Machine-learning for processing lead-invariant electrocardiogram inputs

A system for performing a machine learning task on a neural network input derived from electrocardiogram (ECG) data to generate a neural network output, the neural network input including representations of any number n of ECG leads from the ECG data in which n is an integer in a set of integers from 1 to a pre-defined maximum number of ECG leads m, the system comprising:

• one or more computers and one or more storage devices storing instructions that, when executed by the one or more computers, cause the one or more computers to perform one or more operations to implement a neural network configured to perform the machine learning task, the neural network comprising:
• a feature extraction sub-neural network that is configured to process the neural network input to generate n feature extraction network outputs, each of the n feature extraction network outputs describing temporal features from a different one of the n ECG leads represented in the neural network input;
• a feature fusing sub-neural network that is configured to process the n feature extraction network outputs generated by the feature extraction sub-neural network to generate a fused feature network output;
• and
• a task sub-neural network that is configured to process the fused feature network output to generate the neural network output.