Mining Implicit Treatment Concepts for Neural Precision Medicine.

Abstract

Precision medicine (PM) is regarded as an information retrieval (IR) task in which biomedical articles containing treatment information about specific diseases or genetic variants are retrieved in response to patient record for the purpose of providing medical evidence to the point-of-care. In existing PM approaches, manual keywords, such as "treatment" and "therapy," are considered direct indicators of treatment information and are thereby introduced to expand the original query. However, the common medical concepts that are implicitly related to treatment (such as "oncogene" and "tumor"), and differ the relevant documents from the non-relevant ones, are yet to be utilized. To bridge the gap, in this paper, we propose an extension of the state-of-the-art neural IR (NIR) models, including K-NRM and DRMM, to encapsulate the PM solutions within a neural network framework, referred to as NIR PM . Specifically, the proposed approach mines a global list of common medical concepts from documents that are judged pertinent to different queries. Thereafter, the mined implicit concepts are incorporated within an NIR framework to enhance the effectiveness of PM. The experimental results on the standard Text REtrieval Conference (TREC) PM track benchmark confirm the superior performance of the proposed NIRPM model.