Our research focuses on the regulatory science of FDA-regulated products, those overseen by the Office of the National Coordinator for Health Information Technology (ONC), and advancements in artificial intelligence and machine learning. We conduct research that explores the development and evaluation of regulatory frameworks to ensure the safe and effective use of digital health technologies, including AI and machine learning-based tools. This includes studying the complexities of medical device approvals, assessing compliance with evolving ONC standards, and addressing the unique challenges posed by AI and machine learning in healthcare. Our goal is to advance regulatory science in a way that fosters innovation while maintaining a strong focus on patient safety and public trust.
Projects
In a collaboration of CHIP faculty and fellows, we are using machine learning and NLP techniques to develop tools to support FDA activities around novel device evaluation and postmarketing safety monitoring. This work has led to high impact publications evaluating device safety reporting systems and assessments of the approval and clinical use of cardiac devices in pediatric populations. We have also created large manually-labeled datasets that can be used as evaluation benchmarks and for the development of more advanced methods that will support important downstream tasks around device regulation.
The Pediatrics Therapeutics and Regulatory Science Initiative (PedRx) provides a forum for collaboration with academia, patients, policymakers, and industry.
CHIP has been instrumental in shaping the 21st Century Cures Act to include requirements for the API technology it developed, ensuring that federally mandated interoperability aligns with the cutting-edge solutions CHIP pioneered. It has also engaged directly with regulators, contributing valuable insights and technical expertise that helped inform the final rulemaking process led by the Office of the National Coordinator for Health Information Technology (ONC). This collaborative work with policymakers ensured that the resulting Health Data, Technology, and Interoperability – Certification Program Updates, Algorithm Transparency, and Information Sharing (HTI-1) rule reflected both the needs of patients and the practical realities of health information exchange, ultimately setting the stage for a more interconnected, data-driven healthcare environment.