In this section
@article{Musbahi:2024:10.1016/j.knee.2024.08.015,
author = {Musbahi, O and Nurek, M and Pouris, K and Vella-Baldacchino, M and Bottle, A and Hing, C and Kostopoulou, O and Cobb, JP and Jones, GG},
doi = {10.1016/j.knee.2024.08.015},
journal = {Knee},
pages = {120--129},
title = {Can ChatGPT make surgical decisions with confidence similar to experienced knee surgeons?},
url = {http://dx.doi.org/10.1016/j.knee.2024.08.015},
volume = {51},
year = {2024}
}
TY - JOUR
AB - 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.
AU - Musbahi,O
AU - Nurek,M
AU - Pouris,K
AU - Vella-Baldacchino,M
AU - Bottle,A
AU - Hing,C
AU - Kostopoulou,O
AU - Cobb,JP
AU - Jones,GG
DO - 10.1016/j.knee.2024.08.015
EP - 129
PY - 2024///
SN - 0968-0160
SP - 120
TI - Can ChatGPT make surgical decisions with confidence similar to experienced knee surgeons?
T2 - Knee
UR - http://dx.doi.org/10.1016/j.knee.2024.08.015
UR - https://www.ncbi.nlm.nih.gov/pubmed/39255525
UR - https://www.sciencedirect.com/science/article/pii/S0968016024001492?via%3Dihub
VL - 51
ER -