Effectiveness of Informed AI Use on Clinical Competence of General Practitioners and Internists: Pre-Post...

Area of Science:

• Medical Education
• Artificial Intelligence in Healthcare
• Clinical Competence Assessment

Background:

• Artificial intelligence (AI) holds potential for clinical diagnosis, treatment support, and healthcare efficiency.
• Limited clinical validation and unclear impact on practitioner competence hinder AI adoption in real-world healthcare.
• Effective, confident, and ethical AI integration requires addressing these adoption barriers.

Purpose of the Study:

• To evaluate the impact of tailored AI training on general practitioners (GPs) and internists' clinical competence.
• To assess changes in physicians' attitudes towards clinical AI applications after training.
• To determine the effectiveness of informed AI use in medical practice.

Main Methods:

• A pre-post intervention study involved 326 physicians from 39 countries.
• Participants completed clinical decision-making tests (diagnosis, treatment, counseling) before and after a 1.5-hour AI training course.
• Post-training tests allowed AI assistance (GPT-4.0), with performance, time, and AI perception evaluated.

Main Results:

• Average test scores increased from 56.9% to 77.6% (P<.001), with pass rates rising from 6.4% to 58.6%.
• All skill domains showed significant improvement (P<.001); test completion time slightly increased.
• Physicians reported increased confidence in AI accuracy and efficiency, and greater willingness to integrate AI into patient care.

Conclusions:

• Tailored AI training enhances physicians' clinical decision-making performance and confidence in AI use.
• This study provides empirical evidence of competence and perceptual gains in a large, multinational cohort.
• Findings support integrating structured AI training into medical education and professional development for improved clinical practice.