Can large language models be new supportive tools in coronary computed tomography angiography reporting?

Eren Çamur1, Turay Cesur2, Yasin Celal Güneş3

  • 1Department of Radiology, Ministry of Health Ankara 29 Mayis State Hospital, Ankara, Türkiye.

Clinical Imaging
|September 5, 2024
PubMed
Summary

Large language models (LLMs) show strong performance in coronary artery disease (CAD) diagnosis using CAD-RADS 2.0 guidelines. ChatGPT 4o achieved 100% accuracy, highlighting LLMs' potential to improve radiological reporting and patient care.