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

arXiv: https://arxiv.org/abs/2403.09226 · HTML: https://mlsanity.com/paper/2403.09226/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 14 Mar 2024.

## Placed in

- Retrieval-augmented generation / [Medical and biomedical RAG](https://mlsanity.com/rag/medical-and-biomedical-rag/)

## Builds on (most cited first, 13 of 13)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [Self-Alignment Pretraining for Biomedical Entity Representations](https://mlsanity.com/paper/2010.11784/) (2020)
- [Text-to-SQL Generation for Question Answering on Electronic Medical Records](https://mlsanity.com/paper/1908.01839/) (2019)
- [How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings](https://mlsanity.com/paper/2305.11853/) (2023)
- [Knowledge-Rich Self-Supervision for Biomedical Entity Linking](https://mlsanity.com/paper/2112.07887/) (2021)
- [Selective Demonstrations for Cross-domain Text-to-SQL](https://mlsanity.com/paper/2310.06302/) (2023)
- [Multi-label Few-shot ICD Coding as Autoregressive Generation with Prompt](https://mlsanity.com/paper/2211.13813/) (2022)
- [Towards Understanding the Generalization of Medical Text-to-SQL Models and Datasets](https://mlsanity.com/paper/2303.12898/) (2023)
- [Generalizing over Long Tail Concepts for Medical Term Normalization](https://mlsanity.com/paper/2210.11947/) (2022)

## Built on by (most cited first, 8 of 8)

- [A Collaborative Multi-Agent Approach to Retrieval-Augmented Generation Across Diverse Data](https://mlsanity.com/paper/2412.05838/) (2024)
- [Generating patient cohorts from electronic health records using two-step retrieval-augmented text-to-SQL generation](https://mlsanity.com/paper/2502.21107/) (2025)
- [BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Bases](https://mlsanity.com/paper/2505.20321/) (2025)
- [Timing Analysis Agent: Autonomous Multi-Corner Multi-Mode (MCMM) Timing Debugging with Timing Debug Relation Graph](https://mlsanity.com/paper/2504.11502/) (2025)
- [Disentangling Ambiguity from Instability in Large Language Models: A Clinical Text-to-SQL Case Study](https://mlsanity.com/paper/2602.12015/) (2026)
- [EHRNavigator: A Multi-Agent System for Patient-Level Clinical Question Answering over Heterogeneous Electronic Health Records](https://mlsanity.com/paper/2601.10020/) (2026)
- [CBR-to-SQL: Rethinking Retrieval-based Text-to-SQL using Case-based Reasoning in the Healthcare Domain](https://mlsanity.com/paper/2603.05569/) (2026)
- [Ascent: An Agentic System over the Model Context Protocol for Real-World Clinical Data Analysis](https://mlsanity.com/paper/2609.24620/) (2026)

## Abstract (arXiv)

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 a medical coding step into the text-to-SQL process, significantly improves the performance over simple prompting. Our findings indicate that although current language models are not yet sufficiently accurate for unsupervised use, RAG offers a promising direction for improving their capabilities, as shown in a realistic industry setting.