Disclosed is a method of calculating an expected analysis time regarding an electrocardiogram signal. The method includes receiving an electrocardiogram signal and classification data regarding the electrocardiogram signal, calculating a first analysis time for each section of the electrocardiogram signal by using the classification data, and calculating an expected analysis time regarding the electrocardiogram signal based on first analysis times calculated for respective sections of the electrocardiogram signal.

Disclosed is a method of calculating an expected analysis time regarding an electrocardiogram signal. The method includes receiving an electrocardiogram signal and classification data regarding the electrocardiogram signal, calculating a first analysis time for each section of the electrocardiogram signal by using the classification data, and calculating an expected analysis time regarding the electrocardiogram signal based on first analysis times calculated for respective sections of the electrocardiogram signal.

A method of processing analysis tasks for signal sections corresponding to an analysis condition includes (i) generating output data that includes a plurality of pieces of label information regarding sections of electrocardiogram signal in conjunction with one another; (ii) based on the output data, displaying pre-stored past medical history information regarding the first target object on a separate region, by using the electrocardiogram signal and classification data regarding the electrocardiogram signal; (iii) transmitting the output data to a medical staff terminal; (iv) determining one or more sections of the electrocardiogram signal corresponding to all or a part of the analysis condition as a first section of interest to be analyzed; (v) calculating an expected analysis time for analyzing the first section of interest; (vi) transmitting information regarding the expected analysis time to the medical staff terminal; and (viii) generating an analysis request signal regarding the electrocardiogram signal.

A method of processing analysis tasks for signal sections corresponding to an analysis condition includes (i) generating output data that includes a plurality of pieces of label information regarding sections of electrocardiogram signal in conjunction with one another; (ii) based on the output data, displaying pre-stored past medical history information regarding the first target object on a separate region, by using the electrocardiogram signal and classification data regarding the electrocardiogram signal; (iii) transmitting the output data to a medical staff terminal; (iv) determining one or more sections of the electrocardiogram signal corresponding to all or a part of the analysis condition as a first section of interest to be analyzed; (v) calculating an expected analysis time for analyzing the first section of interest; (vi) transmitting information regarding the expected analysis time to the medical staff terminal; and (viii) generating an analysis request signal regarding the electrocardiogram signal.

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.

Embodiments of the present disclosure provide systems and methods for diagnosing LVH based on a user's ECG data as well as blood pressure data. The user may record their ECG and blood pressure data using any appropriate ECG and blood pressure monitors, and may augment the ECG and blood pressure data with user characteristics such as user age, sex, diet, and previous medical history before transmitting the ECG and blood pressure data to a cloud storage system. A machine learning (ML) model implemented in the cloud storage system may analyze ECG data of the user using LVH diagnosis criteria, and augment the results of the ECG data analysis with the blood pressure data of the user to form a diagnosis. The diagnosis may indicate whether the user is suffering from LVH, as well as a severity of the LVH.

Embodiments of the present disclosure provide systems and methods for diagnosing LVH based on a user's ECG data as well as blood pressure data. The user may record their ECG and blood pressure data using any appropriate ECG and blood pressure monitors, and may augment the ECG and blood pressure data with user characteristics such as user age, sex, diet, and previous medical history before transmitting the ECG and blood pressure data to a cloud storage system. A machine learning (ML) model implemented in the cloud storage system may analyze ECG data of the user using LVH diagnosis criteria, and augment the results of the ECG data analysis with the blood pressure data of the user to form a diagnosis. The diagnosis may indicate whether the user is suffering from LVH, as well as a severity of the LVH.

A physiological information acquisition device configured to acquire physiological information of a subject includes: an input interface configured to receive waveform data corresponding to a measurement waveform of the physiological information from a sensor; a prediction unit configured to extract a feature from the waveform data using a convolutional neural network and predict a probability of the waveform data being classified into each of a plurality of classes; an importance specification unit configured to specify an importance of the feature with respect to a prediction result of the probability for at least one of the plurality of classes; and an output unit configured to output an indicator indicating the importance together with the measurement waveform.

A method includes assigning a first instance of a cardiac event that occurred in a patient during a period of time to a first bucket of a first plurality of buckets based on a first measured heart rate of the patient during the first instance. A first heart rate threshold of the first bucket is less than the first measured heart rate. The method also includes determining whether the first heart rate threshold exceeds heart rate thresholds of all buckets of the plurality of buckets to which an instance of the cardiac event that occurred in the patient during the period of time is assigned, determining whether a number of instances of the cardiac event that occurred in the patient during the period of time exceeds an event threshold, and preventing the first instance of the cardiac event from being communicated for clinical review.

A method includes assigning a first instance of a cardiac event that occurred in a patient during a period of time to a first bucket of a first plurality of buckets based on a first measured heart rate of the patient during the first instance. A first heart rate threshold of the first bucket is less than the first measured heart rate. The method also includes determining whether the first heart rate threshold exceeds heart rate thresholds of all buckets of the plurality of buckets to which an instance of the cardiac event that occurred in the patient during the period of time is assigned, determining whether a number of instances of the cardiac event that occurred in the patient during the period of time exceeds an event threshold, and preventing the first instance of the cardiac event from being communicated for clinical review.