# US 11,896,399 B2 · Single channel and dual channel noise detection systems and techniques > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,896,399 B2 - Document ID: US11896399B2 - Status: Granted - Kind: B2 - Application number: 17/646,880 - Filed: 2022-01-04 - Published: 2022-07-21 - Granted: 2024-02-13 - Earliest claimed: 2019-03-20 - Assignees: ZOLL Medical Corp tion - Applicants: ZOLL Medical Corporation - Inventors: Jeffery T. Mitchell; Michael A. Sipe; Francesco Nicolo - Web page: https://patentgrep.com/patent/US11896399B2 ## CPC - A61B 5/7203: {for noise prevention, reduction or removal} - A61B 5/0006: {ECG or EEG signals} - A61B 5/256: Wearable electrodes, e.g. having straps or bands - A61B 5/33: specially adapted for cooperation with other devices - A61B 5/346: Analysis of electrocardiograms - A61B 5/35: by template matching - A61B 5/352: Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval - A61B 5/361: Detecting fibrillation - A61B 5/6804: {Garments; Clothes} - A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems} - G16H 40/60: for the operation of medical equipment or devices - A61B 5/363: Detecting tachycardia or bradycardia - A61B 5/366: Detecting abnormal QRS complex, e.g. widening - A61B 5/6833: {Adhesive patches} - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G16H 50/30: for calculating health indices; for individual health risk assessment - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract An ECG processing system for identifying noisy ECG data segments is provided. The ECG processing system includes a network interface and a processor. The network interface is configured to receive a first collection of ECG data segments from wearable medical devices associated with a plurality of patients, each wearable medical device of the wearable medical devices being configured to be continuously worn by a patient for an extended period of time. The processor is configured to produce a second collection of ECG data segments from the first collection of ECG data segments that excludes noisy ECG data segments. ## Claims ### Claim 1 A method of processing noisy electrocardiogram (ECG) data segments via a computer system, the method comprising: (a) receiving, by the computer system, a first collection of ECG data segments recorded over a continuous and extended period of time from one or more ECG channels of wearable medical devices associated with a plurality of patients; (b) for each ECG data segment of the first collection, transforming the ECG data segment into a corresponding ECG baseline representation by (i) dividing the ECG data segment into a plurality of sample periods, each sample period of the plurality of sample periods spanning between 2 and 8 seconds, and (ii) removing, for each sample period within the plurality of sample periods, ECG data collected within the sample period having one or more fiducial peaks that transgress one or more threshold values corresponding to the one or more fiducial peaks, after transforming the ECG data segment into the corresponding ECG baseline representation, fitting the corresponding ECG baseline representation to a function comprising at least one coefficient, comparing the at least one coefficient to at least one threshold value corresponding to the at least one coefficient, and identifying the ECG data segment as a noisy ECG data segment where the at least one coefficient transgresses the at least one threshold value corresponding to the at least one coefficient; (c) producing a second collection of ECG data segments from the first collection of ECG data segments that excludes the noisy ECG data segments; (d) outputting one or more ECG metrics relating to the plurality of patients based on the second collection of ECG data segments; (e) analyzing the one or more ECG metrics to determine a current heart failure condition of at least one of the plurality of patients; and (f) based on the current heart failure condition of the at least one of the plurality of patients, causing one or more therapy electrodes of the wearable medical device associated with the at least one of the plurality of patients to deliver a treatment to the at least one of the plurality of patients. ### Claim 2 (depends on 1) The method of claim 1, further comprising updating the first collection of ECG data segments over time to include additional ECG data segments. ### Claim 3 (depends on 2) The method of claim 2, further comprising repeating operations (a)-(d) after a duration of time. ### Claim 4 (depends on 3) The method of claim 3, wherein repeating the operations (a)-(d) after the duration of time comprises repeating the operations (a)-(d) after one or more of 30 minutes, 1 hour, 4 hours, 24 hours, 1 week, 2 weeks, or 1 month. ### Claim 5 (depends on 3) The method of claim 3, further comprising determining one or more trends in the one or more ECG metrics over the duration of time. ### Claim 6 (depends on 1) The method of claim 1, wherein fitting the corresponding ECG baseline representation comprises fitting the corresponding ECG baseline representation to a polynomial. ### Claim 7 (depends on 6) The method of claim 6, wherein comparing the at least one coefficient to the at least one threshold value corresponding to the at least one coefficient comprises comparing a coefficient of a first-degree monomial of a third-degree polynomial to the at least one threshold value corresponding to the at least one coefficient. ### Claim 8 (depends on 7) The method of claim 7, wherein comparing the coefficient of the first-degree monomial to the at least one threshold value corresponding to the at least one coefficient comprises comparing the coefficient of the first-degree monomial to a range of threshold values between −0.5 and 0.5. ### Claim 9 (depends on 1) The method of claim 1, further comprising determining the at least one threshold value corresponding to the at least one coefficient based on the first collection of ECG data segments. ### Claim 10 (depends on 1) The method of claim 1, wherein fitting the corresponding ECG baseline representation comprises using linear regression to fit the corresponding ECG baseline representation of the ECG data segment to the function. ### Claim 11 (depends on 1) The method of claim 1, further comprising: determining, for each sample period within the plurality of sample periods, a mean of ECG data collected within the sample period; determining, for each sample period within the plurality of sample periods, a standard deviation of ECG data collected within the sample period; and determining, for each sample period within the plurality of sample periods, the one or more threshold values corresponding to the one or more fiducial peaks based on the mean of the ECG data collected within the sample period and the standard deviation of the ECG data collected within the sample period. ### Claim 12 (depends on 1) The method of claim 1, wherein receiving the first collection of ECG data segments comprises receiving ECG data segments spanning between 15 and 120 seconds. ### Claim 13 (depends on 1) The method of claim 1, receiving the first collection of ECG data segments comprises receiving ECG data segments having an average length of one or more of about 15 seconds, about 30 seconds, about 45 seconds, about 60 seconds, about 90 seconds, about 120 seconds, about 150 seconds, about 180 seconds, about 5 minutes, about 10 minutes, or about 15 minutes. ### Claim 14 (depends on 1) The method of claim 1, wherein outputting the one or more ECG metrics comprises outputting one or more of a heart rate metric, a heart rate variability metric, a QRS duration metric, a QT interval metric, a heart rate turbulence metric, or pre-ventricular contraction (PVC) burden metric. ### Claim 15 (depends on 14) The method of claim 14, wherein outputting the one or more ECG metrics comprises providing the one or more ECG metrics to a cardiac prediction process. ### Claim 16 (depends on 1) The method of claim 1, wherein outputting the one or more ECG metrics comprises outputting one or more ECG metrics indicative of one or more arrhythmias comprising one or more of ventricular tachycardia, ventricular fibrillation, bradycardia, tachycardia, asystole, pause, bigeminy, or trigeminy. ### Claim 17 (depends on 1) The method of claim 1, further comprising: acquiring, by the wearable medical devices, the first collection of ECG data segments via dry ECG electrodes; and transmitting, by the wearable medical devices, the first collection of ECG data segments to the computer system. ### Claim 18 (depends on 1) The method of claim 1, further comprising: acquiring, by the wearable medical devices, the first collection of ECG data segments via adhesively attached ECG electrodes; and transmitting, by the wearable medical devices, the first collection of ECG data segments to the computer system. ### Claim 19 (depends on 1) The method of claim 1, further comprising analyzing the one or more ECG metrics to determine a change in the current heart failure condition of the at least one of the plurality of patients.