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

2026-03-31

AI Summary

This study investigates how cognitive and affective states within medical teams influence collaborative diagnostic problem-solving. By simultaneously capturing physiological signals and dialogue data, it establishes a novel link between physiological synchrony and semantic similarity derived from sentence embeddings. Integrating SSRL encoding with triangulated qualitative analysis, the research reveals that high physiological synchrony is often associated with low semantic similarity, reflecting exploratory language use. It further identifies “critical turning points” with dual functions: successful teams exhibit synchrony during moments of shared insight, whereas unsuccessful teams synchronize during episodes of mutual confusion. Additionally, semantic similarity during the phase of activating prior knowledge is significantly lower than during task execution, underscoring the stage-dependent dynamics of collaborative cognition.

Abstract

Effective collaboration requires teams to manage complex cognitive and emotional states through Socially Shared Regulation of Learning (SSRL). Physiological synchrony (i.e., longitudinal alignment in physiological signals) can indicate these states, but is hard to interpret on its own. We investigate the physiological and conversational dynamics of four medical dyads diagnosing a virtual patient case using an intelligent tutoring system. Semantic shifts in dialogue were correlated with transient physiological synchrony peaks. We also coded utterance segments for SSRL and derived cosine similarity using sentence embeddings. The results showed that activating prior knowledge featured significantly lower semantic similarity than simpler task execution. High physiological synchrony was associated with lower semantic similarity, suggesting that such moments involve exploratory and varied language use. Qualitative analysis triangulated these synchrony peaks as ``pivotal moments'': successful teams synchronized during shared discovery, while unsuccessful teams peaked during shared uncertainty. This research advances human-centered AI by demonstrating how biological signals can be fused with dialogues to understand critical moments in problem solving.

Problem

• physiological synchrony
• semantic patterns
• medical teams
• collaborative problem solving
• Socially Shared Regulation of Learning

Innovation

• physiological synchrony
• semantic similarity
• intelligent tutoring system
• socially shared regulation of learning
• multimodal fusion