Non-technical Skills for Urology Trainees: A Double-Blinded Study of ChatGPT4 AI Benchmarking Against Consultant Interaction.

Pears, M.; Wadhwa, K.; Payne, SR.; Hanchanale, V.; Elmamoun, MH.; Jain, S.; Konstantinidis, ST.; Rochester, M.; Doherty, R.; Spearpoint, K.; Ng, O.; Dick, L.; Yule, S.; Biyani, CS.

Non-technical Skills for Urology Trainees: A Double-Blinded Study of ChatGPT4 AI Benchmarking Against Consultant Interaction.

All Authors

Pears, M.

Wadhwa, K.

Payne, SR.

Hanchanale, V.

Elmamoun, MH.

Jain, S.

Konstantinidis, ST.

Rochester, M.

Doherty, R.

Spearpoint, K.

Show 4 more

LTHT Author

Elmamoun, Mamoun Hamid
Jain, Sunjay
Ng, Oliver
Biyani, Shekhar

LTHT Department

Abdominal Medicine & Surgery
Urology
Emergency Surgery

Publication Date

2025

Item Type

Journal Article

Abstract

Non-technical skills (NTS) are crucial in healthcare, encompassing cognitive and social skills that support technical ability. Traditional NTS training is evolving with the emergence of artificial intelligence (AI) models that can intelligently converse with their users, known as large language models (LLMs). This study investigated the capabilities and limitations of a popular model named generative pre-trained transformer 4 (GPT-4) in NTS training, comparing its performance to that of human evaluators. Urology trainees identified NTS events in simulated scenarios and discussed them in blinded feedback sessions with AI and human consultants. Experts assessed the blinded interaction data, providing quantitative ratings and qualitative evaluations using annotated transcripts. Wilcoxon signed-rank tests compared pre- and post-intervention ratings, whilst Mann-Whitney U tests compared post-intervention ratings between AI and human feedback. Thematic analysis identified strengths, limitations, and differences between AI and human feedback approaches. The AI model demonstrated significant strengths in reinforcing knowledge gathering (p = 0.04), providing accurate and evidence-based feedback (p = 0.013), conveying empathy (p = 0.021), and tailoring explanations to complexity (p = 0.002). However, human feedback excelled in language terminology (p = 0.003), complexity (p = 0.020), and fact-based feedback (p = 0.025). The study highlights the potential for AI to augment assessment of NTS training in healthcare. A blended approach utilising AI and human expertise may boost training efficacy.