# Generating patient cohorts from electronic health records using two-step retrieval-augmented text-to-SQL generation

arXiv: https://arxiv.org/abs/2502.21107 · HTML: https://mlsanity.com/paper/2502.21107/

## Key facts

- Cited by 4 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 19 of its 43 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [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)
- [Evaluating the Text-to-SQL Capabilities of Large Language Models](https://mlsanity.com/paper/2204.00498/) (2022)
- [Text-to-SQL Generation for Question Answering on Electronic Medical Records](https://mlsanity.com/paper/1908.01839/) (2019)
- [ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought](https://mlsanity.com/paper/2310.17342/) (2023)
- [A Multi-Task Embedder For Retrieval Augmented LLMs](https://mlsanity.com/paper/2310.07554/) (2023)
- [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)
- [A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL](https://mlsanity.com/paper/2411.08599/) (2024)
- [EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records](https://mlsanity.com/paper/2301.07695/) (2023)
- [Knowledge-Rich Self-Supervision for Biomedical Entity Linking](https://mlsanity.com/paper/2112.07887/) (2021)
- [Scaling Clinical Trial Matching Using Large Language Models: A Case Study in Oncology](https://mlsanity.com/paper/2308.02180/) (2023)
- [Selective Demonstrations for Cross-domain Text-to-SQL](https://mlsanity.com/paper/2310.06302/) (2023)
- [Towards Understanding the Generalization of Medical Text-to-SQL Models and Datasets](https://mlsanity.com/paper/2303.12898/) (2023)
- [LeafAI: query generator for clinical cohort discovery rivaling a human programmer](https://mlsanity.com/paper/2304.06203/) (2023)
- [Generalizing over Long Tail Concepts for Medical Term Normalization](https://mlsanity.com/paper/2210.11947/) (2022)
- [Retrieval augmented text-to-SQL generation for epidemiological question answering using electronic health records](https://mlsanity.com/paper/2403.09226/) (2024)
- [Medical Coding with Biomedical Transformer Ensembles and Zero/Few-shot Learning](https://mlsanity.com/paper/2206.02662/) (2022)

## Built on by (most cited first, 4 of 4)

- [Disentangling Ambiguity from Instability in Large Language Models: A Clinical Text-to-SQL Case Study](https://mlsanity.com/paper/2602.12015/) (2026)
- [EHR-RAGp: Retrieval-Augmented Prototype-Guided Foundation Model for Electronic Health Records](https://mlsanity.com/paper/2605.12335/) (2026)
- [ClinQueryAgent: A Conversational Agent for Population Health Management](https://mlsanity.com/paper/2605.18768/) (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)

Clinical cohort definition is crucial for patient recruitment and observational studies, yet translating inclusion/exclusion criteria into SQL queries remains challenging and manual. We present an automated system utilizing large language models that combines criteria parsing, two-level retrieval augmented generation with specialized knowledge bases, medical concept standardization, and SQL generation to retrieve patient cohorts with patient funnels. The system achieves 0.75 F1-score in cohort identification on EHR data, effectively capturing complex temporal and logical relationships. These results demonstrate the feasibility of automated cohort generation for epidemiological research.