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

Xiaoshan Huang; Conrad Borchers; Jiayi Zhang; Susanne P. Lajoie

cs.AIMar 31, 2026

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

Authors: Xiaoshan Huang, Conrad Borchers, Jiayi Zhang, Susanne P. Lajoie

Organizations: McGill University, Montreal, Canada · Carnegie Mellon University, Pittsburgh, USA · University of Pennsylvania, Philadelphia, USA

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.

Figures & tables

Figure 1: Within-speaker similarity patterns. Left: Mean cosine similarity (±95% CI) for the five most frequent SSRL codes, revealing systematic differences in internal consistency across interaction types. Right: Association between physiological synchrony peaks ( $r_{max}$ ) and cosine similarity, with SSRL code means and 95% CI error bars.

Figure 2: Between-speaker similarity patterns. Task execution (TE)maintains higher similarity values, while prior knowledge activation (PKA) shows relatively lower alignment.

Scalable LLM-based Coding of Dialogue in Healthcare Simulation: Balancing Coding Performance, Processing Time, and Environmental Impact
Apr 25, 2026Kiyoshige Garces, Gloria Milena Fernandez-Nieto, Linxuan Zhao +4LLM Inference Efficiency LLM Prompting
RMIT University · Monash University · Adelaide University +2
Rationalize: Shared Semantic Reasoning for Human-AI Alignment
May 28, 2026Aritra Dasgupta, Naga Datha Saikiran Battula, Avina Nakarmi +3AI Alignment Human-AI Interaction
New Jersey Institute of Technology Newark, USA
Searching for Synergy in Shared Workspace Human-AI Collaboration
Jun 16, 2026Nachiket Kotalwar, Rohini Das, Carolyn RoseMulti-Agent Coordination Human-in-the-Loop AI
1Carnegie Mellon University.

Apr 25, 2026J/K move · Enter open · S save

Scalable LLM-based Coding of Dialogue in Healthcare Simulation: Balancing Coding Performance, Processing Time, and Environmental Impact

Kiyoshige Garces, Gloria Milena Fernandez-Nieto, Linxuan Zhao, Sachini Samaraweera+3

RMIT University · Monash University · Adelaide University+2

LLM Inference Efficiency LLM Prompting LLM-Assisted Annotation

Open paper AskPDF arXiv

Research shows that dialogue, the interactive process through which participants articulate their thinking, plays a central role in constructing shared understanding, coordinating action, and shaping learning outcomes in teams. Analysing dialogue content has been central to advancing team learning theory and informing the design of computer-supported collaborative learning environments, yet this progress has depended on labour-intensive qualitative coding. LLMs offer new possibilities for automating and enhancing the dialogue layer within emerging multimodal learning analytics approaches, with recent studies showing that they can approximate human coding through few-shot prompting. However, prior work has focused on replicating human coding accuracy for research purposes, rather than addressing a more educationally consequential question: how can we design prompts that allow an LLM to label team dialogue accurately and fast enough to be useful in real settings, such as in-person healthcare simulations, where results must be returned quickly and computational cost and sustainability also matter? This paper investigates how prompt design and batching strategies can be optimised to balance coding accuracy, processing time, and environmental impact in team-based healthcare simulation debriefing. Using a dataset of 11,647 utterances coded across 6 dialogue constructs, we compared 4 prompt designs across varying batch sizes, evaluating coding performance, processing time, and energy consumption, as well as the trade-offs between these metrics. Results indicate that increasing batch size improves speed and reduces energy use, but negatively impacts coding performance. Beyond demonstrating the feasibility of LLM-based qualitative analysis, this study offers practical guidance for scaling dialogue analytics in contexts where timeliness, privacy, and sustainability are critical.

Abstract

Explore similar work

Scalable LLM-based Coding of Dialogue in Healthcare Simulation: Balancing Coding Performance, Processing Time, and Environmental Impact

Rationalize: Shared Semantic Reasoning for Human-AI Alignment

Searching for Synergy in Shared Workspace Human-AI Collaboration