Supplemental data from: Large language model chatbot-based text-to-SQL application for database analyses in liver diseases and hepatology research
Year: 2026
Type: supplementary-materials
Abstract: Objectives: Large language models (LLMs) may improve analysis of structured clinical data by enabling natural language (NL) queries. We developed an interactive, PHI-compliant “Text2SQL” chatbot as a proof-of-concept for hepatocellular carcinoma (HCC) research. Materials and methods: Using the University of California, San Francisco’s secure artificial intelligence platform, we configured the chatbot to translate NL queries into Structured Query Language (SQL), execute them, and return both code and results. Clinicians posed 30 questions, and outputs were compared with SQL written by a data scientist. We assessed prompt interpretation, SQL accuracy, output accuracy, and error types. Results: Prompt interpretation accuracy was 87%, SQL accuracy ranged from 77-83%, and output accuracy from 70-80%. Frequent errors included group comparisons, ambiguous variables, and exploratory questions. Discussion Text2SQL enables PHI-compliant interaction with clinical datasets without coding, though performance varies across query types. Conclusion: LLM-powered Text2SQL offers a promising approach for clinician-friendly clinical data access.
Source: DRYAD
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: green
Awards: G208418196, Investigating the role of frailty on outcomes in acutely ill patients with cirrhosis undergoing liver transplantation in the acute care setting, NRSA Hepatology Training Grant, The Impact of Frailty on Liver Transplant Outcomes in Older Adults with Hepatocellular Carcinoma, A pragmatic RCT to evaluate the effect of CirrhosisRx, a novel clinical decision support system, versus usual care on guideline-adherence and clinical outcomes for patients with cirrhosis
OpenAlex ID: W7164333472