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.

An electronic device and a method for selecting a feature of an electrocardiogram (ECG) are provided. The method includes: obtaining the ECG; performing a first pre-processing on the ECG to generate a first ECG; marking multiple extreme points corresponding to at least one type of wave on the first ECG; calculating a first feature value corresponding to a first feature according to the multiple extreme points of the at least one type of wave, generating a first performance index corresponding to a machine learning model according to the first feature value, and determining whether to select the first feature according to the first performance index; and outputting the first feature in response to selecting the first feature.

An electronic device and a method for selecting a feature of an electrocardiogram (ECG) are provided. The method includes: obtaining the ECG; performing a first pre-processing on the ECG to generate a first ECG; marking multiple extreme points corresponding to at least one type of wave on the first ECG; calculating a first feature value corresponding to a first feature according to the multiple extreme points of the at least one type of wave, generating a first performance index corresponding to a machine learning model according to the first feature value, and determining whether to select the first feature according to the first performance index; and outputting the first feature in response to selecting the first feature.

An electronic device and a method for predicting a blockage of a coronary artery are provided. The method includes: obtaining multiple pieces of electrocardiogram (ECG) data respectively corresponding to a coronary artery set; generating multiple first probabilities corresponding to the multiple pieces of electrocardiogram data respectively according to the multiple pieces of electrocardiogram data and a first phase model, generating a first determined result according to the multiple first probabilities, and selecting a first data subset corresponding to a first probability subset from the multiple pieces of electrocardiogram data in response to each one in the first data subset of the multiple first probabilities being greater than a first threshold; generating multiple second probabilities corresponding to the first data subset according to the first data subset and a second phase model, and generating a second determined result according to the multiple second probabilities.

An electronic device and a method for predicting a blockage of a coronary artery are provided. The method includes: obtaining multiple pieces of electrocardiogram (ECG) data respectively corresponding to a coronary artery set; generating multiple first probabilities corresponding to the multiple pieces of electrocardiogram data respectively according to the multiple pieces of electrocardiogram data and a first phase model, generating a first determined result according to the multiple first probabilities, and selecting a first data subset corresponding to a first probability subset from the multiple pieces of electrocardiogram data in response to each one in the first data subset of the multiple first probabilities being greater than a first threshold; generating multiple second probabilities corresponding to the first data subset according to the first data subset and a second phase model, and generating a second determined result according to the multiple second probabilities.

Systems and methods for identifying one or more P-waves in real-time are disclosed. Exemplary implementations may: receive a plurality of signals from an ECG lead configured to be connected with a patient; determine a noise level of the plurality of signals during a pre-determined time interval; identify a plurality of QRS-complex candidates from the received plurality of signals; extract one or more features from each QRS-complex candidate based on the determined noise level of the plurality of signals; cluster, based on the extracted one or more features from each QRS-complex candidate, the plurality of QRS-complex candidates; and identify one or more P-waves from the clustered plurality of QRS-complex candidates. Based on the identified one or more P-waves, a heart block event can be detected.

Systems and methods for identifying one or more P-waves in real-time are disclosed. Exemplary implementations may: receive a plurality of signals from an ECG lead configured to be connected with a patient; determine a noise level of the plurality of signals during a pre-determined time interval; identify a plurality of QRS-complex candidates from the received plurality of signals; extract one or more features from each QRS-complex candidate based on the determined noise level of the plurality of signals; cluster, based on the extracted one or more features from each QRS-complex candidate, the plurality of QRS-complex candidates; and identify one or more P-waves from the clustered plurality of QRS-complex candidates. Based on the identified one or more P-waves, a heart block event can be detected.

A system is described for predicting at least one cardiological dysfunction in an individual, having a means for providing an ECG which has a number n of time-synchronized ECG traces, each comprising a chronological sequence of time signals representing a sinus rhythm of the individual's heartbeat, to which at least one P wave, a QRS complex and a T wave can be assigned in chronological order. A selection means selects at least two ECG traces from the n ECG traces, an analysis unit analyses the selected ECG traces as follows: a) determining an isoelectric signal level, b) determining a first point in time chronologically before the QRS complex, c) determining a second point in time chronologically after the first point in time and chronologically before the QRS complex, d) carrying out the determining steps a) to c) for all selected ECG traces, e) determining an earliest first point in time from all the first points in time determined for the respective selected ECG traces and a latest second point in time from all the second points in time determined for the respective selected ECG traces, f) determining a time interval delimited by the earliest first point in time and latest second point in time.

A system is described for predicting at least one cardiological dysfunction in an individual, having a means for providing an ECG which has a number n of time-synchronized ECG traces, each comprising a chronological sequence of time signals representing a sinus rhythm of the individual's heartbeat, to which at least one P wave, a QRS complex and a T wave can be assigned in chronological order. A selection means selects at least two ECG traces from the n ECG traces, an analysis unit analyses the selected ECG traces as follows: a) determining an isoelectric signal level, b) determining a first point in time chronologically before the QRS complex, c) determining a second point in time chronologically after the first point in time and chronologically before the QRS complex, d) carrying out the determining steps a) to c) for all selected ECG traces, e) determining an earliest first point in time from all the first points in time determined for the respective selected ECG traces and a latest second point in time from all the second points in time determined for the respective selected ECG traces, f) determining a time interval delimited by the earliest first point in time and latest second point in time.

An electrocardiogram information processing method and workstation system. The method includes receiving electrocardiogram data output by multiple devices; performs data analysis on the electrocardiogram data, and generating report data and stores same; receiving a report data query by a user, queries corresponding report data according to a user ID of the user, and generating report result list for display and output; receiving a selection by the user, and obtaining selected report data according to the selection; receiving a report data consultation request input by the user; obtaining a user ID of an associated user corresponding to the user ID according to the report data consultation request, and sending the report data to a user equivalent of the associated user according to the user ID of the associated user; and receiving a consultation result feedback data sent by the user equivalent of the associated user.