Medical Clinical Minds Meet Artificial Intelligence: Italian Physicians' Knowledge, Attitudes, and Concordance between Italian Physicians and AI-Generated Diagnoses. A National Cross-Sectional Study

Background: Artificial Intelligence (AI) has increasingly been integrated into clinical practice, yet the adoption and perception of AI among medical professionals remain poorly understood, particularly in the Italian healthcare context. Objective: To investigate Italian physicians' knowledge, attitudes, and clinical concordance with AI-generated diagnostic recommendations, using a validated questionnaire and a clinical scenario processed by ChatGPT. Methods: A national, cross-sectional web-based survey was conducted among 587 Italian physicians using an online validated questionnaire. The first part of the questionnaire assessed self-reported knowledge, prior experience, attitudes, and willingness to adopt AI in medicine. The second part assessed clinical concordance between AI proposals and physicians about clinical cases evaluated by ChatGPT (GPT-4). Descriptive and inferential statistics were used, including the Friedman test and Durbin-Conover post hoc comparisons. Results: Most participants reported basic AI knowledge (n=380, 64.5%) and minimal exposure to AI training (18.3%). The most familiar application was diagnostic imaging (47.0%). Only 22% reported they used AI in clinical practice, 82.0% expressed a willingness to adopt it, and 93.5% were interested in AI training. Major perceived barriers included lack of training (76.7%) and resistance to change (51.1%). In the universal clinical scenario, physicians showed the highest agreement with ChatGPT's correct diagnosis (mean=4.06) compared to incorrect alternatives (mean=2.57 and 1.82, p<0.001). For Correct diagnosis, the agreement rate (agree or strongly agree) was very high at 89% [95%CI:86%-91%]. A total of 68% [95%CI:64%-72%] demonstrated diagnostic discrimination, both endorsing the correct diagnosis and rejecting the incorrect ones. Conclusions: Italian physicians showed a strong interest in adopting AI tools, despite significant knowledge gaps and limited practical experience. The high concordance between physicians' evaluations and ChatGPT's diagnostic insights suggests potential for AI-based decision support in clinical workflows. Targeted training and institutional support are essential to bridge the gap between enthusiasm and readiness for AI integration.