Application of Artificial Intelligence for Enhancing Clinical Reasoning and Providing Personalized Feedback to Veterinary Students in Feline Calicivirus Case Scenarios

Background: Feline calicivirus (FCV) is one of the most prevalent viral agents in upper respiratory tract infections among feline species. The overlap of its clinical signs with other diseases makes accurate diagnosis essential for avoiding unnecessary treatments. Traditional veterinary education—particularly in courses such as Small Animal Internal Medicine and Clinical Examination—often lacks structured strategies to foster clinical reasoning. This study aimed to evaluate the effectiveness of artificial intelligence (AI) in improving students’ clinical reasoning and providing personalized feedback within FCV-related case scenarios. Methods: A Key Features examination was designed, covering five core domains: history taking, physical examination, differential diagnosis, diagnostic testing, and therapeutic/management planning. The questionnaire’s content validity was reviewed, revised, and confirmed by four general practitioners and three residents in small animal internal medicine. Eligible participants were general veterinary students who had completed courses in microbiology, virology, and small animal examination. The questionnaire was distributed electronically via convenience sampling. Out of ۹۰ invited students, ۷۳ valid responses were obtained from eight universities (response rate: ۸۱.۱%). Students were informed that they could optionally provide their email to receive individualized feedback. In addition to overall analysis, personalized AI-generated feedback was sent to those who opted in. Results: Diagnostic testing (mean=۱.۳۸) and differential diagnosis (mean=۱.۹۱) represented the weakest areas. The overall clinical reasoning mean score was ۳.۰۳ (moderate level). Students with internship experience achieved significantly higher scores (p<۰.۰۵), whereas no statistically significant differences were observed across universities or other demographic variables. Conclusion: Integrating artificial intelligence into veterinary education can complement conventional teaching by improving analytical reasoning and enabling personalized feedback delivery, fostering more adaptive and reflective learning environments in small animal clinical training.

کلیدواژه ها:

Artificial intelligence ، Veterinary education ، Clinical reasoning ، Personalized feedback ، Feline calicivirus