Reimagining Multidisciplinary Teams: Challenges and Opportunities for LLMs in Cancer MDTs
Soraia Figueiredo Paulo, Isabel Neto, Nuno Leitão Figueiredo, Daniel Simões Lopes, Hugo Nicolau
Abstract
Multidisciplinary teams are crucial in tailoring cancer care through collaborative decision-making involving several clinical specialties. The inherent complexity of clinical cases, the increasing abundance of unstructured textual data, and the time restrictions of professionals pose significant challenges to team coordination and patient care. This creates an opportunity for generative AI technologies, such as LLMs, to enhance collaborative work. Despite the growing interest in HCI research to explore LLMs in healthcare, we have yet to understand clinicians' perspectives on this emerging technology in multidisciplinary teams. Our work investigates the challenges, expectations and opportunities for LLMs in this context through a speculative approach. We leveraged the Futures Cone framework and conducted a qualitative study with 11 physicians from different cancer multidisciplinary teams. We contribute with an analysis of themes that emerged from individual interviews and a focus group, highlighting LLMs' potential to enhance and reshape multidisciplinary teams' practices. In addition, we uncover concerns and coping strategies related to LLMs' adoption and provide a set of design opportunities to inform the development of technologies for LLM-enhanced multidisciplinary teams.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext d4af5208-342a-49ef-98c5-1079baaeadb1Cited by top-tier papers1
Ask how each one uses itBuilds on10
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Explanations Can Reduce Overreliance on AI Systems During Decision-MakingHelena Vasconcelos, Matthew Jörke, Madeleine Grunde-McLaughlin, Tobias Gerstenberg et al.CSCW 2023 · 362 citations
- Expanding Modes of Reflection in Design FuturingSandjar Kozubaev, Chris Elsden, Noura Howell, Marie Louise Juul Søndergaard et al.CHI 2020 · 171 citations
- Investigating AI Teammate Communication Strategies and Their Impact in Human-AI Teams for Effective TeamworkRui Zhang, Wen Duan, Christopher Flathmann, Nathan J. McNeese et al.CSCW 2023 · 98 citations
- Understanding the Effect of Counterfactual Explanations on Trust and Reliance on AI for Human-AI Collaborative Clinical Decision MakingMin Hun Lee, Chong Jun ChewCSCW 2023 · 74 citations
Related papers
- Exploring the Future of AI in Clinical Collaboration: A Study on Tumor Board Case PreparationJiachen Li, Amanda K. Hall, Ruican Rachel Zhong, Selin S. Everett et al.CHI 2026 · 1 citation
- Multimodal Healthcare AI: Identifying and Designing Clinically Relevant Vision-Language Applications for RadiologyNur Yildirim, Hannah Richardson, Maria Teodora Wetscherek, Junaid Bajwa et al.CHI 2024 · 81 citations
- Current and Future Use of Large Language Models for Knowledge WorkMichelle Brachman, Amina H. El-Ashry, Casey Dugan, Werner GeyerCSCW 2025 · 10 citations
- CliCARE: Grounding Large Language Models in Clinical Guidelines for Decision Support over Longitudinal Cancer Electronic Health RecordsDongchen Li, Jitao Liang, Wei Li, Xiaoyu Wang et al.AAAI 2026 · 1 citation
- Human-Algorithmic Interaction Using a Large Language Model-Augmented Artificial Intelligence Clinical Decision Support SystemNiroop Channa Rajashekar, Yeo Eun Shin, Yuan Pu, Sunny Chung et al.CHI 2024 · 85 citations
