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.

Selected Publications

• Kassis, E.B., Hu, S., Lu, M., Johnson, A., Bose, S., Schaefer, M., Talmor, D., Lehman, L.W. Shahn, Z. (2022). Titration of Ventilator Settings to Target Driving Pressure and Mechanical Power. Respiratory Care.
• Li, R., Hu, S., Lu, M., Utsumi, Y., Chakraborty, P., M. Sow, D., Madan, P., Li, J., Ghalwash, M., Shahn, Z., Lehman, L.W. G-Net: a Recurrent Network Approach to G-Computation for Counterfactual Prediction Under a Dynamic Treatment Regime. Proceedings of Machine Learning for Health, PMLR 158:282-299, 2021.
• Shahn, Z., Lehman, L.W., Mark, R., Talmor, D., and Bose, S. Delaying initiation of diuretics in critically ill patients with recent vasopressor use and high positive fluid balance. British Journal of Anaesthesia, 127 (4): 569e576 (2021)

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.