Chat GPT-4 shows high agreement in MRI protocol selection compared to board-certified neuroradiologists.
Authors
Affiliations (10)
Affiliations (10)
- Clinic of Neuroradiology, University Hospital Bonn, Bonn, Germany; German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany. Electronic address: [email protected].
- Clinic of Neuroradiology, University Hospital Bonn, Bonn, Germany; German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany.
- Clinic of Neuroradiology, University Hospital Bonn, Bonn, Germany.
- Department of Radiology & Nuclear Medicine, Amsterdam UMC, Vrije Universiteit, Cancer Center Amsterdam, Amsterdam, the Netherlands.
- Department of Radiology & Nuclear Medicine, Amsterdam UMC, Vrije Universiteit, Cancer Center Amsterdam, Amsterdam, the Netherlands; Hospital Universitario Son Llátzer (HUSLL), Palma, Mallorca, Spain.
- Department of Medicine II, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany; Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden, Dresden, Germany.
- Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden, Dresden, Germany.
- Department of Diagnostic and Interventional Radiology, University Hospital Bonn, Bonn, Germany.
- Clinic of Neuroradiology, University Hospital Bonn, Bonn, Germany; Department of Radiology, Brigham and Womeńs Hospital, Harvard Medical School, Boston, MA, USA.
- Clinic of Neuroradiology, University Hospital Bonn, Bonn, Germany; Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA, USA.
Abstract
The aim of this study was to determine whether ChatGPT-4 can correctly suggest MRI protocols and additional MRI sequences based on real-world Radiology Request Forms (RRFs) as well as to investigate the ability of ChatGPT-4 to suggest time saving protocols. Retrospectively, 1,001 RRFs of our Department of Neuroradiology (in-house dataset), 200 RRFs of an independent Department of General Radiology (independent dataset) and 300 RRFs from an external, foreign Department of Neuroradiology (external dataset) were included. Patients' age, sex, and clinical information were extracted from the RRFs and used to prompt ChatGPT- 4 to choose an adequate MRI protocol from predefined institutional lists. Four independent raters then assessed its performance. Additionally, ChatGPT-4 was tasked with creating case-specific protocols aimed at saving time. Two and 7 of 1,001 protocol suggestions of ChatGPT-4 were rated "unacceptable" in the in-house dataset for reader 1 and 2, respectively. No protocol suggestions were rated "unacceptable" in both the independent and external dataset. When assessing the inter-reader agreement, Coheńs weighted ĸ ranged from 0.88 to 0.98 (each p < 0.001). ChatGPT-4's freely composed protocols were approved in 766/1,001 (76.5 %) and 140/300 (46.67 %) cases of the in-house and external dataset with mean time savings (standard deviation) of 3:51 (minutes:seconds) (±2:40) minutes and 2:59 (±3:42) minutes per adopted in-house and external MRI protocol. ChatGPT-4 demonstrated a very high agreement with board-certified (neuro-)radiologists in selecting MRI protocols and was able to suggest approved time saving protocols from the set of available sequences.