Advanced large language models like GPT-4 accurately identify thoracic diseases in chest CT reports, enhancing pre-operative surgical planning.
Key Details
- 1Five LLMs (GPT-4, Claude-3.5, Qwen-Max, GPT-3.5-Turbo, Gemini-Pro) compared using 13,489 real-world chest CT reports.
- 2GPT-4 achieved up to 75% accuracy in identifying 13 common chest diseases with multiple-choice prompts.
- 3Multiple-choice prompts significantly improved model accuracy compared to open-ended questions.
- 4Fine-tuning GPT-3.5-Turbo increased its accuracy from 42% to 65% in challenging cases.
- 5No single LLM was best for all diseases, suggesting a tailored approach may be optimal.
- 6Future research will use explainable AI tools to increase transparency and reliability.
Why It Matters
The study demonstrates that modern LLMs can act as accurate 'second readers' for radiology reports, possibly reducing diagnostic errors and alleviating radiologist workload. Fine-tuning and prompt design further boost performance, potentially making AI support accessible even in resource-limited settings.
Source
EurekAlert
Related News
•EurekAlert
AI-Assisted Tracking Reveals Stem Cell Therapy Promotes Stroke Recovery in Mice
Mice with ischemic stroke receiving human neural stem cell transplants showed robust brain recovery, measured using AI-based limb tracking.
•EurekAlert
TCT 2025 to Feature Dedicated AI Lab for Cardiovascular Clinicians
The Cardiovascular Research Foundation and Jon DeHaan Foundation will launch the TCT AI Lab at TCT 2025, focusing on integrating AI into clinical cardiovascular practice.
•EurekAlert
Moffitt Develops AI Model to Predict Urgent Care in Lung Cancer Patients
Moffitt Cancer Center researchers created machine learning models that use patient-reported outcomes and wearable data to predict urgent care visits for non-small cell lung cancer patients.