Smoking Cessation Counseling Performance Among Medical Interns

Effect of Artificial Intelligence-Assisted Interactive Case-Based Training on Smoking Cessation Counseling Performance Among Medical Interns

Smoking remains one of the leading preventable causes of morbidity and mortality worldwide and is strongly associated with chronic respiratory diseases, cardiovascular disease, cancer, and premature death. Physicians play a central role in tobacco control through the delivery of smoking cessation counseling, and even brief physician advice has been shown to significantly increase smoking quit rates. The evidence-based 5A's model (Ask, Advise, Assess, Assist, and Arrange) is widely recommended as the standard framework for smoking cessation counseling.

Despite the availability of effective counseling strategies and pharmacological interventions, smoking cessation counseling remains infrequently used in routine clinical practice. Recent studies have demonstrated gaps in physicians' knowledge, confidence, and implementation of smoking cessation interventions. In Egypt, a recent study among resident physicians reported deficiencies in smoking cessation knowledge and counseling practices, while another study demonstrated low rates of referral for smoking cessation counseling among healthcare workers.

Traditional educational approaches often rely on passive learning methods that may not adequately develop practical counseling skills. Interactive case-based learning has been shown to improve clinical communication skills and smoking cessation counseling performance among healthcare trainees. Furthermore, recent advances in artificial intelligence have enabled the development of interactive educational tools capable of simulating realistic clinical meeting and providing structured feedback. AI-assisted simulation has shown promising results in smoking cessation education and medical training.

However, evidence regarding the effectiveness of AI-assisted interactive case-based training for improving smoking cessation counseling performance among practicing physicians remains limited. Therefore, this study aims to evaluate the effect of AI-assisted interactive case-based training on smoking cessation counseling performance among medicals interns using a randomized controlled educational design.

Inclusion Criteria:

• Medical interns enrolled in the internship training program at the Faculty of Medicine, Assiut University during the study period.
• Able to attend the training session and complete all study assessments, including the pre-test and post-test evaluations.

Exclusion Criteria:

• Previous formal structured training in smoking cessation counseling based on the 5A model.
• Previous participation in a smoking cessation counseling educational program within the preceding 12 months.
• Failure to complete the assigned educational intervention.
• Failure to complete either the pre-test or post-test assessment.
• Withdrawal of consent at any stage of the study.