Literature-Augmented Clinical Outcome Prediction

TL;DR

BEEP enhances clinical outcome prediction by retrieving and integrating relevant medical literature based on patient notes, significantly improving predictive accuracy over existing language model baselines.

Contribution

This work introduces a novel method to incorporate patient-specific literature retrieval into outcome prediction models, improving accuracy in clinical tasks.

Findings

F1 score increased by up to 5 points.

Precision@Top-K improved by over 25%.

Effective retrieval from noisy clinical notes.

Abstract

We present BEEP (Biomedical Evidence-Enhanced Predictions), a novel approach for clinical outcome prediction that retrieves patient-specific medical literature and incorporates it into predictive models. Based on each individual patient's clinical notes, we train language models (LMs) to find relevant papers and fuse them with information from notes to predict outcomes such as in-hospital mortality. We develop methods to retrieve literature based on noisy, information-dense patient notes, and to augment existing outcome prediction models with retrieved papers in a manner that maximizes predictive accuracy. Our approach boosts predictive performance on three important clinical tasks in comparison to strong recent LM baselines, increasing F1 by up to 5 points and precision@Top-K by a large margin of over 25%.