Overview
The AIM-AHEAD (Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity) project focuses on developing and evaluating clinical decision support tools that complement—rather than replace—human expertise in healthcare settings.
Research Focus
Our work within AIM-AHEAD centers on:
Clinician-in-the-Loop AI
We study how AI tools can be designed to augment clinical decision-making while preserving clinician autonomy and expertise. This includes:
- Understanding how clinicians interact with AI recommendations
- Identifying factors that influence appropriate vs. inappropriate reliance on AI
- Designing interfaces that support calibrated trust in AI systems
Equity in Clinical AI
A core focus is ensuring that clinical AI tools work equitably across diverse patient populations:
- Evaluating algorithm performance across demographic groups
- Studying implementation factors that affect equity outcomes
- Developing methods for auditing clinical AI for bias
AugMed Platform
A key output of this project is AugMed, our open-source experimental platform for running behavioral experiments with healthcare providers. AugMed enables:
- Vignette-based clinical decision studies
- Randomized experiments on AI tool design
- Measurement of diagnostic accuracy and response times
- Studies of human-AI interaction in medical settings
Impact
This research informs the development of AI tools that are not only accurate but also usable, trustworthy, and equitable—ensuring that advances in clinical AI benefit all patients.
Related Publications
- Coming soon
Funding
This project is supported by the NIH AIM-AHEAD consortium, which aims to increase the participation and representation of researchers and communities currently underrepresented in AI/ML.