- Machine learning
- Computational health informatics
- Probabilistic Methods
- Time Series Models
- Information extraction in domains with structured and unstructured data (e.g., text, sensing devices, electronic health records, smart rooms)
- Predictive modeling in healthcare.
Saria’s interests span machine learning, computational statistics, and its applications to domains where one has to draw inferences from observing a complex, real-world system evolve over time. The emphasis of her research is on Bayesian and probabilistic graphical modeling approaches for addressing challenges associated with modeling and prediction in real-world temporal systems. In the last seven years, she has been particularly drawn to computational solutions for problems in health informatics (see her recent article on this topic) as she sees a tremendous opportunity there for high impact work.
Prior to joining Johns Hopkins, she earned her PhD and Masters at Stanford in Computer Science working with Dr. Daphne Koller. She also spent a year at Harvard University collaborating with Dr. Ken Mandl and Dr. Zak Kohane as an NSF Computing Innovation Fellow. While in the valley, she also spent time as an early employee at Aster Data Systems, a big data startup acquired by Teradata. She enjoys consulting and advising data-related startups. She is an investor and an informal advisor to Patient Ping.
She is originally from Darjeeling, India and (jokingly) adds that she can be bribed with good tea.
Secondary Appointments: Health Policy and Management, Bloomberg School of Public Health, Institute for Computational Medicine, Center of Population Health Information Technology, Center for Language and Speech Processing, Laboratory for Computational Sensing and Robotics, Armstrong Institute for Patient Safety & Quality.