Evidence map›Paper›PMID 41272207›Full record

ArticleScientific reports2025

Evaluating the reliability of large language models for clinical data extraction in bladder cancer prognosis.

Di Sun, Lubomir Hadjiiski, Grace Bruno, John Gormley, Heang-Ping Chan, Elaine M Caoili, Richard H Cohan, Ajjai Alva, Rada Mihalcea, Chuan Zhou and 1 more

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in Scientific reports, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 3 papers.

0numbers the graph read from it
0cells of the map it votes in
3citing 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

3 citing papers in PubMed.

  1. Article
  2. Article
  3. Article
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.

Di SunDepartment of Radiology, University of Michigan, Ann Arbor, MI, USA. disun@umich.edu.
Lubomir HadjiiskiDepartment of Radiology, University of Michigan, Ann Arbor, MI, USA.
Grace BrunoDepartment of Radiology, University of Michigan, Ann Arbor, MI, USA.
John GormleyDepartment of Radiology, University of Michigan, Ann Arbor, MI, USA.
Heang-Ping ChanDepartment of Radiology, University of Michigan, Ann Arbor, MI, USA.
Elaine M CaoiliDepartment of Radiology, University of Michigan, Ann Arbor, MI, USA.
Richard H CohanDepartment of Radiology, University of Michigan, Ann Arbor, MI, USA.
Ajjai AlvaDepartment of Internal Medicine-Hematology/Oncology, University of Michigan, Ann Arbor, MI, USA.
Rada MihalceaDepartment of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA.
Chuan ZhouDepartment of Radiology, University of Michigan, Ann Arbor, MI, USA.
Vikas GulaniDepartment of Radiology, University of Michigan, Ann Arbor, MI, USA.

Funding

Biomarker-Based Tools for Treatment Response Decision Support of Bladder CancerU01CA232931 · NCI · UNIVERSITY OF MICHIGAN AT ANN ARBOR · PI ALVA, AJJAI SHIVARAM, HADJIYSKI, LUBOMIR M · 2019 to 2024
$3.1M
NCI NIH HHS U01 CA232931NIH HHS U01-CA232931
6 · The paper itself

Abstract

Advances in natural language processing (NLP) and machine learning could assist human users in clinical data extraction from unstructured electronic medical records (EMRs). This study investigates the accuracy and consistency of several Large Language Models (LLMs) - including Dolly, Vicuna, Llama, and GPT-4 - in extracting critical clinical information pertinent to bladder cancer survival prediction. Using EMRs from 163 bladder cancer patients, we assessed the impact on LLM performance by factors such as differences in the trained models, model evolution, input text length, and sequencing of case inputs. GPT-4 demonstrated superior performance with Fleiss' Kappa values exceeding 0.97, accuracy consistently above 93%, and survival prediction metrics closely aligned with ground truth (AUC ± 0.02). Among offline models, Llama-2.0-13b and Llama-3.3-70b exhibited the highest reliability in both information extraction and survival prediction. This study underscores the potential of LLMs to automate clinical data extraction for predictive modeling while highlighting the challenges related to LLM variability and reliability.

Indexed as

Data MiningNatural Language ProcessingUrinary Bladder NeoplasmsAgedElectronic Health RecordsFemaleHumansLarge Language ModelsMachine LearningMaleMiddle AgedPrognosisReproducibility of ResultsBladder cancerCancer prognosisClinical information extractionLarge language modelsModel variabilitySurvival prediction

Identifiers

PMID41272207
PMCPMC12706081

What OpenQuestion holds

Textmetadata
LicenceCC BY-NC-ND
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.