Integrating AI in healthcare requires effective interdisciplinary collaboration, yet challenges like methodological differences, terminology barriers, and divergent objectives persist. To address the issues, we introduce MedAI-SciTS, a structured approach combining a theoretical framework and a toolkit to improve collaboration across disciplines. The framework builds on a formative study (N=12) and literature review, identifying the key challenges and potential solutions in medical-AI projects. We further develop an innovative toolkit with twelve tools, featuring an AI-enhanced research glossary with personalized analogies, an agile co-design platform, and an integrated resource management system. A three-month case study involving AI and medical professionals (N=16 total) applying a segmentation algorithm for adrenal CT images confirmed the toolkit’s effectiveness in enhancing team engagement, communication, trust, and collaboration outcomes. We envision MedAI-SciTS could potentially be applied to a wide range of medical applications and facilitate broader medical-AI collaboration.
https://dl.acm.org/doi/10.1145/3706598.3713926
The ACM CHI Conference on Human Factors in Computing Systems (https://chi2025.acm.org/)