Cohort Retrieval using Dense Passage Retrieval

TL;DR

This paper introduces a novel application of Dense Passage Retrieval (DPR) for patient cohort retrieval in echocardiography, transforming unstructured EHR data into a query-passage format and demonstrating superior retrieval performance.

Contribution

It is the first to apply DPR to echocardiography cohort retrieval, developing a systematic dataset transformation, evaluation metrics, and a custom-trained DPR model for improved accuracy.

Findings

DPR outperforms traditional retrieval methods.

Custom-trained DPR model shows significant performance gains.

Framework adaptable to other medical domains.

Abstract

Patient cohort retrieval is a pivotal task in medical research and clinical practice, enabling the identification of specific patient groups from extensive electronic health records (EHRs). In this work, we address the challenge of cohort retrieval in the echocardiography domain by applying Dense Passage Retrieval (DPR), a prominent methodology in semantic search. We propose a systematic approach to transform an echocardiographic EHR dataset of unstructured nature into a Query-Passage dataset, framing the problem as a Cohort Retrieval task. Additionally, we design and implement evaluation metrics inspired by real-world clinical scenarios to rigorously test the models across diverse retrieval tasks. Furthermore, we present a custom-trained DPR embedding model that demonstrates superior performance compared to traditional and off-the-shelf SOTA methods.To our knowledge, this is the first work to apply DPR for patient cohort retrieval in the echocardiography domain, establishing a framework that can be adapted to other medical domains.