Methods and systems for detecting ecg anomalies

A system for training a neural network engine configured to detect a heart anomaly using electrocardiogram signals, comprising a processor that is configured to:

• receive a set of training electrocardiogram signals, wherein at least one electrocardiogram signal in the set of training electrocardiogram signals is associated with metadata identifying a region of interest that includes the heart anomaly;
• input the set of training electrocardiogram signals into the neural network engine, wherein the neural network engine is trained using an objective function having a first regularization parameter and a second regularization parameter, wherein the first regularization parameter indicates a first degree of sensitivity associated with samples located within the region of interest, and wherein the second regularization parameter indicates a second degree of sensitivity associated with samples located outside of the region of interest;
• operate the neural network engine to identify the heart anomaly by classifying the set of training electrocardiogram signals;
• and
• adjust the neural network engine based on the identified heart anomaly and the metadata.

A method for facilitating detection of one or more heart anomalies in electrocardiogram, comprising:

• receiving information representing a set of electrocardiogram signals;
• inputting the information representing the set of electrocardiogram signals into a neural network engine, wherein the neural network engine is trained using an objective function having a regularization parameter that indicates a degree of sensitivity associated with signal samples located outside of a region of interest, wherein the region of interest is determined based on gradient variation of the set of electrocardiogram signals;
• identifying one or more regions that include the one or more heart anomalies by classifying the set of electrocardiogram signals using the neural network engine;
• and
• generating metadata information to produce an annotated diagram corresponding to the set of electrocardiogram signals, wherein the metadata information indicates the one or more regions that include the one or more heart anomalies annotated based on the metadata information.

A system for facilitating detection of one or more heart anomalies in electrocardiogram, comprising a processor that is configured to:

• receive information representing a set of electrocardiogram signals;
• input the information representing the set of electrocardiogram signals into a neural network engine, wherein the neural network engine is trained using an objective function having a regularization parameter that indicates a degree of sensitivity associated with samples located outside of a region of interest, wherein the region of interest is determined based on gradient variation of the set of electrocardiogram signals;
• identify one or more regions that include the one or more heart anomalies by classifying the set of electrocardiogram signals using the neural network engine;
• and
• generate metadata information to produce an annotated diagram corresponding to the set of electrocardiogram signals, wherein the metadata information indicates the one or more regions that include the one or more heart anomalies annotated based on the metadata information.