2019 Annual Meeting
The MIT Critical Data Consortium is a unique organization engaging in advancing health data analytics research through interdisciplinary industry-academic collaboration. This association of scientist, clinician, and industry leaders are devoted to building and curating uniquely powerful open health datasets, accelerating the discovery of novel machine learning models and applications focused on quality improvements in health outcomes.
The Laboratory for Computational Physiology is organizing our inaugural MIT Critical Data Consortium Meeting, to be held on April 24, 2019. This one day event will bring together all participating Consortium Members and LCP research partners and affiliates who are engaged in building health datasets and/or performing health data analysis. During this meeting, we will present recent laboratory developments and discuss plans for the upcoming year.
Date: April 24, 2019
Time: 9:00 am - 5:30 PM
Location: MIT, Building E25
|9:00||Roger Mark||Welcome Remarks: How We Got Here; Where Are We Going?|
Dr. Mark is Distinguished Professor of Health Sciences and Technology in IMES and EECS at MIT. He received his PhD in electrical engineering from MIT and his MD 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 quantitative physiology to undergraduate and graduate engineering students at MIT, and Introduction to Clinical Medicine to HST PhD students. Dr. Mark’s research activities focus on physiological signal processing and database development, cardiovascular modeling, critical care decision support and predictive modeling. His group launched “PhysioNet” in 1999 to provide open access to major collections of well-characterized physiologic and clinical data and associated analytical software. His laboratory’s project, “Critical Care Informatics,” is focused on transforming massive archives of critical care clinical data into new knowledge that will improve the efficiency, accuracy, and timeliness of clinical decision making in intensive care. Dr. Mark’s own research has depended critically on access to physiologic and clinical data, and he is firmly committed to the importance of making such data freely available to the research community.
|9:20||Leo Celi||MIT Critical Data, MIMIC-Global, and Ophthalmology|
Dr. 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).
|9:40||Thomas Heldt||Epidemiology and Management of NICU Monitoring Alarms|
Thomas Heldt is the W.M. Keck Career Development Professor in Biomedical Engineering at MIT. He is a core faculty member with MIT's Institute for Medical Engineering and Science and an Associate Professor of Electrical and Biomedical Engineering in the Department of Electrical Engineering and Computer Science. His research interests focus on signal processing, mathematical modeling, and model identification to support real-time clinical decision making, monitoring of disease progression, and titration of therapy, primarily in neurocritical and neonatal critical care. His research is conducted in close collaboration with colleagues at MIT and clinicians from Boston-area hospitals.
|10:00||Steve Horng||BIDMC ED Data and CXRs|
Dr. Horng is dual board-certified in emergency medicine and clinical informatics with degrees in computer science and biomedical informatics. He specializes in translational clinical informatics and focuses his research on novel methods of artificial intelligence to improve the quality and efficiency of emergency care. Specifically, he works on applying state-of-the-art machine learning methods to implement automated information retrieval and targeted decision support at the bedside.
Alistair joined the Laboratory for Computational Physiology in 2015 and is currently a full time Research Scientist. He received his B.Eng in Biomedical and Electrical Engineering at McMaster University, Canada, and subsequently read for a D.Phil in Healthcare Innovation at the University of Oxford. His thesis was titled "Mortality and acuity assessment in critical care", and its focus included using machine learning techniques to predict mortality and develop new severity of illness scores for patients admitted to intensive care units. Before joining the LCP, Alistair spent a year as a research assistant at the John Radcliffe hospital in Oxford, where he worked on building early alerting models for patients post-ICU discharge. He has extensive experience and expertise in working with ICU data, and in building decision support tools for critically ill patients. He is actively engaged in research investigations with clinical colleagues. He has worked extensively on creating and releasing the Medical Information Mart for Intensive Care (MIMIC)-III and eICU databases, and in actively supporting its user community.
Omar Badawi, PharmD, MPH, FCCM is the Head of Health Data Science and AI in the Philips Patient Care Analytics business and leads the research for developing and validating product-related predictive algorithms and decision support tools. He is also an Adjunct Assistant Professor with the University of Maryland School of Pharmacy and Research Affiliate at the Massachusetts Institute of Technology. He earned a Master in Public Health degree with a focus in Epidemiology and Biostatistics from The Johns Hopkins Bloomberg School of Public Health and is currently the Program Manager for the Philips eICU Research Institute which supports collaborative research between industry, academia and clinicians using de-identified clinical data representing over 6 million ICU patients. Dr. Badawi is also a Fellow of the American College of Critical Care Medicine.
|11:10||Joe Frassica||Data Sharing & Large Datasets|
Joseph Frassica, MD, is Head of Philips Research, Americas and Chief Medical Officer, Royal Philips North America where he is focused on leading a broad-based medical, science and technology team to bring clinically meaningful innovation to the bedside. In addition, Joe also serves as Senior Consultant in Pediatric Critical Care at the Massachusetts General Hospital, Research Affiliate at the Massachusetts Institute of Technology and Pediatric Editor for the Journal of Intensive Care Medicine.
|11:20||Minnan Xu||Philips Research Acute Care Analytics|
Dr. Minnan Xu is a principal scientist and group leader at Philips Research North America. She leads a team working on analytics and applying machine learning to address unmet needs in acute are settings. She has research experience working with large clinical databases and developing predictive models for adult and pediatric critical care. As an scientist in industry, she works closely with clinicians, academic researchers, and Philips business partners to bring data driven solutions to the bedside in order to help clinicians improve clinical outcomes.
|12:00||Lunch Break||Parallel Session in E25-101: Steering Committee Meeting||E25-119|
Tom earned his PhD in biomedical engineering at University College London and University College London Hospitals (UCLH) where he obtained focused experience in the intensive care environment and computational modelling of patient physiology. He is currently a full time Research Scientist at MIT. He is expert in the development, support, and analysis of critical care databases, including MIMIC and the recently released eICU Collaborative Research Database. He conducts retrospective studies in collaboration with clinical specialists, develops and supports critical care databases that are widely used around the world in research and education, and he has created software used by hundreds of researchers and students internationally. Tom has a broad interest in how we can improve the way that critical care data is managed, shared, and analyzed for the benefit of patients. He is a Fellow of the Software Sustainability Institute.
|13:30||Marianne Slight||Datathons and Online Courses|
Marianne Slight leads Cloud Healthcare Analytics at Google. Her focus is applying scalable analytical technologies to healthcare problems, creating healthcare products with artificial intelligence. Prior to Google, she led healthcare NLP products at Nuance, perioperative and critical care products at Picis and then Optum, and analytic solutions at Oracle.
|14:00||Donny Cheung||Google: Recent Work and Plans for Use of MIMIC|
Donny is a senior software engineer on the Google Cloud Healthcare & Life Sciences team and leads the Healthcare Analytics Platform engineering team. Previously, he worked in Google's Display Ads team, building global-scale machine learning applications to improve the quality and relevance of users' display ad experiences. Prior to Google, he worked as a senior scientist at a Toronto-based medical device startup, focusing on medical imaging device design and image reconstruction algorithms. Donny holds a PhD in Mathematics from the University of Waterloo and held a postdoctoral fellowship at the University of Calgary in the Quantum Information Science group.
|14:30||Chaitanya Shivade||IBM: Deep Neural Networks and The Struggles with Clinical Texts|
Dr. Shivade is a member of the Medical Imaging Solutions Group interested in applying machine learning techniques to solve problems in clinical data. He graduated with a PhD in Computer Science and Engineering from The Ohio State University. At IBM Research, his work has focused on language inference, question answering, and patient summarization.
|15:10||Cindy Wang & Prescott Klassen||Automated Analysis of Chest XRays and Reports|
Prescott Klassen, PhD, is a Senior Research Scientist at Philips Research North America in Cambridge, MA. His current work at PRNA is focused on natural language processing for applied tasks in clinical informatics. Xin (Cindy) Wang, PhD, is a Senior Scientist at Philips Research North America. Her current research focuses on applying deep learning in medical imaging informatics.
|15:30||Jesse Raffa||The Global Open Source Severity for Illness Score (GOSSIS)|
Dr. Jesse Raffa, PhD, is a biostatistician Research Scientist at MIT and provides statistical and epidemiological expertise to the group. His primary area of interest in methodological research has been the analysis of complex longitudinal data, in particular using different types of latent variable structures. This is highly relevant in the critical care setting, where most data is both longitudinal and complex in nature. He provides study design and analytical support for LCP’s clinical collaborations both as a consultant and data analyst.
|15:50||Student Presentations||Research Projects from HST.953 and Datathons|
|17:30||Networking Reception||Light refreshments will be served|