Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Medical Informatics

Date Submitted: Nov 10, 2025
Open Peer Review Period: Nov 25, 2025 - Jan 20, 2026
Date Accepted: Apr 21, 2026
(closed for review but you can still tweet)

The final, peer-reviewed published version of this preprint can be found here:

Improving Radiology Report Error Detection Using a Multipass Large Language Model: Framework Development and Validation

Kim S, Lee S, Lee SY, Kim J, Kan K, Lee H, Yoon D

Improving Radiology Report Error Detection Using a Multipass Large Language Model: Framework Development and Validation

JMIR Med Inform 2026;14:e87368

DOI: 10.2196/87368

PMID: 42241684

Improving Radiology Report Error Detection Using a Multi-Pass LLM: Framework Development and Validation

  • Songsoo Kim; 
  • Seungtae Lee; 
  • See Young Lee; 
  • Joonho Kim; 
  • Keechan Kan; 
  • Hyunji Lee; 
  • Dukyong Yoon

ABSTRACT

Background:

Large language model (LLM) proofreaders for radiology reports generate many false positives (FP) due to the low prevalence of errors.

Objective:

This study aimed to determine whether an optimized LLM framework could improve both precision and cost-efficiency without compromising error detection capability.

Methods:

In this retrospective study, 1,000 radiology reports (radiography, ultrasonography, CT, and MRI; 250 each) were sampled from the Medical Information Mart for Intensive Care III (MIMIC-III) database. Two public chest radiography corpora (CheXpert and Open-i) served as external test sets. Three LLM frameworks were evaluated: single-prompt detector (Framework 1); report extractor plus single-prompt detector (Framework 2); and extractor, detector, and false positive verifier (Framework 3). Precision for each framework was assessed using positive predictive value (PPV) and detected errors per 1,000 reports (DE/1k). Overall efficiency was estimated using model inference computational costs.

Results:

PPV increased from 0.063 [95% CI, 0.036–0.101] in Framework 1 to 0.079 (0.049–0.118) in Framework 2 and 0.159 (0.090–0.252) in Framework 3 (P<.001). Despite improved PPV, detected errors remained stable (DE/1k: 12–14). Human review burden decreased from 192 to 88 reports. Framework 3 also reduced costs to $5.58 per 1,000 reports (vs $9.72 and $6.85 for Frameworks 1 and 2; 42.6% and 18.5% reductions). External validation confirmed similar improvements.

Conclusions:

A three-pass LLM framework more than doubled precision and halved the cost of radiology report error detection without compromising error detection capability, offering sustainable strategies for AI-assisted quality assurance in both radiological practice and research.


 Citation

Please cite as:

Kim S, Lee S, Lee SY, Kim J, Kan K, Lee H, Yoon D

Improving Radiology Report Error Detection Using a Multipass Large Language Model: Framework Development and Validation

JMIR Med Inform 2026;14:e87368

DOI: 10.2196/87368

PMID: 42241684

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.