# US 11,896,387 B2 · Methods, systems, and devices for detecting sleep and apnea events > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,896,387 B2 - Document ID: US11896387B2 - Status: Granted - Kind: B2 - Application number: 17/235,807 - Filed: 2021-04-20 - Published: 2021-12-02 - Granted: 2024-02-13 - Earliest claimed: 2020-06-02 - Assignees: Pacesetter, Inc. - Applicants: Pacesetter, Inc. - Inventors: Jong Gill; Prakrit Shrestha; Kyungmoo Ryu - Web page: https://patentgrep.com/patent/US11896387B2 ## CPC - A61B 5/4818: {Sleep apnoea} - A61B 5/0205: Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition - A61B 5/1116: {Determining posture transitions} - A61B 5/1118: {Determining activity level} - A61B 5/349: Detecting specific parameters of the electrocardiograph cycle - A61B 5/366: Detecting abnormal QRS complex, e.g. widening - A61B 5/4809: {Sleep detection, i.e. determining whether a subject is asleep or not} - A61B 5/686: {Permanently implanted devices, e.g. pacemakers, other stimulators, biochips (A61B5/6861 takes precedence)} - A61B 5/7221: {Determining signal validity, reliability or quality (preventing, reducing or removing noise induced by motion artefacts A61B5/7207; noise originating from a therapeutic or surgical apparatus A61B5/7217)} - G16H 40/67: for remote operation - A61B 5/02405: {Determining heart rate variability} - A61B 5/352: Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval - A61B 5/353: Detecting P-waves - A61B 5/355: Detecting T-waves - A61B 5/358: Detecting ST segments - A61B 5/36: Detecting PQ interval, PR interval or QT interval - A61B 2562/0219: Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches - 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 Described herein are methods, devices, and systems that use electrogram (EGM) or electrocardiogram (ECG) data for sleep apnea detection. An apparatus and method detect potential apnea events (an apnea or hypopnea event) using a signal indicative of cardiac electrical activity of a patient's heart, such as an EGM or ECG. Variations in one or more morphological or temporal features of the signal over several cardiac cycles are determined and used to detect a potential apnea event in a measurement period. Checks can then be made for a number of factors which could result in a false detection of an apnea event and if such factors are not present, an apnea event is recorded. Described herein are also methods, devices, and systems for classifying a patient as being asleep or awake, which can be used to selectively enable and disable sleep apnea detection monitoring, as well as in other manners. ## Claims ### Claim 1 An apparatus, comprising: sensing circuitry couplable to electrodes and configured to sense an electrocardiogram (ECG) or electrogram (EGM) signal indicative of cardiac electrical activity of a patient's heart; and at least one processor configured to determine a measure of short-term variation (STV) and a measure of long-term variation (LTV) in a feature of the ECG or EGM signal over a measurement period that includes a plurality of cardiac cycles; and detect a potential apnea event in the measurement period based on the measure of STV and the measure of LTV in the feature of the ECG or EGM signal; wherein the feature comprises one of a morphological feature or a temporal feature. ### Claim 2 (depends on 1) The apparatus of claim 1, wherein the apparatus comprises one of an implantable pacemaker, an implantable cardiac defibrillator, an implantable cardiac monitor, or a non-implanted apparatus. ### Claim 3 (depends on 1) The apparatus of claim 1, wherein the at least one processor is configured to detect the potential apnea event by determining that the measure of LTV is greater than the measure of STV for at least the measurement period. ### Claim 4 (depends on 1) The apparatus of claim 1, wherein the at least one processor is configured to detect the potential apnea event by determining that the measure of LTV is greater than the measure of STV for at least the measurement period, and the measure of STV is less that a specified threshold for at least the measurement period. ### Claim 5 (depends on 1) The apparatus of claim 1, wherein the at least one processor is configured to: identify individual cardiac cycles within the ECG or EGM signal indicative of cardiac electrical activity of a patient's heart; determine the measure of STV based on a first number of the individual cardiac cycles; and determine the measure of LTV based on a second number of the individual cardiac cycles, wherein the second number is greater than the first number. ### Claim 6 (depends on 1) The apparatus of claim 1, wherein the feature of the ECG or EGM signal, for which the measure of STV and the measure of LTV are determined over the measurement period, comprises a morphological feature, which comprises one of: an area under a curve of a QRS complex, R-wave, T-wave, ST-region, or evoked response; a maximum amplitude of a QRS complex, R-wave, T-wave, or evoked response; or a peak-to-peak amplitude of a QRS complex, R-wave, T-wave, or evoked response. ### Claim 7 (depends on 1) The apparatus of claim 1, wherein the feature of the ECG or EGM signal, for which the measure of STV and the measure of LTV are determined over the measurement period, comprises a temporal feature, which comprises one of: RR interval duration; PR interval duration; QT interval duration; QRS complex duration; AR interval duration; PV interval duration; or evoked response duration. ### Claim 8 (depends on 1) The apparatus of claim 1, wherein each of the measure of STV and the measure of LTV in the feature of the ECG or EGM signal over the measurement period is one of: a standard deviation of the feature; a standard deviation of the feature divided by an average of the feature; a difference between a maximum and a mean of the feature; a difference between a maximum and a minimum of the feature; a difference between a second maximum and a second mean of the feature; a difference between an Nth maximum and an Nth mean of the feature; or any one of said differences divided by an average of the feature. ### Claim 9 (depends on 1) The apparatus of claim 1, further comprising an accelerometer that alone or in combination with the at least one processor is used to obtain posture information and activity information, wherein the at least one processor is further configured to: classify the patient as being asleep based on the posture information and the activity information; classify the patient as being awake based on at least one of the posture information or the activity information; enable the determining of the measure of STV and the measure of LTV that are used to detect the potential apnea event, in response to the patient being classified as being asleep; and disable the determining of the measure of STV and the measure of LTV that are used to detect the potential apnea event, in response to the patient being classified as being awake. ### Claim 10 (depends on 1) The apparatus of claim 1, wherein the at least one processor is further configured to determine whether the potential apnea event is a true apnea event or a false detection by analyzing a portion of the ECG or EGM signal preceding the measurement period in which the potential apnea event was detected to determine whether a heart rhythm change likely caused the potential apnea event to be detected. ### Claim 11 (depends on 1) The apparatus of claim 1, wherein the apparatus comprises an implantable medical device (IMD) that is configured to selectively deliver stimulation therapy under control of the at least one processor. ### Claim 12 A method for use by an implantable medical device (IMD) including sensing circuitry, electrodes, an accelerometer, and at least one processor, the method comprising: using the sensing circuitry, coupled to the electrodes, to sense an electrocardiogram (ECG) or electrogram (EGM) signal indicative of cardiac electrical activity of a patient's heart; using the accelerometer to obtain posture information and activity information for the patient; during a first period of time, the at least one processor classifying the patient as being asleep based on the posture information and the activity information obtained from the accelerometer, and in response thereto the at least one processor enabling monitoring for apnea, which includes determining a measure of short-term variation (STV) and a measure of long-term variation (LTV) of a feature of the ECG or EGM signal over a measurement period that includes a plurality of cardiac cycles; and detecting a potential apnea event in the measurement period based on the measure of STV and the measure of LTV in the feature of the ECG or EGM signal; wherein the feature comprises one of a morphological feature or a temporal feature; and during a second period of time, the at least one processor classifying the patient as being awake based on further posture information and further activity information obtained from the accelerometer, and in response thereto the at least one processor disabling the monitoring for apnea. ### Claim 13 (depends on 12) The method of claim 12, further comprising: the at least one processor identifying individual cardiac cycles within the ECG or EGM signal; wherein the measure of STV is determined based on a first number of the individual cardiac cycles, and the measure of LTV is determined based on a second number of the individual cardiac cycles, wherein the second number is greater than the first number. ### Claim 14 (depends on 12) The method of claim 12, further comprising: the at least one processor determining whether the potential apnea event that is detected is a true apnea event or a false detection by analyzing a portion of the ECG or EGM signal preceding the measurement period in which the potential apnea event was detected to determine whether a heart rhythm change, a presence of a non-cardiac signal, or a change in the feature is due to a change in patient posture or patient activity likely caused the potential apnea event to be detected; and the at least one processor in response to determining that the potential apnea event is a true apnea event, causing storing or uploading of information about the true apnea event so that the information can be accessed by a medical practitioner; wherein the heart rhythm change comprises at least one of: multiple cardiac rhythms comprising a pacing rhythm in conjunction with an intrinsic rhythm; one or more premature ventricular contractions; or one or more premature atrial contractions. ### Claim 15 (depends on 12) The method of claim 12, wherein the detecting the potential apnea event occurs in response to the measure of LTV of the feature being greater than the measure of STV of the feature for at least the measurement period. ### Claim 16 (depends on 12) The method of claim 12, wherein the detecting the potential apnea event occurs in response to both the measure of LTV of the feature being greater than the measure of STV for at least the measurement period, and the measure of STV of the feature being less that a specified threshold for at least the measurement period. ### Claim 17 (depends on 12) The method of claim 12, wherein the feature of the ECG or EGM signal, for which the measure of STV and the measure of LTV are determined over the measurement period, comprises a morphological feature, which comprises one of: an area under a curve of a QRS complex, R-wave, T-wave, ST-region, or evoked response; a maximum amplitude of a QRS complex, R-wave, T-wave, or evoked response; or a peak-to-peak amplitude of a QRS complex, R-wave, T-wave, or evoked response. ### Claim 18 (depends on 12) The method of claim 12, wherein the feature of the ECG or EGM signal, for which the measure of STV and the measure of LTV are determined over the measurement period, comprises a temporal feature, which comprises one of: RR interval duration; PR interval duration; QT interval duration; QRS complex duration; AR interval duration; PV interval duration; or evoked response duration. ### Claim 19 (depends on 12) The method of claim 12, wherein each of the measure of STV and the measure of LTV in the feature of the ECG or EGM signal over the measurement period is one of: a standard deviation of the feature; a standard deviation of the feature divided by an average of the feature; a difference between a maximum and a mean of the feature; a difference between a maximum and a minimum of the feature; a difference between a second maximum and a second mean of the feature; a difference between an Nth maximum and an Nth mean of the feature; or any one of said differences divided by an average of the feature. ### Claim 20 (depends on 12) The method of claim 12, wherein: the IMD is configured to selectively deliver stimulation therapy under control of the at least one processor. ### Claim 21 A non-transitory computer readable medium storing instructions to detect an apnea event that, when executed by at least one processor of an implantable medical device (IMD) that also includes an accelerometer, sensing circuitry, and electrodes, causes the at least one processor to perform operations, comprising: obtaining an electrocardiogram (ECG) or electrogram (EGM) signal indicative of cardiac electrical activity of a patient's heart using the sensing circuitry, coupled to the electrodes; obtaining posture information and activity information from the accelerometer; during a first period of time, classifying the patient as being asleep based on the posture information and the activity information obtained from the accelerometer, and in response thereto enabling monitoring for apnea, which includes determining a measure of short-term variation (STV) and a measure of long-term variation (LTV) in a feature of the ECG or EGM signal over a measurement period that includes a plurality of cardiac cycles; and detecting a potential apnea event in the measurement period based on the measure of STV and the measure of LTV in the feature of the ECG or EGM signal; wherein the feature comprises one of a morphological feature or a temporal feature; and during a second period of time, classifying the patient as being awake based on further posture information and further activity information obtained from the accelerometer, and in response thereto disabling the monitoring for apnea. ### Claim 22 (depends on 21) The non-transitory computer readable medium of claim 21, wherein IMD that is configured to selectively deliver stimulation therapy under control of the at least one processor.