Patient Cohort Retrieval using Transformer Language Models
This work addresses the problem of efficiently identifying patient cohorts for healthcare professionals, but it is incremental as it applies existing methods to a new domain.
The authors tackled patient cohort retrieval from electronic health records by applying transformer language models to this document retrieval task, finding that most of their models outperformed the BM25 baseline on various metrics.
We apply deep learning-based language models to the task of patient cohort retrieval (CR) with the aim to assess their efficacy. The task of CR requires the extraction of relevant documents from the electronic health records (EHRs) on the basis of a given query. Given the recent advancements in the field of document retrieval, we map the task of CR to a document retrieval task and apply various deep neural models implemented for the general domain tasks. In this paper, we propose a framework for retrieving patient cohorts using neural language models without the need of explicit feature engineering and domain expertise. We find that a majority of our models outperform the BM25 baseline method on various evaluation metrics.