Li-wei Lehman

Research Scientist. massachusetts institute of technology
E25-505 · 77 Massachusetts Ave. · Cambridge, MA 02139 · LILEHMAN@MIT.EDU

I am a research scientist in the Institute for Medical Engineering & Science (IMES) at MIT. My research focuses on the use of machine learning to derive insights from physiological and clinical data for informed treatment decision making. My interests include representation learning, structure discovery, generative probabilistic models, switching state-space models, Bayesian non-parametric learning of disease phenotypes, and, more recently, off-policy reinforcement learning and causal inference. I received my Master’s degree in Computer Science from Georgia Institute of Technology, and my Ph.D. from Massachusetts Institute of Technology in June 2005.

Research/Post-doc position available: I am looking for a highly-motivated post-doc to join my research team.

Selected Publications

Switching State-Space Approaches for Modeling Physiological Dynamics

Representation Learning from Physiological and Clinical Data

Machine Learning for Informed Clinical Decision Making

  • "Evaluating Reinforcement Learning Algorithms in Observational Health Settings," Omer Gottesman, Fredrik Johansson, Joshua Meier, Jack Dent, Donghun Lee, Srivatsan Srinivasan, Linying Zhang, Yi Ding, David Wihl, Xuefeng Peng, Jiayu Yao, Isaac Lage, Christopher Mosch, Li-wei H. Lehman, Matthieu Komorowski, Aldo Faisal, Leo Anthony Celi, David Sontag, Finale Doshi-Velez,, 2018.
  • "Improving Sepsis Treatment Strategies by Combining Deep and Kernel-Based Reinforcement Learning," Xuefeng Peng, Yi Ding, David Wihl, Omer Gottesman, Matthieu Komorowski, Li-wei H. Lehman, Andrew Ross, Aldo Faisal, Finale Doshi-Velez, Proceedings of the AMIA Annual Symposium, 2018.
  • "Adherence to Individualized Fluid and Vasopressor Dosing Recommendation is Associated with Mortality Reduction in Sepsis: A Machine Learning Approach," Shamim Nemati, Matthew Stanley, Fereshteh Razmi, Timothy Buchman, Li-wei Lehman, presented at ICCAI, July 2017, abstract to appear in Journal of Critical Care.

Deriving Insights from Clinical Text: Bayesian Non-parametric Learning of Patient Phenotypes

Electronic Health Records and Medical Informatics

All Publications (By Year)










Honors and Professional Activities

  • Local organizing committee of the Computing in Cardiology Conference held in Boston, September 2014.

  • Member of the IEEE and the IEEE Engineering in Medicine and Biology Society.

  • Closing plenary presentation in the 2014 Computing in Cardiology Conference on “Uncovering Clinical Significance of Vital Sign Dynamics in Critical Care,” Boston, September 2014.

  • Closing plenary presentation in the 2010 Computers in Cardiology Conference on “Hypotension as a risk factor for acute kidney injury in ICU patients,” Belfast, September 2010.

  • Best poster presentation award, Computers in Cardiology Conference, September 2007.

  • Recipient of Schoettler Fellowship, awarded to outstanding incoming graduate students, MIT.

  • Appointed as Head TA for 1.00, Introduction to Computers and Engineering Problem Solving, an MIT course comprising 200 students and 18 student teaching staff, 2001.

  • MIT class awards: (1) algorithm & implementation in C++ won 2nd place in final project contest in MIT course 1.124; (2) voted one of the top 3 term papers in MIT course 6.853, Computer Systems.