Large language model chatbot-based text-to-SQL application for database analyses in liver diseases and hepatology research
Aryana T Far, Steve Sun, Gabrielle Jutras, Melinda B Wang, Shohei Burns, Joseph Owens, Victor Galvez, Ma Somsouk, Jennifer C Lai, Ki Lai, Jin Ge · 2026
Read Large language model chatbot-based text-to-SQL application for database analyses in liver diseases and hepatology research by Aryana T Far, Steve Sun, Gabrielle Jutras, Melinda B Wang, Shohei Burns, Joseph Owens, Victor Galvez, Ma Somsouk, Jennifer C Lai, Ki Lai, Jin Ge (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13278831.txt.
Description
Aryana T Far leads a 2026 proof-of-concept study of a chatbot that turns plain-language questions into database queries for liver cancer research. Clinicians often cannot use structured research data without coding skills. Built on a secure university platform, the chatbot writes SQL code, runs it, and returns both code and results, keeping protected health information inside approved systems.
Clinicians posed thirty questions, and outputs were compared with a data scientist's code. The chatbot read the intent of about seventy-three percent of prompts correctly. Its generated code and final outputs were each accurate in roughly fifty-three to sixty-three percent of cases. Errors clustered around group comparisons, ambiguous variables, and open-ended exploration.
Catalog record
| CREATOR | Aryana T Far, Steve Sun, Gabrielle Jutras, Melinda B Wang, Shohei Burns, Joseph Owens, Victor Galvez, Ma Somsouk, Jennifer C Lai, Ki Lai, Jin Ge |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 19582 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |