ArticleUltrasonography (Seoul, Korea)2025
Diagnostic performance of multimodal large language models in radiological quiz cases: the effects of prompt engineering and input conditions.
Article in Ultrasonography (Seoul, Korea), 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 7 papers.
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.
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.
Who cites it
7 citing papers in PubMed.
- How Robust Are Radiology Teaching-Case Benchmarks for Multimodal Large Language Models? An Audit of Exposure Opportunity, Inference Configuration, and Text-Only Solvability Across Eighteen Models.Journal of imaging informatics in medicine · 2026Article
- Diagnostic accuracy and consistency of ChatGPT-4o in radiology: influence of image, clinical data, and answer options on performance.Diagnostic and interventional radiology (Ankara, Turkey) · 2026Article
- Letter to the Editor: Comment on the diagnostic sensitivity of ChatGPT for detecting hemorrhages in cranial computed tomography scans.Diagnostic and interventional radiology (Ankara, Turkey) · 2026Article
- Confidence Measurement Metrics in Multimodal Large Language Models for Ultrasound-Based Radiology Cases: Comparative Evaluation Study of Self-Reported, Consistency-Based, and Hybrid Methods.Journal of medical Internet research · 2026Article
- Demographic prompt cues shift clinical recommendations in multimodal large language models: a multi-model audit of 25,380 dental radiograph assessments.BMC oral health · 2026Article
- ChatGPT-4V prompt: A tool to enhance junior radiologists' diagnostic capabilities in cystic renal masses to senior-level accuracy.Computational and structural biotechnology journal · 2026Article
- Comparative performance evaluation of large language models in answering esophageal cancer-related questions: a multi-model assessment study.Frontiers in digital health · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
purposeThis study aimed to evaluate the diagnostic accuracy of three multimodal large language models (LLMs) in radiological image interpretation and to assess the impact of prompt engineering strategies and input conditions.
methodsThis study analyzed 67 radiological quiz cases from the Korean Society of Ultrasound in Medicine. Three multimodal LLMs (Claude 3.5 Sonnet, GPT-4o, and Gemini-1.5-Pro-002) were evaluated using six types of prompts (basic [without system prompt], original [specific instructions], chain-of-thought, reflection, multiagent, and artificial intelligence [AI]-generated). Performance was assessed across various factors, including tumor versus non-tumor status, case rarity, difficulty, and knowledge cutoff dates. A subgroup analysis compared diagnostic accuracy between imaging-only inputs and combined imaging-descriptive text inputs.
resultsWith imaging-only inputs, Claude 3.5 Sonnet achieved the highest overall accuracy (46.3%, 186/402), followed by GPT-4o (43.5%, 175/402) and Gemini-1.5-Pro-002 (39.8%, 160/402). AI-generated prompts yielded superior combined accuracy across all three models, with improvements over the basic (5.5%, P=0.035), chain-of-thought (4.0%, P=0.169), and multiagent prompts (3.5%, P=0.248). The integration of descriptive text significantly enhanced diagnostic accuracy for Claude 3.5 Sonnet (46.3% to 66.2%, P<0.001), GPT-4o (43.5% to 57.5%, P<0.001), and Gemini-1.5-Pro-002 (39.8% to 60.4%, P<0.001). Model performance was significantly influenced by case rarity for GPT-4o (rare: 6.7% vs. non-rare: 53.9%, P=0.001) and by knowledge cutoff dates for Claude 3.5 Sonnet (post-cutoff: 23.5% vs. pre-cutoff: 64.0%, P=0.005).
conclusionClaude 3.5 Sonnet achieved the highest diagnostic accuracy in radiological quiz cases, followed by GPT-4o and Gemini-1.5-Pro-002. The use of AI-generated prompts and the integration of descriptive text inputs enhanced model performance.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
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.