Reflections from Research Roundtables at the Conference on Health, Inference, and Learning (CHIL) 2025

2025-10-16

AI Summary

This study addresses core challenges impeding the clinical deployment of machine learning in healthcare: insufficient model interpretability, weak causal inference capabilities, poor generalization under small-sample regimes, shallow multimodal fusion, and inadequate modeling of fairness and uncertainty. To tackle these issues, the project pioneered a “senior–junior expert co-chairing” roundtable mechanism, organizing eight focused workshops on foundational topics including foundation model adaptation, domain adaptation, and multimodal learning—emphasizing inclusive dialogue and collective co-creation. The outcomes comprise actionable roadmaps spanning technical methodologies, evaluation frameworks, and cross-disciplinary collaboration protocols. These deliverables consolidate academic consensus, catalyze a clinically viable AI-in-healthcare research initiative, and foster an active collaborative network. Collectively, they advance systematic understanding of critical barriers and strengthen translational orientation across the field.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Security and privacy of machine learning and AI applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The 6th Annual Conference on Health, Inference, and Learning (CHIL 2025), hosted by the Association for Health Learning and Inference (AHLI), was held in person on June 25-27, 2025, at the University of California, Berkeley, in Berkeley, California, USA. As part of this year's program, we hosted Research Roundtables to catalyze collaborative, small-group dialogue around critical, timely topics at the intersection of machine learning and healthcare. Each roundtable was moderated by a team of senior and junior chairs who fostered open exchange, intellectual curiosity, and inclusive engagement. The sessions emphasized rigorous discussion of key challenges, exploration of emerging opportunities, and collective ideation toward actionable directions in the field. In total, eight roundtables were held by 19 roundtable chairs on topics of "Explainability, Interpretability, and Transparency," "Uncertainty, Bias, and Fairness," "Causality," "Domain Adaptation," "Foundation Models," "Learning from Small Medical Data," "Multimodal Methods," and "Scalable, Translational Healthcare Solutions."

Problem

• Addressing interpretability challenges in healthcare machine learning models
• Mitigating bias and uncertainty in medical AI systems
• Developing scalable solutions for limited medical data scenarios

Innovation

• Roundtables discussed machine learning healthcare challenges
• Sessions explored explainability fairness causality in medicine
• Dialogue addressed multimodal methods for small data