Santiago Romero-Brufau

Santiago Romero-Brufau

Master’s of Science in Health Data Science Candidate at the Harvard T.H. Chan School of Public Health
Assistant Professor in Medicine and in Healthcare Systems Engineering at Mayo Clinic
santiago

Santiago Romero-Brufau is an M.D. with a Ph.D. in Clinical Informatics and an engineering background, currently enrolled in the Master’s of Science in Health Data Science at the Harvard T.H. Chan School of Public Health. He is also an Assistant Professor in Medicine and in Healthcare Systems Engineering at Mayo Clinic and has been a guest lecturer at the University of Verona, University of Barcelona, and the St. James’ Hospital at Trinity College Dublin, among others.
 

Dr. Romero-Brufau’s main area of interest is in the development of clinical decision support tools using machine learning and the implementation of those tools into the clinical practice. For example, he developed a predictive model for early identification of clinical deterioration in hospitalized patients and implemented the model as part of an alert system at Mayo Clinic, resulting in significant reductions to response times. While at Mayo Clinic he has also worked on the implementation of triaging algorithms to efficiently determine appropriate specialty appointments for ambiguous clinical conditions as well as new approaches to risk identification.
 

In collaboration with his mentor, Dr. Jeanne Huddleston, he has also consulted for several hospital systems to help them establish new systems and processes, like a mortality review or identification of admission risk. Further, he has been a co-investigator on an NSF-funded research grant focused on identification and optimal management of sepsis using engineering principles. Several of his developments have also been licensed to Mayo Clinic’s industry partners.


More recently, his research is focused on the use of social determinants of health in the context of clinical decision support. Dr. Romero-Brufau also has an interest in how to best combine information from data science methods and clinical expertise to best predict adverse clinical outcomes and intervene early to prevent them. During the program, he is hoping to improve his data science and machine-learning repertoire, specifically deep language and natural language processing; and to establish fruitful collaborations.

People Taxonomy