A method for analyzing arrhythmia in real time and an electrocardiogram monitoring device is disclosed. The method for analyzing arrhythmia in real time includes: acquiring a QRS template set currently used for arrhythmia analysis; determining whether each QRS template in the QRS template set is reliable; displaying information of a QRS template when the QRS template set contains an unreliable QRS template; determining the QRS template set according to an operation performed by a user on the information of the QRS template; and acquiring real-time electrocardiogram data, performing arrhythmia analysis on the real-time electrocardiogram data by using a determined QRS template set, and outputting an arrhythmia analysis result of the real-time electrocardiogram data in real time. The method for analyzing arrhythmia in real time may achieve the correction of a template of a special waveform by means of editing a currently created QRS template. When the same type of waveform is analyzed again, a correct arrhythmia analysis result may be provided, which may improve the accuracy of arrhythmia analysis and improve the quality of electrocardiogram monitoring.

Techniques are disclosed for monitoring a patient for the occurrence of cardiac arrhythmias. A computing system obtains a cardiac electrogram (EGM) strip for a current patient. Additionally, the computing system may apply a first cardiac rhythm classifier (CRC) with a segment of the cardiac EGM strip as input. The first CRC is trained on training cardiac EGM strips from a first population. The first CRC generates first data regarding an aspect of a cardiac rhythm of the current patient. The computing system may also apply a second CRC with the segment of the cardiac EGM strip as input. The second CRC is trained on training cardiac EGM strips from a smaller, second population. The second CRC generates second data regarding the aspect of the cardiac rhythm of the current patient. The computing system may generate output data based on the first and/or second data.

Techniques are disclosed for monitoring a patient for the occurrence of cardiac arrhythmias. A computing system obtains a cardiac electrogram (EGM) strip for a current patient. Additionally, the computing system may apply a first cardiac rhythm classifier (CRC) with a segment of the cardiac EGM strip as input. The first CRC is trained on training cardiac EGM strips from a first population. The first CRC generates first data regarding an aspect of a cardiac rhythm of the current patient. The computing system may also apply a second CRC with the segment of the cardiac EGM strip as input. The second CRC is trained on training cardiac EGM strips from a smaller, second population. The second CRC generates second data regarding the aspect of the cardiac rhythm of the current patient. The computing system may generate output data based on the first and/or second data.

A bio-signal measuring apparatus for detecting signal peaks includes a bio-signal sensing circuit configured to sense an electrocardiogram signal by using an electrode attached to the body. The bio-signal measuring apparatus further includes a first filtering unit, a second filtering unit, a candidate peak detector, a peak integrator, and a valid peak detector. The peak integrator is configured to define windows by time intervals and calculate, as average peak time values, average values of time values of the first candidate peaks and the second candidate peaks included in the windows. The valid peak detector is configured to calculate complexity values for time intervals including the average peak time values, determine a peak occurrence time value on the basis of the complexity value, and detect valid peaks in the electrocardiogram signal by using the peak occurrence time value.

A bio-signal measuring apparatus for detecting signal peaks includes a bio-signal sensing circuit configured to sense an electrocardiogram signal by using an electrode attached to the body. The bio-signal measuring apparatus further includes a first filtering unit, a second filtering unit, a candidate peak detector, a peak integrator, and a valid peak detector. The peak integrator is configured to define windows by time intervals and calculate, as average peak time values, average values of time values of the first candidate peaks and the second candidate peaks included in the windows. The valid peak detector is configured to calculate complexity values for time intervals including the average peak time values, determine a peak occurrence time value on the basis of the complexity value, and detect valid peaks in the electrocardiogram signal by using the peak occurrence time value.

Long-term electrocardiographic and physiological monitoring over a period lasting up to several years in duration can be provided through a continuously-recording insertable cardiac monitor. The sensing circuitry and the physical layout of the electrodes are specifically optimized to capture electrical signals from the propagation of low amplitude, relatively low frequency content cardiac action potentials, particularly the P-waves that are generated during atrial activation and storing samples of captured signals. In general, the ICM is intended to be implanted centrally and positioned axially and either over the sternum or slightly to either the left or right of the sternal midline in the parasternal region of the chest.

Long-term electrocardiographic and physiological monitoring over a period lasting up to several years in duration can be provided through a continuously-recording insertable cardiac monitor. The sensing circuitry and the physical layout of the electrodes are specifically optimized to capture electrical signals from the propagation of low amplitude, relatively low frequency content cardiac action potentials, particularly the P-waves that are generated during atrial activation and storing samples of captured signals. In general, the ICM is intended to be implanted centrally and positioned axially and either over the sternum or slightly to either the left or right of the sternal midline in the parasternal region of the chest.

A medical device, such as an extra-cardiovascular implantable cardioverter defibrillator (ICD), senses R-waves from a first cardiac electrical signal by a first sensing channel and stores a time segment of a second cardiac electrical signal acquired by a second sensing channel in response to each sensed R-wave. The ICD determines morphology match scores from the stored time segments of the second cardiac electrical signal and, based on the morphology match scores, withholds detection of a tachyarrhythmia episode. In some examples, the ICD detects T-wave oversensing based on the morphology match scores and withholds detection of a tachyarrhythmia episode in response to detecting the T-wave oversensing.

A medical device, such as an extra-cardiovascular implantable cardioverter defibrillator (ICD), senses R-waves from a first cardiac electrical signal by a first sensing channel and stores a time segment of a second cardiac electrical signal acquired by a second sensing channel in response to each sensed R-wave. The ICD determines morphology match scores from the stored time segments of the second cardiac electrical signal and, based on the morphology match scores, withholds detection of a tachyarrhythmia episode. In some examples, the ICD detects T-wave oversensing based on the morphology match scores and withholds detection of a tachyarrhythmia episode in response to detecting the T-wave oversensing.

The present invention provides a learning device including a learning unit that performs learning related to the output of vital data indicating life signs of a subject, with the use of first sensor data acquired from the subject by the first system as learning data and of teacher data based on second sensor data acquired from the subject by the second system in the same period as an acquisition period of the first sensor data, the second system being less affected by noises than the first system.