MedGame: Storytelling Gamification Empowered by Large Language Models for Medical Education
2026-07-23 • Computation and Language
Computation and LanguageHuman-Computer Interaction
AI summaryⓘ
The authors created MedGame, a system that turns clinical cases into interactive storytelling games to help medical students learn by making decisions. It has two parts: one designs the medical story with choices, and the other turns it into a playable game with visuals and interactions. They also made a big set of 5,000 cases to test how well models can create these stories and games. Their tests show that training models specifically for this task makes them better, and students found MedGame more engaging than plain text materials.
Large Language ModelsMedical EducationClinical CaseInteractive StorytellingDecision-makingMultimodal InteractionBenchmark DatasetFine-tuningUser EngagementNarrative Generation
Authors
Qian Wu, Xinrong Zhou, Zizhan Ma, Kai Chen, Zheyao Gao, Xun Lin, Hongqiu Wu, Longfei Gou, Yixiao Liu, Ann Sin Nga Lau, Qi Dou
Abstract
Large Language Models (LLMs) show promise for medical education, but most existing systems focus on localized interactions such as question answering or single-turn feedback, rather than organizing an entire clinical case into a decision-centered learning trajectory. We introduce \textit{MedGame}, a framework that transforms static clinical cases into structured, executable storytelling games. MedGame uses a dual-engine design: a Medical Narrative Designer synthesizes case-grounded clinical storylines with states and decision nodes, while a Story Director converts them into dependency-aware multimodal orchestration plans rendered by our released interactive platform. We construct MedGame Bench, a 5,000-case benchmark and evaluation protocol for Medical Narrative Generation and Story Direction. Experiments show that task-specific fine-tuning substantially improves open-source LLMs on MedGame Bench and narrows the gap with commercial models. A pilot student study further shows that learners perceive MedGame as more engaging and useful than text-only alternatives.