Exploring the Future of AI in Clinical Collaboration: A Study on Tumor Board Case Preparation
- Jiachen Li ,
- Amanda K. Hall ,
- Ruican Zhong ,
- Selin S. Everett ,
- Alyssa Unell ,
- Hanwen Xu ,
- Matthias Blondeel ,
- Jonathan M. Carlson ,
- Katie Claveau ,
- Thulasee Jose ,
- Tristan Naumann ,
- David C. Rhew ,
- Naiteek Sangani ,
- Frank Tuan ,
- James Weinstein ,
- Varun Mishra ,
- Elizabeth D. Mynatt ,
- Hao Qiu ,
- Leonardo Schettini ,
- Joseph S. Preston ,
- Aiden Gu ,
- Naoto Usuyama ,
- Zelalem Gero ,
- Cliff Wong ,
- Noel C. Codella ,
- Hoifung Poon ,
- Shrey Jain ,
- Matthew P Lungren ,
- Eric Horvitz
ACM CHI Conference on Human Factors in Computing Systems (CHI 2026) |
Honorable Mention Award
Download BibTexMultidisciplinary tumor boards (MTBs) bring specialists together to identify therapies for complex cancer cases, but preparing for them is time-intensive. Clinicians must extract key details from extensive records and evaluate treatment options. While large language models (LLMs) show promise in medicine for basic tasks like summarizing notes, little is known about their role in high-stakes tasks like MTB preparation. We conducted a mixed-methods study with 16 oncologists using two AI systems to prepare patient cases for MTB: an off-the-shelf assistant (Copilot) and a task-specific multi-agent system (Healthcare Agent Orchestrator, HAO). We analyzed oncologist prompts, AI responses, and oncologists’ perception of AI. Participants showed greater willingness to adopt HAO but were often overconfident in AI summaries and skeptical of AI-recommended therapies. Trust calibration strategies, such as source links and agent-trajectories, failed to align trust with system capabilities. We conclude with how AI systems should be built to support clinicians in high-stakes tasks.