In one embodiment, a method to determine reliable electrocardiogram (ECG) signal is described. The method includes receiving at least one ECG signal for a period of time from a patient. The method also includes analyzing the at least one ECG signal to determine a first heart rate using a first method and analyzing the at least one ECG signal to determine a second heart rate using a second method different from the first method. The method includes comparing the first and second heart rates to each other and classifying the at least one ECG signal as reliable when a reliability threshold is satisfied.

A medical data providing device includes a memory, a communication unit, and a processor. The processor is configured to read a biosignal stored in the memory, divide the biosignal at certain time intervals, convert a signal segment into the frequency, and determines whether the signal segment is an analysis necessary section or an analysis unnecessary section based on a frequency component of the signal segment. The processor is further configured to analyze the signal segment of the analysis necessary section to generate data including an analysis result, and transmits data including the analysis result to a certain device.

A method and a system for analyzing electrocardiographic segments previously derived from a cardiac device so as to help to discriminate true positives episodes, including abnormal heart rhythms, from false positives episodes, including normal heart rhythms. Each episode received includes at least one segment of electrocardiographic signal, and each segment is segmented into sub-segments. Score vectors are obtained for each sub-segment to classify the episode so as to discriminate true positive episodes from false positive episodes, and the classification results, which include at least the true positive episodes, are output.

A data processing method including the computer-implemented steps of: acquiring one or more pieces of fibrillation wave electrocardiogram data including fibrillation waves included in whole electrocardiogram data obtained by measuring change over time of an action potential due to electric activity of a heart muscle; inputting the one or more pieces of fibrillation wave electrocardiogram data into a first machine learning model that classifies a plurality of pieces of electrocardiogram data including the fibrillation waves into electrocardiogram data in which the fibrillation waves are clear and electrocardiogram data in which the fibrillation waves are unclear, and acquiring clear electrocardiogram data output from the first machine learning model as the electrocardiogram data in which the fibrillation waves are clear; and outputting the clear electrocardiogram data.

A data processing method including the computer-implemented steps of: acquiring one or more pieces of fibrillation wave electrocardiogram data including fibrillation waves included in whole electrocardiogram data obtained by measuring change over time of an action potential due to electric activity of a heart muscle; inputting the one or more pieces of fibrillation wave electrocardiogram data into a first machine learning model that classifies a plurality of pieces of electrocardiogram data including the fibrillation waves into electrocardiogram data in which the fibrillation waves are clear and electrocardiogram data in which the fibrillation waves are unclear, and acquiring clear electrocardiogram data output from the first machine learning model as the electrocardiogram data in which the fibrillation waves are clear; and outputting the clear electrocardiogram data.

Described here are systems and methods for generating cardiac vibrational energy spectral (“VIBES”) heat maps from physical vibration data and cardiac cycle timing data measured from a subject. Quick screening for heart valve, cardiovascular, and/or cardiothoracic abnormalities can be provided based on an analysis and/or classification of the generated VIBES heat maps.

Described here are systems and methods for generating cardiac vibrational energy spectral (“VIBES”) heat maps from physical vibration data and cardiac cycle timing data measured from a subject. Quick screening for heart valve, cardiovascular, and/or cardiothoracic abnormalities can be provided based on an analysis and/or classification of the generated VIBES heat maps.

A definer defines heartbeat segments in an electrocardiac waveform. A primary determiner determines, from among the heartbeat segments, segments that satisfy a primary determination criterion as provisional stable segments. A secondary determiner determines a provisional stable segment as a stable segment when the provisional stable segment satisfies a secondary determination criterion. An end-diastole detector and an end-systole detector detect an end-diastole and an end-systole in a segment of interest. At the time of changing the segment of interest, a selection control unit controls selection of segment of interest such that the segment of interest after change corresponds to a stable segment.

A definer defines heartbeat segments in an electrocardiac waveform. A primary determiner determines, from among the heartbeat segments, segments that satisfy a primary determination criterion as provisional stable segments. A secondary determiner determines a provisional stable segment as a stable segment when the provisional stable segment satisfies a secondary determination criterion. An end-diastole detector and an end-systole detector detect an end-diastole and an end-systole in a segment of interest. At the time of changing the segment of interest, a selection control unit controls selection of segment of interest such that the segment of interest after change corresponds to a stable segment.

An apparatus for producing information indicative of cardiac condition includes a processing system for receiving a rotation signal indicative of rotational movement of a chest. The processing system is configured to form one or more indicator quantities each being derivable from an energy spectral density based on one or more samples of the rotation signal, where each sample has a temporal length. The processing system is configured to determine an indicator of cardiac condition on the basis of the one or more indicator quantities. The determination of the cardiac condition is based on that for example myocardial infarction causes changes in the energy spectral density. Thus, it is possible to distinguish between for example myocardial infarction and plain heartburn.