Lifelong machine learning (lml) model for patient subpopulation identification using real-world healthcare data

Abstract

A deep learning model implements continuous, lifelong machine learning (LML) based on a Bayesian neural network using an inventive framework including wide, deep, and prior components that employ diverse algorithms to leverage available real-world healthcare data differently to improve prediction performance. The outputs from each component of the framework are fed into a wide and shallow neural network and the posterior structure of the final model output may be utilized as a prior structure when the deep learning model is refreshed with new data in a deep learning process. Lifelong learning is implemented by dynamically integrating present learning from the wide and deep learning components with past learning from traditional tree models in the prior component into future predictions. Thus, the present Bayesian deep neural network-based LML model increases accuracy in identifying patient profiles by continuously learning, as new data become available, without forgetting prior knowledge.