Suchi Saria, Ph.D., M.Sc.

  • Joint Appointment in Medicine

Research Interests

Big data analytics; Machine learning; Informatics; Patient safety and quality; Multimorbidity; mHealth; Predictive modeling; ICU informatics ...read more

Background

Dr. Suchi Saria holds a joint appointment in health system informatics at the Johns Hopkins University School of Medicine. She is also an assistant professor of computer science at the Whitings School of Engineering and of health policy and management at the Bloomberg School of Public Health.

Her research focuses on machine learning and computational statistics, and their applications to domains where one has to draw inferences from observing a complex, real-world system evolve over time. Her lab has been recognized by the National Science Foundation for its work in modeling complex, chronic diseases such as scleroderma. 

She is currently engaged in Bayesian and probabilistic graphical modeling approaches for addressing challenges associated with modeling and prediction in real-world temporal systems. In the last seven years, she has been particularly drawn to problems that involve modeling data from sensing platforms and electronic health records.

Dr. Saria received her undergraduate degree from Mt. Holyoke College. She earned her M.Sc. and Ph.D. from Stanford University. She completed an NSF Communication Innovation fellowship at Harvard University. Dr. Saria joined the Johns Hopkins faculty in 2012.

Her work has been recognized with two Hopkins Discovery Awards, a National Science Foundation Smart and Connected Health Research Grant, a Google Research Award, an Annual Scientific Award from the Society of Critical Care, and a Betty and Gordon Moore Research Award.

...read more

Education

Degrees

  • B.A.; Mount Holyoke College (Massachusetts) (2004)
  • M.Sc.; Stanford University (California) (2008)
  • Ph.D.; Stanford University (California) (2011)

Research & Publications

Research Summary

Dr. Saria’s research interests span machine learning and computational statistics, and their applications to domains where one has to draw inferences from observing a complex, real-world system evolve over time. 

The emphasis of her research is on Bayesian and probabilistic graphical modeling approaches for addressing challenges associated with modeling and prediction in real-world temporal systems. In the last seven years, she has been particularly drawn to computational solutions for problems in health informatics, as she sees a tremendous opportunity there for high impact work.

Selected Publications

Schulam P, Saria S. “Latent disease trajectory model for individualizing prognoses in complex chronic diseases.” J Mach Learn Res. Forthcoming. 

Chisholm KM, Heerema-Mckenney A, Tian L, Rajani AK, Saria S, Koller D, Penn AA. “Correlation of preterm infant illness severity with placental histology.” Placenta. 2016 Mar 1;(39):61-69.

Robinson D, Saria S. “Trading-off cost of deployment versus accuracy in learning predictive models.” International Joint Conference of Artificial Intelligence (IJCAI). 2016.

Dyagilev K, Saria S. “Learning (predictive) risk scores in the presence of censoring due to interventions.” Mach Learn. 2016 Mar;102(2):323-48.

Henry, KE, Hager, DN, Pronovost, PJ, Saria S. “A targeted real-time early warning score (TREWScore) for septic shock.” Sci TM. 2015 Aug;7: 299, 299ra122.

Saria S, Goldenberg A. “Subtyping: What it is and its role in precision medicine.” IEEE Intell Syst. 2015 Jul/Aug;30(4):70-75.

Academic Affiliations & Courses

Courses and Syllabi

  • Machine Learning: Data to Models (600.476/676)
    Johns Hopkins University
    2015
  • Machine Learning in Complex Domains (600.476/676)
    Johns Hopkins University
    2013

Activities & Honors

Honors

  • Early Career Spotlight, International Joint Conference on Artificial Intelligence (IJCAI), 2016
  • AI’s 10 to Watch, IEEE Intelligent Systems, 2015 - 2016
  • Discovery Award, Johns Hopkins University (two awards), 2015
  • Smart and Connected Health Research Grant Award, National Science Foundation, 2014
  • Google Research Award, Google, 2014
  • Annual Scientific Award, Society of Critical Care, 2014
  • Research Award, Betty and Gordon Moore Foundation, 2013
  • Computing Innovation Fellowship, National Science Foundation, 2011
  • Best Paper Finalist, American Medical Informatics Association, 2010
  • Best Student Paper, Association for Uncertainty in Artificial Intelligence, 2007
  • Rambus Corporation Fellowship, Stanford University, 2004 - 2009
  • Full Scholarship, Microsoft, 2002 - 2003

Videos & Media

Recent News Articles and Media Coverage

  • “Hopkins Looks to Code to Identify a ‘Major and Unappreciated’ Health Problem,” Baltimore Sun, Aug. 7, 2015
  • “Predictive Model Identifies Patients Who Might Go into Septic Shock,” Popular Science, Aug. 5, 2015
  • “New Model Predicts Complications in Preemies,” Science, Sept. 28, 2010
Is this you? Edit Profile
back to top button