作者: Siriwan Suebnukarn , Peter Haddawy
DOI:
关键词:
摘要: This paper describes COMET, a collaborative intelligent tutoring system for medical problembased learning. COMET uses Bayesian networks to model individual student knowledge and activity, as well that of the group. Generic domainindependent algorithms use models generate hints. We present an overview then results two evaluation studies. The validity modeling approach is evaluated in areas head injury, stroke heart attack. Receiver operating characteristic (ROC) curve analysis indicates that, are accurate predicting actions. Comparison learning outcomes shows clinical reasoning gains from our significantly higher than those obtained human tutored sessions (Mann-Whitney, p = 0.011).