Roger Mark
Distinguished Professor of Health Sciences and Technology, Harvard-MIT Division of Health Sciences and Technology; Professor, Department of Electrical Engineering and Computer Science

Categories
Roger Mark is the Distinguished Professor of Health Sciences and Technology in the Institute for Medical Engineering and Science (IMES), and the Harvard-MIT Division of Health Sciences and Technology. He is also a member of the Laboratory for Computational Physiology in IMES. His research focuses on physiological signal processing and database development, cardiovascular modeling, and critical care decision support and predictive modeling. His group launched the National Institutes of Health-supported “PhysioNet” to provide open access to major collections of physiologic signals and associated signal processing software. His NIH-funded project, Critical Care Informatics, is focused on transforming critical care clinical data into new knowledge that will improve the efficiency, accuracy, and timeliness of clinical decision making in intensive care. That project has developed a public ICU database (MIMIC), holding clinical data from about 60,000 ICU admissions. Now part of PhysioNet, MIMIC is currently used by more than 14,000 people worldwide. Mark’s own research depends on access to physiologic and clinical data, and he is committed to making this data available to researchers worldwide.
Mark is a fellow of the Institute of Electrical and Electronics Engineers, American College of Cardiology and American Institute of Medical and Biological Engineering. He earned a BS and a PhD in electrical engineering from MIT, and an MD from Harvard Medical School.
Publications
- Representation Learning Approaches to Detect False Arrhythmia Alarms from ECG Dynamics. Proc Mach Learn Res. Aug; 85:571-586.
- A Model-Based Machine Learning Approach to Probing Autonomic Regulation From Nonstationary Vital-Sign Time Series. IEEE J Biomed Health Inform. Jan; 22(1):56-66.
- Recent advances in heart sound analysis. Physiol Meas. Aug 1;38(8): E10-E25.
- Phenotyping Hypotensive Patients in Critical Care Using Hospital Discharge Summaries. IEEE EMBS Int Conf Biomed Health Inform. Feb: 401-404.
Media
- February 1, 2019: MIT News, MIMIC Chest X-Ray database to provide researchers access to over 350,000 patient radiographs.
- January 18, 2019: MIT News, Democratizing artificial intelligence in health care.
- July 20, 2018: MIT News, Doctors rely on more than just data for medical decision making.
- July 7, 2017: IMES News, Faculty Profile: Roger Mark.