From medical centers and individual physicians adopting electronic medical records, to patients keeping track of chronic diseases through websites and apps, we live in an era of unprecedented access to health data. These data enable inference of drug side effects, causes of disease, and new treatments, but the new terminologies, policies, and challenges in understanding the data itself can make it difficult for computational researchers to apply their techniques to this new area and for health professionals to begin using informatics to solve practical problems. This course will give both groups the foundation needed to propose, evaluate and develop projects such as secondary analysis of health data and will enable them to begin effective interdisciplinary collaborations. Students will learn how health data is collected (in both hospital and non-hospital settings), how the structure of record systems impacts the research process and interpretation of results, and how to design and evaluate studies involving secondary use of health data (while complying with HIPAA and IRB regulations) in order to gain new medical knowledge and improve healthcare delivery.
This course covers what causality is, how we can infer it using automated methods, and how to use causes to predict future events, explain past occurrences and intervene on systems. Students will learn both the theory behind causal inference methods as well as how to apply them to real-world datasets such as from finance, biology, and politics. In addition to Bayesian networks, we will cover methods for causal inference in time series including dynamic Bayesian networks, Granger causality, and logic-based methods.
Schaefer School of Engineering & Science
Bioinnovation / Center for Healthcare Innovation
Research & Education
Ph.D. in Computer Science, New York University, 2010.
B.A. Computer Science and Physics, New York University, 2006.
Causal inference and explanation
Big data (specifically time series data)
Experience & Service
Assistant Professor, Dept. of Computer Science, Stevens Institute of Technology 2012 - Present
S. Kleinberg and N. Elhadad. (2013). "Lessons Learned in Replicating Data-Driven Experiments in Multiple Medical Systems and Patient Populations", AMIA Annual Symposium Proceedings.
S. Kleinberg. (2013). "Causal Inference with Rare Events in Large-Scale Time-Series Data", Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI).
S. Kleinberg. (2011). "A Logic for Causal Inference in Time Series with Discrete and Continuous Variables", International Joint Conference on Artificial Intelligence (IJCAI).
S. Kleinberg and B. Mishra. (2010). "The Temporal Logic of Token Causes", International Conference on the Principles of Knowledge Repre- sentation and Reasoning (KR).
S. Kleinberg and B. Mishra. (2009). "The Temporal Logic of Causal Structures", Conference on Uncertainty in Artificial Intelligence (UAI).
J. Claassen, A. Perotte, D. Albers, S. Kleinberg, J. M. Schmidt, B. Tu, N. Badjatia, H. Lantigua, L. J. Hirsch, S. A. Mayer, E. S. Connolly, and G. Hripcsak. (2013). "Nonconvulsive seizures after subarachnoid hemorrhage: Multimodal detection and outcomes", Annals of Neurology, 74.
S. Kleinberg and G. Hripcsak. (2011). "A review of causal inference for biomedical informatics", Journal of Biomedical Informatics, 44 (6), 1102-1112.
A. Mitrofanova, S. Kleinberg, J. Carlton, S. Kasif, and B. Mishra. (2010). "redicting Malaria Interactome Classifications from Time-Course Transcriptomic Data along the Intra-Erythrocytic Developmental Cycle", Artificial Intelligence in Medicine, 49 (3), 167-176.
S. Kleinberg and B. Mishra. (2009). "Metamorphosis: the Coming Transformation of Translational Systems Biology", Queue, 7 (9), 40-52.
S. Kleinberg, K. Casey, and B. Mishra. (2007). "Systems Biology via Redescription and Ontologies (I): Finding Phase Changes With Applications to Malaria Temporal Data", Systems and Synthetic Biology, 1 (4), 197-205.
S. Kleinberg. (2012). Causality, Probability, and Time, Cambridge University Press.