Physiological and Semantic Patterns in Medical Teams Using an Intelligent Tutoring System

Effective collaboration in medical teams involves managing complex cognitive and emotional states through Socially Shared Regulation of Learning (SSRL). This research investigates physiological and conversational dynamics of medical dyads diagnosing virtual patient cases using an intelligent tutoring system. Semantic shifts in dialogue were correlated with transient physiological synchrony peaks, with high synchrony associated with lower semantic similarity, suggesting exploratory language use. Qualitative analysis revealed these peaks as "pivotal moments" for successful (shared discovery) and unsuccessful (shared uncertainty) teams. This advances human-centered AI by fusing biological signals with dialogues to understand critical problem-solving moments.