Can ChatGPT make surgical decisions with confidence similar to experienced knee surgeons?
The Knee · 2024
DOI: 10.1016/j.knee.2024.08.015 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Knee, 2024. Verfasst von Omar Musbahi und 8 weiteren Autor:innen. Beteiligte Einrichtung: MSk Lab, Sir Michael Uren Hub, Imperial College London, London, UK. Electronic address: o.musbahi19@imperial.ac.uk. Hauptthemen laut MEDLINE: Arthroplasty, Replacement, Knee, Osteoarthritis, Knee, Clinical Decision-Making. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Patient Safety Translational Research Centre, National Institute for Health and Care Research, NIHR Imperial Biomedical Research Centre.
Abstract (Originalsprache)
BACKGROUND: Unicompartmental knee replacements (UKRs) have become an increasingly attractive option for end-stage single-compartment knee osteoarthritis (OA). However, there remains controversy in patient selection. Natural language processing (NLP) is a form of artificial intelligence (AI). We aimed to determine whether general-purpose open-source natural language programs can make decisions regarding a patient's suitability for a total knee replacement (TKR) or a UKR and how confident AI NLP programs are in surgical decision making. METHODS: We conducted a case-based cohort study using data from a separate study, where participants (73 surgeons and AI NLP programs) were presented with 32 fictitious clinical case scenarios that simulated patients with predominantly medial knee OA who would require surgery. Using the overall UKR/TKR judgments of the 73 experienced knee surgeons as the gold standard reference, we calculated the sensitivity, specificity, and positive predictive value of AI NLP programs to identify whether a patient should undergo UKR. RESULTS: There was disagreement between the surgeons and ChatGPT in only five scenarios (15.6%). With the 73 surgeons' decision as the gold standard, the sensitivity of ChatGPT in determining whether a patient should undergo UKR was 0.91 (95% confidence interval (CI): 0.71 to 0.98). The positive predictive value for ChatGPT was 0.87 (95% CI: 0.72 to 0.94). ChatGPT was more confident in its UKR decision making (surgeon mean confidence = 1.7, ChatGPT mean confidence = 2.4). CONCLUSIONS: It has been demonstrated that ChatGPT can make surgical decisions, and exceeded the confidence of experienced knee surgeons with substantial inter-rater agreement when deciding whether a patient was most appropriate for a UKR.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- MSk Lab, Sir Michael Uren Hub, Imperial College London, London, UK. Electronic address: o.musbahi19@imperial.ac.uk.
- Department of Surgery and Cancer, Imperial College London, London, UK.
- MSk Lab, Sir Michael Uren Hub, Imperial College London, London, UK.
- School of Public Health, Imperial College London, London, UK.
- St George's University Hospitals NHS Foundation Trust, London, UK.
- Department of Surgery and Cancer, Imperial College London, London, UK; Institute of Global Health Innovation, Imperial College London, London, UK.
Förderung
- Patient Safety Translational Research Centre
- National Institute for Health and Care Research
- NIHR Imperial Biomedical Research Centre
Zitieren
APA
Musbahi, O., Nurek, M., Pouris, K., Vella-Baldacchino, M., Bottle, A., Hing, C., Kostopoulou, O., Cobb, J. P., & Jones, G. G. (2024). Can ChatGPT make surgical decisions with confidence similar to experienced knee surgeons?. The Knee. https://doi.org/10.1016/j.knee.2024.08.015
Vancouver
Musbahi O, Nurek M, Pouris K, Vella-Baldacchino M, Bottle A, Hing C, et al. Can ChatGPT make surgical decisions with confidence similar to experienced knee surgeons?. The Knee. 2024. doi:10.1016/j.knee.2024.08.015
BibTeX
@article{Musbahi2024,
author = {Musbahi, Omar and Nurek, Martine and Pouris, Kyriacos and Vella-Baldacchino, Martinique and Bottle, Alex and Hing, Caroline and Kostopoulou, Olga and Cobb, Justin P and Jones, Gareth G},
title = {Can ChatGPT make surgical decisions with confidence similar to experienced knee surgeons?},
journal = {The Knee},
year = {2024},
doi = {10.1016/j.knee.2024.08.015}
}
EUVIMED