Comparison of AI-generated and human-made animated videos for medical education: experts and students preferred AI over humans

Resumo

Objective: This study compared medical students and experts, and evaluated a frames‑to‑video AI‑generated problem‑based learning (PBL) trigger against its scene‑matched human‑made animated counterpart in terms of evaluations and preferences. Study Design: A mixed‑methods study was conducted at a medical school. Two scene‑matched videos were used: an AI‑generated video and an animated (human‑made) video. Students (n210; Years 2–5) viewed both videos in counterbalanced order and rated eight 5‑point Likert items for each; they also indicated their preferred video for engagement, emotional impact, and PBL use. A multidisciplinary expert panel (n=104) evaluated only the AI video on comparable items and provided open‑ended comments. Mann–Whitney-U tests compared experts with students on the AI video; Wilcoxon signed‑rank tests compared students’ ratings across videos. Qualitative data underwent thematic analysis. Results: Students rated the AI‑generated video significantly higher than the animated video on all eight items (all p≤.026) and preferred it for engagement (83.8%), emotional impact (81.0%), and PBL use (79.0%). Experts’ ratings of the AI video were also high and exceeded students’ ratings on visual quality, distraction avoidance, and visual consistency (p≤.001). Qualitative themes highlighted realism, suitability for PBL sessions, and strong engagement, while suggested improvements included micro‑continuity, pronunciation, and body language. Conclusion: Within the PBL context, a frames‑to‑video AI workflow produced a fully synthetic trigger that was preferred by students and endorsed by experts. AI‑generated triggers appear feasible, acceptable, and educationally promising, provided attention is given to fine‑grained audiovisual continuity and communication cues.