MedGame: Storytelling Gamification Empowered by Large Language Models for Medical Education

2026-07-23

AI Summary

This work addresses the limitation of existing large language model–driven medical education systems, which are largely confined to question-answering or single-turn feedback and thus struggle to support clinical decision–centric learning trajectories. To overcome this, the authors propose MedGame, a novel framework that transforms static clinical cases into structured, executable narrative games. MedGame employs a dual-engine mechanism to generate coherent clinical storylines and orchestrate multimodal interactive experiences. The study introduces MedGame Bench, a benchmark comprising 5,000 cases, and releases a task-finetuned language model alongside an open-source interactive platform. Experimental results demonstrate that the proposed model significantly outperforms baseline approaches on the benchmark, achieving performance comparable to commercial models. User studies further indicate that the narrative-driven, interactive format enhances both pedagogical engagement and practical utility relative to purely text-based methods.

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.

Problem

• medical education
• clinical case
• decision-centered learning
• storytelling gamification
• Large Language Models

Innovation

• storytelling gamification
• large language models
• medical education
• narrative generation
• interactive learning