Regularizing the Deepsurv Network Using Projection Loss for Medical Risk Assessment

Thammasorn P, Schaub SK, Hippe DS, Spraker MB, Peeken JC, Wootton LS, Kinahan PE, Combs SE, Chaovalitwongse WA, Nyflot MJ (2022)

Publication Type: Journal article

Publication year: 2022

Journal

IEEE Access Institute of Electrical and Electronics Engineers (IEEE)

Book Volume: 10

Pages Range: 8005-8020

DOI: 10.1109/ACCESS.2022.3142032

Abstract

State-of-the-art deep survival prediction approaches expand network parameters to accommodate performance over a fine discretization of output time. For medical applications where data are limited, the regression-based Deepsurv approach is more advantageous because its continuous output design limits unnecessary network parameters. Despite the practical advantage, the typical network lacks control over the feature distribution causing the network to be more prone to noisy information and occasional poor prediction performance. We propose a novel projection loss as a regularizing objective to improve the time-to-event Deepsurv model. The loss formulation maximizes the lower bound of the multiple-correlation coefficient between the network's features and the desired hazard value. Reducing the loss also theoretically lowers the upper bound on the likelihood of discordant pair and improves C-index performance. We observe superior performances and robustness of regularized Deepsurv over many state-of-the-art approaches in our experiments with five public medical datasets and two cross-cohort validation tasks.

Involved external institutions

University of Arkansas US United States (USA) (US) University of Washington US United States (USA) (US) Fred Hutchinson Cancer Research Center US United States (USA) (US) Washington University US United States (USA) (US) Technische Universität München (TUM) DE Germany (DE)

How to cite

APA:

Thammasorn, P., Schaub, S.K., Hippe, D.S., Spraker, M.B., Peeken, J.C., Wootton, L.S.,... Nyflot, M.J. (2022). Regularizing the Deepsurv Network Using Projection Loss for Medical Risk Assessment. IEEE Access, 10, 8005-8020. https://doi.org/10.1109/ACCESS.2022.3142032

MLA:

Thammasorn, Phawis, et al. "Regularizing the Deepsurv Network Using Projection Loss for Medical Risk Assessment." IEEE Access 10 (2022): 8005-8020.

BibTeX: Download