CAB's Core Faculty and collaborators represent a multidisciplinary team committed to developing a state-of-the-art program that fosters collaboration across the Harvard campus, external researchers, and industry experts.
Learn more about the Center's key strengths and goals.
CAB is built to respond to the need to test, evaluate, and implement trustworthy, unbiased, transparent, and accountable data quality and AI methods and technologies in population health settings using real world data. This includes innovative applications of Generative Artificial Intelligence (Gen AI) and Large Language Models (LLMs) as well as the use of these technologies to improve research efficiency and impact. As an academic institution, it will offer training and education for students, fellows, and faculty to nurture the future leaders in healthcare and technology who share our values.
The Center is uniquely equipped to:
Proactively engage with emerging technologies to ensure data integrity, promote data sharing, and facilitate collaborative research efforts across diverse healthcare settings.
Analyze and link data from electronic health records, nonmedical drivers of health, wearables, patient reported outcomes, and other new sources.
Conduct systematic research and evaluation to improve methods to ensure quality of data that supports high-caliber epidemiological, clinical, policy, and social research in population health, mental health, cancer care, maternal and child health issues, chronic disease management, and health services research.
Innovations in Gen AI and LLMs in centralized or federated data networks offer unprecedented opportunities for data analysis, predictive modeling, and knowledge extraction. CAB will conduct the testing and validation required to adopt these technologies in healthcare in real world settings with a focus on equity, accuracy, generalizability, and privacy.
CAB recognizes and emphasizes the close linkage between the informatics innovations required to access reliable, comprehensive, high quality, and timely health data and the concerns about fairness, accountability, validity, and effectiveness of Gen AI and LLM methods. Similarly, AI applications can improve health data quality and help with anomaly detection systems, feedback loop mechanisms, and unstructured data analysis. CAB faculty expertise in these areas is a unique asset to working with industry, health systems, and communities to develop, test, implement, and evaluate AI applications and health informatics innovations that hold great promise to improve health outcomes and equity.