Systems and methods for diagnosing a health condition based on patient time series data

A system for predicting a patient is at risk of developing a health condition based on patient time series data, wherein the system comprises:

• a non-transitory memory;
• and
• one or more hardware processors configured to read instructions from the non-transitory memory that, when executed, cause the one or more hardware processors to perform operations comprising:
• receive patient time series data, wherein the patient time series data comprises patient electrocardiogram data measured from the patient prior to a patient diagnosis date for a health condition;
• execute one or more trained neural network models as a function of the patient time series data, wherein:
• the one or more trained neural network models have been trained using a training set of health records comprising electrocardiogram data, measured only within diagnosis windows and not pre-emptively to diagnoses, correlated to positive diagnoses of the health condition;
• the one or more trained neural network models comprise:
• one or more convolutional branches, wherein at least one convolutional branch is configured to process the patient time series data into a 1-dimensional waveform representation;
• and
• a concatenating layer configured to concatenate one or more outputs of the one or more convolutional branches to generate an output for the one or more trained neural network models;
• and
• predict the patient is at risk of developing the health condition within the next 5 years as a function of the patient time series data.