Use of Artificial Intelligence in Vesicoureteral Reflux Disease: A Comparative Study of Guideline Compliance DOI Open Access
Mehmet SARIKAYA, Fatma ÖZCAN SIKI, İlhan Çiftçi

et al.

Journal of Clinical Medicine, Journal Year: 2025, Volume and Issue: 14(7), P. 2378 - 2378

Published: March 30, 2025

Objective: This study aimed to evaluate the compliance of four different artificial intelligence applications (ChatGPT-4.0, Bing AI, Google Bard, and Perplexity) with American Urological Association (AUA) vesicoureteral reflux (VUR) management guidelines. Materials Methods: Fifty-one questions derived from AUA guidelines were asked each AI application. Two experienced paediatric surgeons independently scored responses using a five-point Likert scale. Inter-rater agreement was analysed intraclass correlation coefficient (ICC). Results: ChatGPT-4.0, Perplexity received mean scores 4.91, 4.85, 4.75 4.70 respectively. There no statistically significant difference between accuracy (p = 0.223). The inter-rater ICC values above 0.9 for all platforms, indicating high level consistency in scoring. Conclusions: evaluated agreed highly VUR These results suggest that may be potential tool providing guideline-based recommendations urology.

Language: Английский

Use of Artificial Intelligence in Vesicoureteral Reflux Disease: A Comparative Study of Guideline Compliance DOI Open Access
Mehmet SARIKAYA, Fatma ÖZCAN SIKI, İlhan Çiftçi

et al.

Journal of Clinical Medicine, Journal Year: 2025, Volume and Issue: 14(7), P. 2378 - 2378

Published: March 30, 2025

Objective: This study aimed to evaluate the compliance of four different artificial intelligence applications (ChatGPT-4.0, Bing AI, Google Bard, and Perplexity) with American Urological Association (AUA) vesicoureteral reflux (VUR) management guidelines. Materials Methods: Fifty-one questions derived from AUA guidelines were asked each AI application. Two experienced paediatric surgeons independently scored responses using a five-point Likert scale. Inter-rater agreement was analysed intraclass correlation coefficient (ICC). Results: ChatGPT-4.0, Perplexity received mean scores 4.91, 4.85, 4.75 4.70 respectively. There no statistically significant difference between accuracy (p = 0.223). The inter-rater ICC values above 0.9 for all platforms, indicating high level consistency in scoring. Conclusions: evaluated agreed highly VUR These results suggest that may be potential tool providing guideline-based recommendations urology.

Language: Английский

Citations

0