Events Calendar

Epstein ISE Department Seminar

Speaker: Diana M. Negoescu, Dept of Management Science and Engineering, Stanford University

Talk Title: "Dynamic Learning of Patient Response Types"

Abstract: For many chronic diseases, available treatments are effective only for a subgroup of patients, and biomarkers that accurately assess the responsiveness of an individual patient do not exist. In these settings, information regarding the response type of a patient can only be generated by experimentation -- subjecting the patient to a variety of treatments. Physicians then learn about the response through self-reported patient evaluations, as well as from the (non)occurrence of negative health events such as disease flare-ups. The timing of these events also carries substantial information, which should be taken into account when determining optimal personalized treatments.

In this talk, I will introduce a continuous-time, two-armed bandit framework that balances the trade-off between exploring alternative treatments and exploiting available information. Unlike most multi-armed bandit models that learn only from observed rewards, our model also incorporates information regarding the frequency of health events, and can be analyzed in closed form to derive guidelines for treatment policies. I will showcase the effectiveness of our methodology by developing an adaptive policy to treat multiple sclerosis, a chronic autoimmune disease. We compare the performance of our policy to that of a standard, non-adaptive treatment policy, and show that, by identifying non-responders earlier, our approach leads to improvements in quality-adjusted life expectancy, as well as significant cost savings. Beyond multiple sclerosis, dynamic learning models that incorporate the timing of events may find several applications in a broader medical decision making context, as a means to design treatment policies for diseases such as depression, rheumatoid arthritis, celiac or Crohn's disease.

Based on joint work with Kostas Bimpikis, Margaret L. Brandeau and Dan A. Iancu.


THURSDAY, FEBRUARY 27, 2014
ANDRUS GERONTOLOGY BLDG (GER) ROOM 206
2:00 - 3:00 PM

Biography: Diana Negoescu is a PhD candidate in the Department of Management Science and Engineering at Stanford University. Her dissertation focuses on the application of operations research and management science to medical and health policy decision-making problems. In particular, her research focuses on personalized medical decision-making and healthcare models for problems where patient characteristics are partially unknown or evolving over time, and where decision makers are risk-averse, or face constraints on the resources they can use or the actions they can take.

Host: Daniel J. Epstein Department of Industrial and Systems Engineering

More Information: Seminar-Negoescu.doc

Location: Room 206

Audiences: Everyone Is Invited

Contact: Georgia Lum