Artificial intelligence in healthcare and medicine : enhancing the expert
Abstract/Contents
- Abstract
- Due to a convergence of large open-source datasets, significant improvements in the parallelization capabilities of hardware (notably, multi-thousand core graphics processing units), and renewed academic interest in decades-old neural network algorithms, primary subfields of AI have flourished in the past 5 years. Natural Language Processing, Computer Vision, and robotics have attained impressive performance across many key AI tasks. In this thesis we focus not on the development of new AI algorithms, but on their application to a series of important problems in healthcare and medicine. Machine learning and AI will impact industries that generate significant amounts of data, by extracting insights that humans cannot. Healthcare and medicine are examples of such industries and thus are excellent use cases for AI deployment. Our story is divided into 4 sections - neuroscience, psychiatry, drug screening, and dermatology - all linked by the common thread of using AI to \textit{enhance the expert}, either in-clinic or in the analysis of data. This underlying motif is the connection to a paradigm in AI development popularized as the \textit{virtual cycle of AI}: build a product that has front-facing user value, generate data with it, use that data to train AI algorithms that improve your product, acquire more data, etc.
Description
| Type of resource | text |
|---|---|
| Form | electronic; electronic resource; remote |
| Extent | 1 online resource. |
| Publication date | 2018 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Associated with | Esteva, Andres |
|---|---|
| Associated with | Stanford University, Department of Electrical Engineering. |
| Primary advisor | Boyd, Stephen P |
| Primary advisor | Thrun, Sebastian, 1967- |
| Thesis advisor | Boyd, Stephen P |
| Thesis advisor | Thrun, Sebastian, 1967- |
| Thesis advisor | Duchi, John |
| Advisor | Duchi, John |
Subjects
| Genre | Theses |
|---|
Bibliographic information
| Statement of responsibility | Andres Esteva. |
|---|---|
| Note | Submitted to the Department of Electrical Engineering. |
| Thesis | Thesis (Ph.D.)--Stanford University, 2018. |
| Location | electronic resource |
Access conditions
- Copyright
- © 2018 by Carlos Andres Esteva
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...