Data-driven operations and incentives in healthcare
Abstract/Contents
- Abstract
- The United States has the highest per-capita healthcare spending in the world, surpassing annual national expenditures of $2.5 trillion a year. Yet, there are serious concerns about the quality of care, including medical errors, as well as the underuse and overuse of healthcare resources. This thesis focuses on improving patient outcomes through (1) optimizing hospital operations using machine learning and statistical decision-making tools based on increasingly available data, and (2) the design of healthcare policy that better aligns provider incentives with the goal of high-quality and cost-effective care. Chapter 1 proposes new algorithms for personalized medical decision-making that can efficiently leverage high-dimensional patient data. Chapter 2 empirically assesses pitfalls of current pay-for-performance healthcare policies. Chapter 3 studies the game-theoretic design of pay-for-performance policies that optimize hospitals' financial incentives in the presence of institutional constraints.
Description
| Type of resource | text |
|---|---|
| Form | electronic; electronic resource; remote |
| Extent | 1 online resource. |
| Publication date | 2017 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Associated with | Bastani, Hamsa Sridhar |
|---|---|
| Associated with | Stanford University, Department of Electrical Engineering. |
| Primary advisor | Bayati, Mohsen |
| Thesis advisor | Bayati, Mohsen |
| Thesis advisor | Johari, Ramesh, 1976- |
| Thesis advisor | Zenios, Stefanos A |
| Advisor | Johari, Ramesh, 1976- |
| Advisor | Zenios, Stefanos A |
Subjects
| Genre | Theses |
|---|
Bibliographic information
| Statement of responsibility | Hamsa Sridhar Bastani. |
|---|---|
| Note | Submitted to the Department of Electrical Engineering. |
| Thesis | Thesis (Ph.D.)--Stanford University, 2017. |
| Location | electronic resource |
Access conditions
- Copyright
- © 2017 by Hamsa Sridhar Bastani
Also listed in
Loading usage metrics...