Retrieval augmented text-to-SQL generation for epidemiological question answering using electronic health records

arXiv:2403.09226v1 Announce Type: new
Abstract: Electronic health records (EHR) and claims data are rich sources of real-world data that reflect patient health status and healthcare utilization. Querying these databases to answer epidemiological questions is challenging due to the intricacy of medical terminology and the need for complex SQL queries. Here, we introduce an end-to-end methodology that combines text-to-SQL generation with retrieval augmented generation (RAG) to answer epidemiological questions using EHR and claims data. We show that our approach, which integrates …

abstract arxiv cs.cl data databases ehr electronic electronic health records health healthcare medical medical terminology patient question question answering questions records retrieval sql sql generation terminology text text-to-sql type world