multiple convolutional layers with non-linear activation functions.
Pedalty discloses converting cardiac electrogram data into a lower-dimensional intermediate representation using signal processing and neural network operations. [0076]: "In further examples, processing circuitry 402 may generate, from the cardiac electrogram data, an intermediate representation of the cardiac electrogram data. For example, processing circuitry 402 may apply one or more signal processing, signal decomposition, wavelet decomposition, filtering, or noise reduction operations to the cardiac electrogram data to generate the intermediate representation of the cardiac electrogram data. In this example, machine learning system 450 processes such an intermediate representation of the cardiac electrogram data to detect and classify an episode of arrhythmia in patient 4. Furthermore, machine learning system may train the machine learning model via a plurality of training intermediate representations labeled with episodes of arrhythmia, instead of the plurality of raw ECG waveforms labeled with episodes of arrhythmia as described above. The use of such intermediate representations of the cardiac electrogram data may allow for the training and development of a lighter-weight, less computationally complex machine learning model by machine learning system 450." [0070]: "Machine learning system 450 may operate to convert the training data into vectors and tensors (e.g., multi-dimensional arrays) upon which machine learning system 450 may apply mathematical operations, such as linear algebraic, nonlinear, or alternative computation operations."
Conclusion
The prior art made of record2 and NOT relied upon is considered pertinent to applicant's disclosure:
Liu3: Recent advances of Internet of Medical Things have allowed for continuous heart rhythm monitoring in a comfortable fashion. Single lead Electrocardiograph (ECG) is first collected by the wearable devices, and then some intelligent approaches are employed for automatic recognition of heart rhythms. Because the single lead ECG wave is different from traditional 12-leads Holter-based ECG signal in terms of high noise/artifact and the missing of other channels, specific algorithms for pattern recognition of the single lead ECG waves have been proposed in recent years. This paper systematically surveys state-of-the-art methods for screening atrial fibrillation from a single lead ECG wave. The database and performance metrics for this problem are demonstrated, the data preprocessing and feature extraction techniques are collected, and then the learning methods in terms of machine learning and deep learning are comparatively summarized. Specifically, the techniques for data preprocessing are reviewed and the most common and powerful features are listed, which are capable of providing a guideline for researchers aiming at developing AF detection algorithms. Finally, we discuss the potential contributors that are probably helpful for screening the atrial fibrillation from a single lead ECG wave.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL EZEWOKO whose telephone number is 571 272 7850. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Fonya Long can be reached on 571 270 5096. The fax phone number for the organization where this application or proceeding is assigned is 571-273-7850.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/MICHAEL I EZEWOKO/Primary Examiner, Art Unit 3682
1 See Liu, Elsevier, 2021, pp 245-258
2Please see Form 892 for complete listing
3 See Liu, Elsevier, 2021, pp 245-258