LCP personnel and collaborators

Research in the Laboratory for Computational Physiology takes place both in the lab itself and through collaborations with other researchers elsewhere on campus. LCP researchers and principal collaborators are listed below.

[Roger Mark photo] Roger Mark

Dr. Mark is Distinguished Professor of Health Sciences and Technology, and Professor of Electrical Engineering at MIT. He received the SB and PhD degrees in EE from MIT, and the MD degree from Harvard Medical School. He trained in internal medicine at the Harvard Medical Unit at Boston City Hospital, and then spent two years in the Medical Corps of the USAF studying the biological effects of laser radiation. He joined the faculty of the EE Department at MIT in 1969, and also the faculty of the Department of Medicine at Harvard Medical School. He has been active in teaching cardiovascular pathophysiology to HST students, and quantitative physiology to undergraduate biomedical engineering students at MIT. Dr. Mark is a fellow of the IEEE, a fellow of the American College of Cardiology, and a founding fellow of the American Institute of Medical and Biological Engineering. He remains active in the practice of primary care internal medicine and geriatrics for about 20% of his time, and is Senior Physician at the Beth Israel Deaconess Medical Center.

Dr. Mark’s research activities include physiological signal processing and database development, cardiovascular modeling, and intelligent patient monitoring. Finally, Dr. Mark is investigating techniques to utilize the enormous volumes of clinical and physiologic data generated by patients in intensive care units in order to track and possibly predict their pathophysiological state. The techniques being explored include multi-parameter real-time signal processing, system identification and modeling, and expert systems. The goal is to solve the problem of information overload in the ICU, improve clinician-machine interface, decrease false alarm rates, and support clinical decision-making.

[Thomas Brennan photo] Thomas Brennan

With a background in electrical and computer engineering, Thomas Brennan was awarded the Rhodes Scholarship from South Africa in 2004. In 2009 he completed his D.Phil. in Biomedical Engineering from the University of Oxford. He then worked for the Vodafone Foundation developing a mobile-based platform to monitor and support community health workers in South Africa. In 2010, he accepted a Wellcome Trust post-doctoral research fellowship at the Institute of Biomedical Engineering in Oxford to develop and assess mobile health solutions for monitoring chronic disease in resource-constrained settings. He has over 10 years experience in cardiac modeling and biomedical signal processing, with a special focus on machine learning.

[Leo Celi photo] Leo Celi

Leo moved to the US from the Philippines after medical school to pursue specialty training in internal medicine (Cleveland Clinic), infectious diseases (Harvard) and critical care medicine (Stanford). He has practiced medicine in three continents (Philippines, US and New Zealand) and has worked in both industry (Philips Visicu) and academe (faculty positions at Harvard, MIT, Stanford and University of Otago), rendering him with broad perspectives in healthcare delivery. He has a strong interest in systems re-design for quality improvement, and became the New Zealand representative to the Quality and Safety Committee of the Australia New Zealand Intensive Care Society in 2006. Feeling he needed more skills to tackle the healthcare inefficiencies he faced wherever he practiced, he went back to the US to pursue graduate studies in biomedical informatics at MIT and public health at Harvard. While attending both schools and working part-time as an emergency department physician, he co-founded Sana, personally recruiting most of the current members, and was instrumental in shaping the mission and vision of the young organization.

His other research interest is in data mining and the application of machine learning on large databases. As a research scientist at the Laboratory of Computational Physiology at MIT, he works with MIMIC, a publicly-available de-identified ICU database from BIDMC. He is working on a data-driven decision support system known as Collective Experience that (1) allows a clinician to draw on the experience of other clinicians who have taken care of similar patients as recorded in a clinical database, and (2) uses models performed on relatively homogeneous patient subsets.

[Mengling Feng photo] Mengling Feng

Dr. Mengling Feng (http://web.mit.edu/mfeng/www/) obtained both his Bachelor and PhD degrees from School of Electronic and Electrical Engineering, Nanyang Technological University. Under the supervision of Prof. Limsoon Wong (School of Computing, NUS) and Prof. Yap-Peng Tan (School of EEE, NTU), Dr. Feng’s PhD study focused on developing data mining methods to discover meaningful knowledge that impacts real life practices. Before his current affliction at MIT, Dr. Feng joined the Data Analytic Department of Institute for Infocomm Research (I2R) as a research scientist. Dr. Feng was awarded the Ministry of Education Scholarship for his undergraduate studies and the A*STAR Graduate Scholarship for his PhD study. His work was also recognized with the “Bi-annual Best Paper Award” from the Institute for Infocomm Research. Dr. Feng’s research focus is to develop data mining and machine learning methods to discover or infer casual phenomenon among real-life practice and strategic planning.

[Li-wei Lehman photo] Li-wei Lehman

Dr. Li-wei Lehman is a Research Engineer in the Laboratory for Computational Physiology (LCP) at the Harvard-MIT Division of Health Sciences and Technology. Her work focuses on the NIH-funded project Research Resource for Complex Physiologic Signals (PhysioNet), which is aimed to stimulate current research and new investigations in the study of complex biomedical and physiologic signals. Her research interests include searching, mining, and detection of physiologically significant events in biomedical databases. She is particularly interested in probabilistic modeling and inferencing algorithms on physiological and clinical data to identify patients with similar pathophysiologies, and to discover “hidden” information that may be predictive of disease progressions. Prior to joining the PhysioNet team, she worked on (and continues to be involved in) several projects in the research program, “Integrating Data, Models, and Reasoning in Critical Care” at LCP, including an annotation system, a pattern-matching de-identification system, and a temporal search engine for multi-parameter biomedical databases. She received her Master’s degree in Computer Science from Georgia Institute of Technology, and her Ph.D. in Information Systems and Technology from MIT in June 2005.

[George Moody photo] George Moody

George Moody is the architect, technical director, and webmaster of PhysioNet, and the author of its core open-source software, the WFDB software package. He has been continuously involved in the development of many of the data collections freely available on PhysioNet, beginning with the MIT-BIH Arrhythmia Database in the late 1970s. He led the design and implementation of the PhysioNet web site since its beginnings in 1999, including the annual PhysioNet/CinC Challenge series of open engineering competitions since 2000, and most recently the PhysioNetWorks facility for data sharing and collaboration.

George has invented a number of widely-used algorithms for physiologic signal processing, including the EDR (ECG-Derived Respiration) technique; a method for atrial fibrillation detection based on quasi-continuous Markov process-like models; ECG-based indices of physical activity; the TRIM (Turning-point/Recursive Improvement Method) algorithm, a widely-used ECG compression algorithm; and novel methods for robust estimation of principal components of continuous waveforms, such as QRS and ST waveforms in the ECG. He was also the first to apply the Lomb transformation of unevenly sampled data for power spectral density estimation of heart rate variability. In addition, he has designed and implemented many of the physiologic signal processing and analysis algorithms in regular use in our laboratory, including ARISTOTLE (a state-of-the-art arrhythmia detector that has been the nucleus of several successful commercial products) and WAVE (an extensible interactive graphical environment for exploratory data analysis of digital signals, in use by researchers worldwide). He contributed the methods for quantitative evaluation of ECG analysis algorithms, the reference implementations of those methods in software, and the descriptions of those methods contained in current ISO and American National Standards for automated ECG analysis (ANSI/AAMI EC38, EC57, and IEC 60601), while serving as a member of the AAMI ECG Committee and of its Ambulatory Monitoring Subcommittee, and as the chair of its Arrhythmia Monitoring Subcommittee. He has been a Director of Computing in Cardiology since 2002 and a member of its Editorial Board since 2006.

His research interests include robust methods in pattern recognition and power spectral density estimation; methods for assessment of signal quality and detection of events in weakly correlated multiparameter data; false alarm reduction in the ICU; methods for multivariate trend analysis and forecasting, with applications in intensive care; novel signal processing techniques for automated or semi-automated patient diagnosis; web-enabled signal processing, with applications in research and telemedicine; data mining algorithms for efficient searching in very long time series; automated arrhythmia and ischemia detection, artificial intelligence-based medical decision support; and heart rate variability.

[Ikaro Silva photo] Ikaro Silva

Dr. Ikaro Silva is a Research Engineer in the Laboratory for Computational Physiology (LCP) at the Harvard-MIT Division of Health Sciences and Technology. His research focuses on the NIH-funded project Research Resource for Complex Physiologic Signals (PhysioNet). Dr. Silva's research interests include adaptive filtering, statistical signal processing, detection & estimation theory, and non-stationary analysis. As part of the PhysioNet team, he is also interested on helping develop exciting biomedical signal processing challenges, improving the WFDB Toolbox, and strengthening PhysioNet's resources and community. He has worked at The MathWorks for two years before going for his Masters (2004) and Ph.D. (2009) in Computer and Electrical Engineering at Northeastern University, Boston, USA. Dr. Silva's Ph.D. thesis focused on objective estimation of loudness perception from evoked auditory responses conditioned on a non-stationary quality estimation metric (his complete Ph.D. data and references are publicly available through PhysioNet).

Collaborating researchers

Peter Szolovits
http://groups.csail.mit.edu/medg/people/psz/psz.html
George Verghese
http://eecsfacweb.mit.edu/facpages/verghese.html
Ary Goldberger
http://reylab.bidmc.harvard.edu/people/Ary.shtml