Evidence map›Paper›PMID 42327622›Full record

ArticleJAMIA open2026

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 and 1 more

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in JAMIA open, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.

0numbers the graph read from it
0cells of the map it votes in
0citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

0 citing papers in PubMed.

No citing paper in PubMed yet.

4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

11 authors.

Aryana T FarDivision of Gastroenterology and Hepatology, Department of Medicine at the University of California, San Francisco, San Francisco, CA, United States.
Steve SunUCSF Health Information Technology at the University of California, San Francisco, San Francisco, CA, United States.
Gabrielle JutrasDivision of Gastroenterology and Hepatology, Department of Medicine at the University of California, San Francisco, San Francisco, CA, United States.
Melinda B WangDivision of Gastroenterology and Hepatology, Department of Medicine at the University of California, San Francisco, San Francisco, CA, United States.
Shohei BurnsDivision of Gastroenterology and Hepatology, Department of Medicine at the University of California, San Francisco, San Francisco, CA, United States.
Joseph OwensUCSF Health Information Technology at the University of California, San Francisco, San Francisco, CA, United States.
Victor GalvezUCSF Health Information Technology at the University of California, San Francisco, San Francisco, CA, United States.
Ma SomsoukDivision of Gastroenterology and Hepatology, Department of Medicine at the University of California, San Francisco, San Francisco, CA, United States.ORCID https://orcid.org/0000-0001-6116-3645
Jennifer C LaiDivision of Gastroenterology and Hepatology, Department of Medicine at the University of California, San Francisco, San Francisco, CA, United States.
Ki LaiUCSF Health Information Technology at the University of California, San Francisco, San Francisco, CA, United States.
Jin GeDivision of Gastroenterology and Hepatology, Department of Medicine at the University of California, San Francisco, San Francisco, CA, United States.

Funding

UCSF Liver Core CenterP30DK026743 · NIDDK · UNIVERSITY OF CALIFORNIA, SAN FRANCISCO · PI Holger Willenbring · 1986 to 2026
$30.7M
NIDDK NIH HHS P30 DK026743
6 · The paper itself

Abstract

Objective: 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 according to strict binary criteria. Results: Prompt interpretation accuracy was 73.3%, SQL accuracy ranged from 53% to 63%, and output accuracy from 53% to 63%. 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.

Indexed as

data analysisgastroenterologygenerative artificial intelligenceLarge language modelsliver diseases

Identifiers

PMID42327622
PMCPMC13278831

What OpenQuestion holds

Textmetadata
LicenceCC BY
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.