Training a neural network prediction model for survival analysis

A computer hardware system for iteratively training a prediction model for survival analysis, the computer hardware system comprising:

• a hardware processor configured to perform executable operations comprising:
• selecting a batch of data from a training dataset representing a plurality of individuals;
• generating, using a non-parametric statistical function and for the batch of data, a curve representing a survival rate of a group of individuals within the batch over a period of time, wherein the plurality of individuals includes the group of individuals;
• estimating, using the prediction model, individual survival functions for each individual of the group of individuals within the batch;
• generating an average survival function from the individual survival functions;
• generating a calibration loss using the average survival function and the curve representing the survival rate;
• and
• updating weights of a neural network including the prediction model based upon a total loss including the calibration loss for the iterative training of the prediction model.

A computer program product, comprising:

• a computer readable storage medium having stored therein program code for iteratively training a prediction model,
• the program code, which when executed by a computer hardware system, cause the computer hardware system to perform:
• selecting a batch of data from a training dataset representing a plurality of individuals;
• generating, using a non-parametric statistical function and for the batch of data, a curve representing a survival rate of a group of individuals within the batch over a period of time, wherein the plurality of individuals includes the group of individuals;
• estimating, using the prediction model, individual survival functions for each individual of the group of individuals within the batch;
• generating an average survival function from the individual survival functions;
• generating a calibration loss using the average survival function and the curve representing the survival rate;
• and
• updating weights of a neural network including the prediction model based upon a total loss including the calibration loss for the iterative training of the prediction model.