DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network.
Katzman JL, Shaham U, Cloninger A, Bates J, Jiang T, Kluger Y. · 2018
Read DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network. by Katzman JL, Shaham U, Cloninger A, Bates J, Jiang T, Kluger Y. (2018) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc5828433.txt.
Description
Katzman and co-authors present DeepSurv, a neural survival model that recommends treatments. Doctors use survival models to weigh how patient traits affect outcomes. Classic Cox models need heavy hand-built features. They also miss tangled interactions between traits and treatments.
DeepSurv keeps the Cox risk frame but learns features itself. Tests on simulated and real data match or beat rival methods. The model captures growing layers of trait-to-risk complexity. Applied to real trials, its picks would lengthen patient survival. The code is open for researchers to use. Readers get a deep learning tool aimed at personal treatment choice.
Catalog record
| CREATOR | Katzman JL, Shaham U, Cloninger A, Bates J, Jiang T, Kluger Y. |
|---|---|
| YEAR | 2018 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |