Systems and methods for classifying ECG data

Inventors

Korzinov, Lev • Baumann, Eric • McNamara, Anna

Assignees

INFOBIONIC Inc

Abstract

A computer-implemented method for processing ECG data may include: receiving, over an electronic network, ECG data, wherein the ECG data represents a plurality of heartbeats; analyzing the ECG data, by at least one processor, to determine whether each of the plurality of heartbeats is a normal heartbeat or an abnormal heartbeat; associating, by the at least one processor, each of the abnormal heartbeats with either only one of a plurality of existing templates or a new template; receiving, from a user, input related to each new template, wherein the input includes either: a) a confirmation that the new template represents an abnormal heartbeat, or b) a reclassification of the new template as representing a normal heartbeat or a different abnormal heartbeat; and in response to the user input, updating, by the at least one processor, a label of each of the heartbeats associated with each confirmed new template and each of the heartbeats associated with each reclassified new template. The ECG data may be received from a portable monitor configured to be carried on a patient's body.

Core Innovation

The invention relates to classifying heartbeats in ECG data as normal heartbeats, abnormal heartbeats associated with one or more preexisting templates, or abnormal heartbeats associated with one or more new templates. The classification is performed using at least one processor, and it produces heartbeat labels that associate abnormal heartbeats with templates.

After the classifying step, user input is received for each new template of the one or more new templates. The user input includes either confirmation that the new template represents an abnormal heartbeat, reclassification of the new template as a normal heartbeat, or reclassification of the new template as representing an abnormal heartbeat different than the abnormal heartbeat from the classifying step.

After receiving the user input, the processor determines a total number of abnormal heartbeats as a sum of the heartbeats associated with the one or more preexisting templates and the one or more new templates representing an abnormal heartbeat. By using user input to validate and update the new templates, the total number of abnormal heartbeats reflects the updated association of abnormal heartbeats to templates.

The problem addressed is the need to classify ECG data into normal and abnormal heartbeats and to determine a total number of abnormal heartbeats while incorporating user input for templates generated during classification. The approach supports abnormal heartbeat counting, including PVC and arrhythmias, by updating heartbeat labels based on user-confirmed template associations.

Claims Coverage

The independent claims are directed to a computer-implemented method, a system, and a non-transitory computer-readable medium. Across the independent claims, the inventive coverage centers on classification of ECG heartbeats using preexisting templates versus new templates, collecting user input for each new template, and determining a total number of abnormal heartbeats as a sum over preexisting-template and user-updated new-template associations.

Across clm-00001, clm-00010, and clm-00016, the independent claims consistently require template-associated classification of ECG heartbeats into normal and abnormal categories using preexisting templates and new templates, receiving user input to confirm or correct each new template’s abnormal or normal status and abnormal type, and determining a total number of abnormal heartbeats as a sum of template-associated abnormal heartbeats from both sources.

Stated Advantages

Documented Applications