Visualizing and Interpreting Temporal Care Team Dynamics for Cancer Survival Risk Analysis

Authors

Yuhua Huang (University of California, Davis), Hsiao-Ying Lu (University of California, Davis), Kwan-Liu Ma (University of California at Davis)

Presentation

Session

Can we have a (real) doctor, please?

Time

Tuesday, Nov 10, 13:48 – 14:00 (US/Eastern) · session 13:00 – 14:30

Location

Hall America north

Keywords

Graph/Network and Tree Data ; Temporal Data ; Life Sciences, Health, Medicine, Biology, Bioinformatics, Genomics ; Data Analysis, Reasoning, Problem Solving, and Decision Making ; Machine Learning, AI, LLM, and GenAI Techniques ; Coordinated and Multiple Views

Abstract

Cancer care is a longitudinal, time-sensitive process that depends on the coordinated activities of diverse healthcare professionals (HCPs), whose patterns of collaboration evolve continuously throughout the course of treatment. Prior studies have shown that care team structure is associated with patient outcomes; however, the temporal dynamics of these collaborations and their relationship to evolving patient risk remain insufficiently understood. To address this gap, we introduce a visual analytics framework for modeling and interpreting time-varying care team interactions in oncology. We construct dynamic collaboration networks from electronic health record (EHR)-mediated communication data and employ a temporal graph neural network (TGNN) to estimate patient outcome risk over time. Building on these predictions, we examine how changes in care team composition and specialist participation are associated with shifts in estimated risk across different treatment stages. To support practitioner-driven analysis, we design a multi-view interactive system that integrates TGNN-based risk modeling with coordinated visualizations of care team networks, feature-level explanations derived from a surrogate logistic regression model, and exploratory what-if analysis. Rather than inferring causality, the system enables analysts to investigate how risk estimates co-evolve with collaboration patterns and to identify the care team characteristics most strongly associated with these temporal changes. We demonstrate the utility of the system through expert-guided analysis scenarios on a cohort of 505 cancer patients spanning breast, colorectal, and lung cancers, and evaluate its effectiveness in uncovering clinically meaningful collaboration patterns. This work contributes a practical approach for improving the interpretability of temporal graph-based models in longitudinal, team-based healthcare settings, with broader applicability to domains involving complex, evolving collaborative processes.

For Practitioners

This work may be of interest to clinicians, clinical informaticians, health-services researchers, healthcare data scientists, visualization practitioners, and machine learning and explainable AI researchers working with longitudinal, collaborative, or graph-based data. Practitioners can apply the ideas in this paper to analyze how teams and interactions evolve over time, relate these changes to model-estimated outcomes, and use coordinated visualizations to compare cohorts, examine individual trajectories, interpret important features, and identify patterns for further investigation. In healthcare, this approach can support the exploration of EHR-derived care-team activity and its relationship to changing patient risk. More broadly, the framework can inform the design of interpretable visual analytics systems for other domains involving complex, evolving collaborative processes.