@inproceedings{Zhang:2022:10.1007/978-3-031-14771-5_12,
author = {Zhang, K and Toni, F and Williams, M},
doi = {10.1007/978-3-031-14771-5_12},
pages = {171--185},
publisher = {Springer},
title = {A federated cox model with non-proportional hazards},
url = {http://dx.doi.org/10.1007/978-3-031-14771-5_12},
year = {2022}
}

Download

TY  - CPAPER
AB  - Recent research has shown the potential for neural networksto improve upon classical survival models such as the Cox model, whichis widely used in clinical practice. Neural networks, however, typicallyrely on data that are centrally available, whereas healthcare data arefrequently held in secure silos. We present a federated Cox model thataccommodates this data setting and also relaxes the proportional hazardsassumption, allowing time-varying covariate effects. In this latter respect,our model does not require explicit specification of the time-varying ef-fects, reducing upfront organisational costs compared to previous works.We experiment with publicly available clinical datasets and demonstratethat the federated model is able to perform as well as a standard model.
AU  - Zhang,K
AU  - Toni,F
AU  - Williams,M
DO  - 10.1007/978-3-031-14771-5_12
EP  - 185
PB  - Springer
PY  - 2022///
SN  - 1860-949X
SP  - 171
TI  - A federated cox model with non-proportional hazards
UR  - http://dx.doi.org/10.1007/978-3-031-14771-5_12
UR  - https://link.springer.com/book/9783031147708
UR  - http://hdl.handle.net/10044/1/93613
ER  - 

Download