Skip Navigation

Center for Health Services and Outcomes Research

Innovative Methods: New Applications

Collaborative Research: Modeling Disease Trajectories in Patients with Complex, Multiphenotypic Conditions

Chronic conditions are driving the majority of our health care costs, and this burden is only expected to rise. Simultaneously, due to the rapid proliferation of electronic clinical data stores, longitudinal electronic health data, containing the multitude of clinical measurements taken during routine clinical visits, are becoming available at scale for retrospective analysis. These data provide an unprecedented opportunity to learn about canonical patterns of variability between individuals in the way a disease manifests, and develop novel approaches for individualizing risk prediction.

This project proposes a novel computational framework for individualized risk prediction from modern electronic health data sources. The project develops a flexible Bayesian framework for jointly modeling the array of complex measurements present in the electronic health record to track an individual's disease status over time. Overall, the project significantly advances computational modeling for individualized risk prediction from modern electronic health data sources. 

Publications:

 S. Saria. "A $3 Trillion Challenge to Computational Scientists: Transforming Healthcare Delivery," IEEE Intelligent Systems., v.29, 2014.

K. Dyagilev, S. Saria. "Learning (Predictive) Risk Scores in the Presence of Censoring due to Interventions," Machine Learning, v.102, 2016.

P. Schulam, C. Ligon, B. Wise, L. Hummers, F. Wigley, S. Saria. "A Computational Tool for Individualized Prognosis of Percent of Predicted Forced Vital Capacity Trajectories in Systemic Sclerosis," Arthritis and Rheumatology, v.67, 2015.

P. Schulam, S. Saria. "A Framework for Individualizing Prognosis of Disease Trajectories by Exploiting Multiresolution Structure," Neural Information Processing Systems (NIPS), 2015.

P. Schulam, S. Saria. "A Probabilistic Graphical Model for Individualizing Prognosis in Chronic, Complex Diseases," Proceedings of the American Medical Informatics Association Ann. Sym., 2015.