77 Massachusetts Ave.
Cambridge, MA 02139
Sana Research Lab:
Medical Information Mart for Intensive Care:
- MPH in Clinical Effectiveness, Harvard University School of Public Health, 2010
- MSc in Biomedical Informatics, MIT, 2009
- MD in Medicine, University of the Philippines, 1990
Leo Anthony Celi has practiced medicine in three continents, giving him broad perspectives in healthcare delivery. As clinical research director and principal research scientist at the MIT Laboratory of Computational Physiology (LCP), he brings together clinicians and data scientists to support research using data routinely collected in the intensive care unit (ICU). His group built and maintains the Medical Information Mart for Intensive Care (MIMIC) database. This public-access database has been meticulously de-identified and is freely shared online with the research community. It is an unparalleled research resource; over 2000 investigators from more than 30 countries have free access to the clinical data under a data use agreement. In 2016, LCP partnered with Philips eICU Research Institute to host the eICU database with more than 2 million ICU patients admitted across the United States. The goal is to scale the database globally and build an international collaborative research community around health data analytics.
Leo founded and co-directs Sana, a cross-disciplinary organization based at the Institute for Medical Engineering and Science at MIT, whose objective is to leverage information technology to improve health outcomes in low- and middle-income countries. At its core is an open-source mobile tele-health platform that allows for capture, transmission and archiving of complex medical data (e.g. images, videos, physiologic signals such as ECG, EEG and oto-acoustic emission responses), in addition to patient demographic and clinical information. Sana is the inaugural recipient of both the mHealth (Mobile Health) Alliance Award from the United Nations Foundation and the Wireless Innovation Award from the Vodafone Foundation in 2010. The software has since been implemented around the globe including India, Kenya, Lebanon, Haiti, Mongolia, Uganda, Brazil, Ethiopia, Argentina, and South Africa.
He is one of the course directors for HST.936—global health informatics to improve quality of care, and HST.953—secondary analysis of electronic health records, both at MIT. He is an editor of the textbook for each course, both released under an open access license. The textbook Secondary Analysis of Electronic Health Records came out in October 2016 and was downloaded over 48,000 times in the first two months of publication. The course “Global Health Informatics to Improve Quality of Care” was launched under MITx in February 2017.
Leo was featured as a designer in the Smithsonian Museum National Design Triennial “Why Design Now?” held at the Cooper-Hewitt Museum in New York City in 2010 for his work in global health informatics. He was also selected as one of 12 external reviewers for the National Academy of Medicine 2014 report “Investing in Global Health Systems: Sustaining gains, transforming lives”.
As a practicing intensivist, I deal with uncertainties and unanswered clinical questions all the time. One example of a difficult decision involved the resumption of anticoagulation in a patient with two mechanical heart valves who was recovering from endocarditis complicated by brain abscesses. The ICU team consulted local experts as well as the literature to guide them in weighing the risk and benefits of re-initiating anticoagulation given the patient’s age, co-morbidities, the specific bacteria involved, the number of mechanical valves, the extent and current status of the infection, etc. The information resources so accessed provided only general recommendations that were obviously not tailored to the patient’s demographics and co-morbidities, nor to the specifics of the clinical context. The majority of these recommendations were based on expert opinions or small clinical trials, and not on ‘gold-standard’, multi-center randomized controlled studies. The decision was made to re-start anticoagulation cautiously given the patient’s clinical stability, the absence of bleeding complications during the acute phase, and the lack of any planned surgical intervention. In fact, preparations were underway for discharge to a skilled nursing facility. Four days after re-initiation of anticoagulation, the patient suffered from a massive hemorrhage of one of the brain abscesses, prompting emergent hemicraniectomy. What if I had access to a database of patient records that could predict the harms and benefits of anticoagulation for such a complicated patient based on similar patients? Could I feed that database into an information system that provides the most likely outcome associated with each test and treatment option—for every type of patient, and for every clinical context—to review in real time?
As clinical research director of the Laboratory of Computational Physiology, I bring together clinicians and data scientists to support research using data routinely collected in the ICU. The collaboration has numerous benefits. The data scientists are involved in projects with immediate impact by addressing information gaps in clinical practice. The frontline clinicians are provided an opportunity to contribute to knowledge discovery. Clinicians at the frontline of care should be at the core of this dynamic learning system, fully supported by engineers to collaborate on the daily translation of questions into strategies for database interrogation, modeling and analysis. This learning system will engender a medical culture in which clinicians and engineers work together in a mutually supportive environment where cross-specialty communication is not only possible but intrinsic and continuous. My vision is for the development of a care system consisting of “clinical informatics without walls”, in which the creation of evidence and clinical decision support tools is initiated, updated, honed, and enhanced by crowd sourcing. In this collaborative medical culture, knowledge generation would become routine and fully integrated into the clinical workflow. This system would employ individual data to benefit the care of populations and population data to benefit the care of individuals.
- Mobile Health University Challenge, 1st place, MIT-Universidades Federal do Rio Grande do Norte team (Faculty Adviser: Leo Anthony Celi), Global System for Mobile Communications, 2012
- Auditory Research Grant Awardee, Capita Foundation, 2011
- Gawad Lagablab Awardee, Most Outstanding Alumni (Medicine), Philippine Science High School National Alumni Association, 2011
- Finalist, INDEX: Award 2011, Design to Improve Life, for Sana (Project Lead: Leo Anthony Celi) 60 finalists out of 966 entries from 78 countries; Danish Enterprise and Construction Authority, The Danish Ministry of Economic and Business Affairs, Den Obelske Familiefond, Konsul George Jorck og Hustru Emma Jorck’s Fond, Holger Petersens Fond, the Lauritzen Foundation and The Confederation of Danish Industry, 2011
- Featured Designer, National Design Triennial “Why Design Now?”, Cooper-Hewitt National Design Museum, Smithsonian Museum, 2010
- Information Technology Award, Massachusetts Medical Society, 2010
- Wireless Innovation Prize, 3rd Place, for Sana (Project Lead: Leo Anthony Celi), Vodafone Americas Foundation, 2010
- mHealth Alliance Award, for Sana (Project Lead: Leo Anthony Celi), United Nations Foundation, 2010
- L. A. Celi, D. J. Stone, R. A. Montgomery, R. G. Mark. “‘Big Data’ in the ICU: Closing the data loop.” AJRCCM 87.11 (2013): 1157-60.
- M. Ghassemi, J. Marshall, N. Singh, D. Stone, L. A. Celi. “Leveraging a critical care database: SSRI use prior to ICU admission is associated with increased hospital mortality.” Chest 145.4 (2014): 745-52.
- M. M. Ghassemi, S. E. Richter, I. M. Eche, T. W. Chen, J. Danziger, L. A. Celi. “A data-driven approach to optimized medication dosing: A focus on heparin.” Intensive Care Med 40.9 (2014): 1332-9.
- L. A. Celi, on behalf of the Organizing Committee, MIT Critical Data Conference and Datathon. “Making Big Data Useful for Health Care: A summary of the Inaugural MIT Critical Data Conference.” JMIR Med Inform 2.2 (2014): e22.
- L. A. Celi, et al. on behalf of MIT Critical Data. “A datathon model to support cross-disciplinary collaboration.” Sci Transl Med 8.333 (2016): 333ps8.
Global Health Informatics
- K. Byamba, S. Syed-Abdul, M. García-Romero, C. W. Huang, S. Nergyi, A. Nyamdorj, P. Nguyen, U. Iqbal, K. Paik, L. Celi, V. Nikore, M. Somai, W. S. Jian, Y. C. Li. “Mobile teledermatology for a prompter and more efficient dermatological care in rural Mongolia.” Br J Dermatol 173.1 (2014): 265-7.
- R. Wyber, S. Vaillancourt, W. Perry, P. Mannava, T. Folaranmi, L. A. Celi. “Big data in global health: the promise of data-informed health care delivery for low- and middle-income countries.” Bull World Health Organ 93.3 (2015): 203-8.
- J. DePasse, L. A. Celi. “Collaboration, capacity building and co-creation as a new mantra in global health.” Int J Qual Health Care 28.4 (2016): 536-7.
- L. A. Celi, et al. on behalf of the MIT Sana Global Team. “The hackathon model to spur innovation around global mHealth.” J Med Eng Technol 40.7-8 (2016): 392-9.
A full list of Dr. Celi’s publications can be found on Pubmed.