AI-Centered Grand Challenges in Visual Analytics for Healthcare: Synthesizing the VAHC 2025 Community Experience

2026-07-01

AI Summary

This study addresses the lack of interdisciplinary consensus in AI-driven medical visualization research. By systematically analyzing 15 papers from the VAHC 2025 workshop, organizing structured discussions among over 40 experts across three core themes, and incorporating post-workshop reflective analysis, this work presents the first integrated synthesis of perspectives from the medical, artificial intelligence, and visualization communities. The research identifies five key challenge clusters: trust and bias, data infrastructure, explainability, human–AI interaction, and model validation. For each cluster, the study offers concrete research recommendations aimed at fostering collaborative innovation across these disciplines and advancing the development of trustworthy, effective, and clinically relevant AI-visualization systems.

Abstract

The intersection of AI, healthcare, and visualization is evolving rapidly, posing challenges that cut across disciplinary boundaries and resist easy resolution. The Visual Analytics in Healthcare workshop (VAHC), co-located every other year at the IEEE VIS conference and the AMIA (American Medical Informatics Association) annual conference, has served as a forum to connect the visualization and medical informatics community since 2010. In 2025, to celebrate the 16th edition, we used the workshop as an opportunity to consolidate the community's collective experience (and expertise) and identify Grand Challenges where the field should prioritize going forward. We combined thematic coding of the 15 accepted VAHC workshop papers with structured group discussions among more than 40 participants, organized around three major themes: "Technical innovation vs. clinical reality", "Human-centered and scalable VAHC", and "From foundations to actionable insights", followed by post-workshop reflexive analysis. Across all three groups, AI emerged as the most consistently recurring concern. In this paper, we report our AI-centered insights from the VAHC 2025 group activity, contextualize them against the broader literature along five Grand Challenges themes, and distill them into five challenge clusters, each concluded with recommendations for future research directions that cross disciplinary boundaries: (1) trust and bias, (2) data and infrastructure, (3) explainability and communication, (4) human-AI interaction, and (5) model reliability and validation. We share these challenges and their associated research directions as a starting point for discussion and collaboration across the healthcare, AI, and visualization communities. All supplemental materials are available at https://osf.io/p79uj.

Problem

• AI
• Visual Analytics
• Healthcare
• Grand Challenges
• Interdisciplinary

Innovation

• AI-centered
• visual analytics
• grand challenges
• human-AI interaction
• explainability