Doctor2Vec: Dynamic Doctor Representation Learning for Clinical Trial Recruitment

TL;DR

This paper introduces doctor2vec, a dynamic learning model for representing doctors based on EHR data, to improve clinical trial recruitment by identifying suitable doctors, demonstrating significant performance gains and transferability in real-world scenarios.

Contribution

The paper proposes a novel dynamic memory network model, doctor2vec, for learning doctor representations from EHR data and applying them to clinical trial recruitment tasks.

Findings

Up to 8.7% improvement in PR-AUC over baselines.

Effective transferability to data-scarce settings, including new countries and rare diseases.

Validated on large-scale real-world data with 2,609 trials, 25K doctors, and 430K patients.

Abstract

Massive electronic health records (EHRs) enable the success of learning accurate patient representations to support various predictive health applications. In contrast, doctor representation was not well studied despite that doctors play pivotal roles in healthcare. How to construct the right doctor representations? How to use doctor representation to solve important health analytic problems? In this work, we study the problem on {\it clinical trial recruitment}, which is about identifying the right doctors to help conduct the trials based on the trial description and patient EHR data of those doctors. We propose doctor2vec which simultaneously learns 1) doctor representations from EHR data and 2) trial representations from the description and categorical information about the trials. In particular, doctor2vec utilizes a dynamic memory network where the doctor's experience with patients are stored in the memory bank and the network will dynamically assign weights based on the trial representation via an attention mechanism. Validated on large real-world trials and EHR data including 2,609 trials, 25K doctors and 430K patients, doctor2vec demonstrated improved performance over the best baseline by up to $8.7\%$ in PR-AUC. We also demonstrated that the doctor2vec embedding can be transferred to benefit data insufficiency settings including trial recruitment in less populated/newly explored country with $13.7\%$ improvement or for rare diseases with $8.1\%$ improvement in PR-AUC.