Abstract: A system for monitoring cardiac arrhythmias including an ECG monitor configured to obtain ECG data, the ECG data being obtained by measuring cardiac potentials during cardiac cycles; a blood flow monitor configured to obtain secondary data, the secondary data being obtained by measuring a physiological parameter indicative of blood flow; a memory storing instructions; and one or more processors configured to execute the instructions to: detect a presence of an arrhythmia based on the ECG data; classify a pulse segment of secondary data obtained during the arrhythmia based on pulse morphology; assign a segment value to the pulse segment based on the classification; calculate a shortage value based on a previous shortage value and the segment value; and generate an arrhythmia severity indicator based on the shortage value.

Abstract: Methods and systems are provided for predicting cardiac arrhythmias based on multi-modal patient monitoring data via deep learning. In an example, a method may include predicting an imminent onset of a cardiac arrhythmia in a patient, before the cardiac arrhythmia occurs, by analyzing patient monitoring data via a multi-arm deep learning model, outputting an arrhythmia event in response to the prediction, and outputting a report indicating features of the patient monitoring data contributing to the prediction. In this way, the multi-arm deep learning model may predict cardiac arrhythmias before their onset.