Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.00772 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912899889364992 |
|---|---|
| author | Xiong, Raymond M. Chen, Panyu Dong, Tianze Lu, Jian Hu, Louis Yu, Nathan Goldstein, Benjamin Zhuo, Danyang Zhang, Anru R. |
| author_facet | Xiong, Raymond M. Chen, Panyu Dong, Tianze Lu, Jian Hu, Louis Yu, Nathan Goldstein, Benjamin Zhuo, Danyang Zhang, Anru R. |
| contents | Electronic health records (EHRs) are central to modern healthcare delivery and research; yet, many researchers lack the database expertise necessary to write complex SQL queries or generate effective visualizations, limiting efficient data use and scientific discovery. To address this barrier, we introduce CELEC, a large language model (LLM)-powered framework for automated EHR data extraction and analytics. CELEC translates natural language queries into SQL using a prompting strategy that integrates schema information, few-shot demonstrations, and chain-of-thought reasoning, which together improve accuracy and robustness. CELEC also adheres to strict privacy protocols: the LLM accesses only database metadata (e.g., table and column names), while all query execution occurs securely within the institutional environment, ensuring that no patient-level data is ever transmitted to or shared with the LLM. On a subset of the EHRSQL benchmark, CELEC achieves execution accuracy comparable to prior systems while maintaining low latency, cost efficiency, and strict privacy by exposing only database metadata to the LLM. Ablation studies confirm that each component of the SQL generation pipeline, particularly the few-shot demonstrations, plays a critical role in performance. By lowering technical barriers and enabling medical researchers to query EHR databases directly, CELEC streamlines research workflows and accelerates biomedical discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_00772 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reliable Curation of EHR Dataset via Large Language Models under Environmental Constraints Xiong, Raymond M. Chen, Panyu Dong, Tianze Lu, Jian Hu, Louis Yu, Nathan Goldstein, Benjamin Zhuo, Danyang Zhang, Anru R. Databases Machine Learning Applications Electronic health records (EHRs) are central to modern healthcare delivery and research; yet, many researchers lack the database expertise necessary to write complex SQL queries or generate effective visualizations, limiting efficient data use and scientific discovery. To address this barrier, we introduce CELEC, a large language model (LLM)-powered framework for automated EHR data extraction and analytics. CELEC translates natural language queries into SQL using a prompting strategy that integrates schema information, few-shot demonstrations, and chain-of-thought reasoning, which together improve accuracy and robustness. CELEC also adheres to strict privacy protocols: the LLM accesses only database metadata (e.g., table and column names), while all query execution occurs securely within the institutional environment, ensuring that no patient-level data is ever transmitted to or shared with the LLM. On a subset of the EHRSQL benchmark, CELEC achieves execution accuracy comparable to prior systems while maintaining low latency, cost efficiency, and strict privacy by exposing only database metadata to the LLM. Ablation studies confirm that each component of the SQL generation pipeline, particularly the few-shot demonstrations, plays a critical role in performance. By lowering technical barriers and enabling medical researchers to query EHR databases directly, CELEC streamlines research workflows and accelerates biomedical discovery. |
| title | Reliable Curation of EHR Dataset via Large Language Models under Environmental Constraints |
| topic | Databases Machine Learning Applications |
| url | https://arxiv.org/abs/2511.00772 |