The Johns Hopkins Individualized Health Initiative (Hopkins inHealth) is a University-wide, collaborative venture to bring advances in statistical science and machine learning to healthcare. Our mission is to: discover new ways to more precisely define, measure, and communicate each person’s unique health state and the trajectory along which it is changing; develop these discoveries into new methods that can be used to better inform patients and their clinicians, resulting in better medical care decisions and improved health outcomes; and apply new knowledge gained from the delivery of individualized care to produce better health outcomes at more affordable costs for whole populations.
As part of this unique initiative, we are seeking applicants for multiple 2-year postdoctoral and research scientist positions. Researchers will have the opportunity to gain broad exposure to topics in statistical science and machine learning and their applications to healthcare through regular interactions with other faculty and fellows within inHealth, and across their home departments of biostatistics and computer science. Both Johns Hopkins and All Children’s Hospital provide highly supportive and dynamic environments for junior investigators to grow and develop their future career.
Example projects include:
Applications are also welcomed from applicants interested in exploring other areas of methodological research in the intersection of machine learning, Bayesian analysis, causal inference, and computational health.
Elizabeth (Betsy) Ogburn is an Assistant Professor of Biostatistics at the Johns Hopkins Bloomberg School of Public Health. She received her PhD in biostatistics from Harvard University, where she worked with Andrea Rotnitzky and Jamie Robins, followed by a postdoctoral fellowship with Tyler VanderWeele at the Harvard School of Public Health Program on Causal Inference. She works on developing statistical methodology for causal inference, with a focus on novel data sources and structures—for example, using electronic medical records to inform individual-level healthcare decisions and using social network and other data that evince complex dependence among observations. She collaborates with medical professionals, mathematicians, political scientists, and researchers across public health, and her research has received special recognition from a number of organizations, including the Journal of the Royal Statistical Society and the Atlantic Causal Inference Conference.
Suchi Saria is an Assistant Professor in Computer Science, with a joint appointment in the Institute of Computational Medicine at Johns Hopkins University. Her research focuses on developing machine learning and statistical inference methods for modeling temporal systems, especially in healthcare. In her work, she developed one of the first studies modeling health trajectories in infants from routinely collected electronic health data; this led to a novel non-invasive and accurate risk stratification score for measuring health at birth in preterm infants, a technology now licensed by one of the largest monitoring companies in Japan. Her works have received recognition in the form of best paper nominations at the Uncertainty in AI and the American Medical Informatics Association meetings, a cover article in Science Translational Medicine, a Gordon and Betty Foundation award, a Google Faculty research award, and a National Science Foundation Computing Innovation fellowship. She did her PhD with Daphne Koller from Stanford University, and her postdoctoral training with Ken Mandl and Zak Kohane at Harvard University.
Scott Zeger is a Professor of Biostatistics, and the Director of the Johns Hopkins Individualized Health Initiative. With his colleague Kung-Yee Liang, Dr. Zeger discovered the generalized estimating equation (GEE) approach to regression analysis for correlated responses as occur in longitudinal, time series, genetic and other studies. This work made Dr. Zeger one of the 10 most cited mathematical scientists over parts of the last two decades. With colleagues Diggle, Heagerty, and Liang, Zeger has written ’The analysis of Longitudinal Data’ published by the Oxford University Press.
For more than a century, Johns Hopkins has been recognized as a leader in medical research and teaching, with a history of successfully combining innovation at the forefront of engineering and medicine. You will have access to:
Baltimore is a thriving city with an expansive waterfront that is surprisingly affordable. The city also has a thriving art scene and a booming biotech and health tech industry. It is also connected to many of the east coast cities (e.g., Washington D.C, New York and Philadelphia) via cheap buses and high-speed rail.
Qualifications: The ideal applicant should have
How to Apply: Interested applicants should submit their curriculum vitae, selected paper(s), 2 references, and a brief cover letter summarizing background and interest via Academic Jobs Online. Applications will be considered until the position is filled. The Johns Hopkins University is an Affirmative Action / Equal Opportunity Employer. There are no citizenship restrictions for this position.