Li-wei Lehman is a research scientist in the Laboratory for Computational Physiology at MIT’s Institute for Medical Engineering and Science. Her research focuses on the use of machine learning to derive insights from physiological and clinical data for informed treatment decision making. Her 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. She is a member of the National Institutes of Health project, Research Resource for Complex Physiologic Signals. Lehman earned a MS in computer science from Georgia Institute of Technology, and a PhD from MIT.

Publications

• Shahn, Z., Shapiro, N. I., Tyler, P. D., Talmor, D., Lehman, L. H. (2020). Fluid-limiting treatment strategies among sepsis patients in the ICU: a retrospective causal analysis. Journal of Critical Care, 24:62.
• Tang, F., Xiao, C., Wang, F., Zhou, J., Lehman, L. H. (2019). Retaining Privileged Information for Multi-Task Learning. Proceedings of the 25th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Anchorage, Alaska.
• Lehman, E. P., Krishnan, R. G., Zhao, X., Mark, R. G., Lehman, L. H. (2018). Representation Learning Approaches to Detect False Arrhythmia Alarms from ECG Dynamics. Proceedings of the 3rd Machine Learning for Healthcare Conference, PMLR 85:571-586.
• Lehman, L. H., Mark, R. G., Nemati, S. (2018). A Model-Based Machine Learning Approach to Probing Autonomic Regulation from Nonstationary Vital-Sign Time Series. IEEE Journal of Biomedical and Health Informatics, Vol. 22, No. 1.

Media

• June 27, 2016: IMES News, Supporting clinical research with the MIMIC-III Critical Care Database.

• July 23, 2008: MIT News, A sensible censor for sharing medical records.