Our lab is broadly interested in advancing machine learning and artificial intelligence, and using these to transform health care. We currently have three main focus areas:
Theoretical Machine Learning
We
research unsupervised learning, causal inference from
observational data, deep learning, time-series modeling,
approximate probabilistic inference, structured prediction, and semi-supervised learning
algorithms for natural language processing.- R. Krishnan, U. Shalit, D. Sontag. Structured Inference Networks for Nonlinear State Space Models, Thirty-First AAAI Conference on Artificial Intelligence, Feb. 2017. [code]
- F. Johansson, U. Shalit, D. Sontag. Learning Representations for Counterfactual Inference. 33rd International Conference on Machine Learning (ICML), June 2016.
- A. Globerson, T. Roughgarden, D. Sontag, C. Yildirim. How Hard is Inference for Structured Prediction? 32nd International Conference on Machine Learning (ICML), July 2015. arXiv [Slides]
- D. Sontag, T. Meltzer, A. Globerson, Y. Weiss, T. Jaakkola. Tightening LP Relaxations for MAP using Message Passing. Uncertainty in Artificial Intelligence (UAI) 24, July 2008. [code]
Precision Medicine
These are exciting times for the practice of medicine. The rapid adoption of electronic health records and has created a wealth of new data about patients, which is a goldmine for improving our understanding of human health. Our lab develops algorithms that use this data to better understand disease progression and to facilitate new, precise treatment strategies for a wide range of diseases and conditions such as Type 2 diabetes, which affects tens of millions of people worldwide every year, and multiple myeloma, a rare blood cancer. In pursuit of these aims, a major methodological focus has been on developing novel approaches to modeling high-dimensional time-series data, particularly approaches that bring together probabilistic modeling and deep learning, and causal inference from observational data.- R. Krishnan, U. Shalit, D. Sontag. Structured Inference Networks for Nonlinear State Space Models, Thirty-First AAAI Conference on Artificial Intelligence, Feb. 2017. [code]
- N. Razavian, J. Marcus, D. Sontag. Multi-task Prediction of Disease Onsets from Longitudinal Laboratory Tests. Proceedings of the 1st Conference on Machine Learning in Health Care (MLHC), Aug. 2016. [code]
- X. Wang, D. Sontag, F. Wang. Unsupervised Learning of Disease Progression Models. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Aug. 2014. [Slides]
- N. Razavian, S. Blecker, A.M. Schmidt, A. Smith-McLallen, S. Nigam, D. Sontag. Population-Level Prediction of Type 2 Diabetes using Claims Data and Analysis of Risk Factors. Big Data (Data and Healthcare Special Issue), Jan. 2016 [PDF]
Intelligent Electronic Health Records
Today's electronic health records are predominately a place for recording a patient's health data. We aim to develop the foundation for the next-generation of intelligent electronic health records, where machine learning and artificial intelligence is built-in to help with medical diagnosis, automatically trigger clinical decision support, personalize treatment suggestions, autonomously retrieve relevant past medical history, make documentation faster and higher quality, and predict adverse events before they happen. A major challenge is the need for robust machine learning algorithms that are safe, interpretable, can learn from little labeled training data, understand natural language, and generalize well across medical settings and institutions.- S. Blecker, S. Katz, L. Horwitz, G. Kuperman, H. Park, A. Gold, D. Sontag. Comparison of Approaches for Heart Failure Case Identification From Electronic Health Record Data. Journal of the American Medical Association (JAMA) Cardiology, Oct. 2016.
- Y. Halpern, S. Horng, Y. Choi, D. Sontag. Electronic Medical Record Phenotyping using the Anchor and Learn Framework. Journal of the American Medical Informatics Association (JAMIA), April 2016. [PDF]
- Y. Jernite, Y. Halpern, S. Horng, D. Sontag. Predicting Chief Complaints at Triage Time in the Emergency Department. NIPS 2013 Workshop on Machine Learning for Clinical Data Analysis and Healthcare, Dec. 2013.