Sequential Inductive Transfer for Coronary Artery Disease Diagnosis

Abstract

A machine lifelong learning system based on task rehearsal and multiple task learning (MTL) is used to sequentially learn a series of medical diagnostic tasks. The representations of successfully learned neural network models of the tasks are stored within a domain knowledge database. Virtual examples generated from these models are relearned, or rehearsed, in parallel with each new task using the J7MTL neural network algorithm, a variant of MTL. The ??MTL algorithm employs a separate learning rate, for each task output, k. r\k varies as a function of the measure of relatedness between each prior task k and the new task being learned. Working together, the task rehearsal method and J7MTL are able to develop more accurate hypotheses for a new task by selectively transferring knowledge from related tasks in domain knowledge. Coronary artery disease data sets from three real and four fictitious hospitals provide a domain of related and unrelated tasks for testing the system. The experimental results demonstrate the method's ability to sequentially retain and transfer clinical diagnostic knowledge when learning from impoverished training sets.