Chasing sleep physicians: ChatGPT-4o on the interpretation of polysomnographic results
Precise prompting improves the output of ChatGPT-4o and provides sleep physician-like polysomnographic result interpretation. Although ChatGPT shows some shortcomings in offering treatment advice, our results provide evidence for AI assisted automation and economization of polysomnographic interpretation by LLMs. Further research should explore data protection issues and demonstrate reproducibility with real patient data on a larger scale.
Authors
- Katharina Bahr‐Hamm (ORCID: https://orcid.org/0000-0001-7428-127X)
- Jonas Eckrich (ORCID: https://orcid.org/0000-0001-5498-4031)
- Tilman Huppertz (ORCID: https://orcid.org/0000-0003-0654-3551)
- Christoph Raphael Buhr (ORCID: https://orcid.org/0000-0002-9551-2310)
- Christopher Seifen (ORCID: https://orcid.org/0000-0002-2356-7494)
- Sebastian Kühn (ORCID: https://orcid.org/0000-0002-8031-2973)
- Johannes Pordzik (ORCID: https://orcid.org/0000-0003-4926-3330)
- Haralampos T Gouveris (ORCID: https://orcid.org/0000-0001-7299-7346)
- Andrew Blaikie (ORCID: https://orcid.org/0000-0001-7913-6872)
- Harry A. Smith (ORCID: https://orcid.org/0009-0003-4497-1394)
- Tom Kelsey (ORCID: https://orcid.org/0000-0002-8091-1458)
- Christoph Matthias
Institutions
- University of St Andrews (GB)
- Johannes Gutenberg University Mainz (DE)
- Universitätsklinikum Gießen und Marburg (DE)
- University Medical Center of the Johannes Gutenberg University Mainz (DE)
Publication Details
- Journal
- European Archives of Oto-Rhino-Laryngology
- Published
- 2024-10-20
- DOI
- https://doi.org/10.1007/s00405-024-08985-3
- Citations
- 9
- Primary Topic
- Obstructive Sleep Apnea Research
- Type
- article
- Field-Weighted Citation Impact
- 2.94
Funders
- Universitätsmedizin der Johannes Gutenberg-Universität Mainz