General-Purpose Retrieval-Enhanced Medical Prediction Model Using Near-Infinite History
This work addresses the problem of manual event selection in EHR-based predictions for clinicians and researchers, offering a method to expedite model development, though it is incremental in automating an existing process.
The paper tackled the bottleneck of manually selecting medical events from electronic health records for machine learning predictions by proposing REMed, a model that can evaluate unlimited events and automatically select relevant ones, outperforming baselines across 27 clinical prediction tasks in four cohorts.
Machine learning (ML) has recently shown promising results in medical predictions using electronic health records (EHRs). However, since ML models typically have a limited capability in terms of input sizes, selecting specific medical events from EHRs for use as input is necessary. This selection process, often relying on expert opinion, can cause bottlenecks in development. We propose Retrieval-Enhanced Medical prediction model (REMed) to address such challenges. REMed can essentially evaluate unlimited medical events, select the relevant ones, and make predictions. This allows for an unrestricted input size, eliminating the need for manual event selection. We verified these properties through experiments involving 27 clinical prediction tasks across four independent cohorts, where REMed outperformed the baselines. Notably, we found that the preferences of REMed align closely with those of medical experts. We expect our approach to significantly expedite the development of EHR prediction models by minimizing clinicians' need for manual involvement.