ArticleDiagnostics (Basel, Switzerland)2024
Optimizing GPT-4 Turbo Diagnostic Accuracy in Neuroradiology through Prompt Engineering and Confidence Thresholds.
Article in Diagnostics (Basel, Switzerland), 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 21 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
21 citing papers in PubMed.
- Quantitative estimation of pleural effusion volume on chest radiography: comparison of radiologists and a general-purpose multimodal AI model using CT as the reference standard.European radiology experimental · 2026Observational
- Context-Guided Mixture-of-Experts with Multimodal LLMs for Lesion Detection in Buccal Mucosa Images.International dental journal · 2026Article
- Impact of Large Language Model Assistance on Radiologists' Diagnostic Performance for Brain Tumors by Experience Level.Journal of clinical medicine · 2026Article
- Diagnostic Accuracy of GPT-4 With Vision in Neuroradiology Board-Style Exam Questions: Cross-Sectional Case-Based Study.JMIR neurotechnology · 2026Article
- Trends and Trajectories in the Rise of Large Language Models in Radiology: Scoping Review.JMIR medical informatics · 2025Article
- Performance Evaluation of 18 Generative AI Models (ChatGPT, Gemini, Claude, and Perplexity) in 2024 Japanese Pharmacist Licensing Examination: Comparative Study.JMIR medical education · 2025Article
- Token Probabilities to Mitigate Large Language Models Overconfidence in Answering Medical Questions: Quantitative Study.Journal of medical Internet research · 2025Article
- Retrieval-augmented generation elevates local LLM quality in radiology contrast media consultation.NPJ digital medicine · 2025Article
- A Review of the Opportunities and Challenges with Large Language Models in Radiology: The Road Ahead.AJNR. American journal of neuroradiology · 2025Review
- AI in Medical Imaging and Image Processing.Journal of clinical medicine · 2025Article
- Large Language Models in Medical Diagnostics: Scoping Review With Bibliometric Analysis.Journal of medical Internet research · 2025Article
- Structured clinical reasoning prompt enhances LLM's diagnostic capabilities in diagnosis please quiz cases.Japanese journal of radiology · 2025Article
- A systematic review and meta-analysis of diagnostic performance comparison between generative AI and physicians.NPJ digital medicine · 2025Article
- Enhancing diagnostic capability with multi-agents conversational large language models.NPJ digital medicine · 2025Article
- Large language models for disease diagnosis: a scoping review.NPJ artificial intelligence · 2025Review
- Evaluation of large language models as a diagnostic tool for medical learners and clinicians using advanced prompting techniques.PloS one · 2025Article
- Assessing the Diagnostic Capabilities of ChatGPT-4 Omni in Grading Diabetic Retinopathy Fundoscopy Using Color Fundus Photographs.Clinical ophthalmology (Auckland, N.Z.) · 2025Article
- A systematic review and meta-analysis of GPT-based differential diagnostic accuracy in radiological cases: 2023-2025.Frontiers in radiology · 2025Article
- Large language models as a diagnostic support tool in neuropathology.The journal of pathology. Clinical research · 2024Article
- Accuracy Evaluation of GPT-Assisted Differential Diagnosis in Emergency Department.Diagnostics (Basel, Switzerland) · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
12 authors.
Funding
Abstract
BACKGROUND AND
objectivesIntegrating large language models (LLMs) such as GPT-4 Turbo into diagnostic imaging faces a significant challenge, with current misdiagnosis rates ranging from 30-50%. This study evaluates how prompt engineering and confidence thresholds can improve diagnostic accuracy in neuroradiology.
methodsWe analyze 751 neuroradiology cases from the American Journal of Neuroradiology using GPT-4 Turbo with customized prompts to improve diagnostic precision.
resultsInitially, GPT-4 Turbo achieved a baseline diagnostic accuracy of 55.1%. By reformatting responses to list five diagnostic candidates and applying a 90% confidence threshold, the highest precision of the diagnosis increased to 72.9%, with the candidate list providing the correct diagnosis at 85.9%, reducing the misdiagnosis rate to 14.1%. However, this threshold reduced the number of cases that responded.
conclusionsStrategic prompt engineering and high confidence thresholds significantly reduce misdiagnoses and improve the precision of the LLM diagnostic in neuroradiology. More research is needed to optimize these approaches for broader clinical implementation, balancing accuracy and utility.
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.