SwarmDeepSurv: Swarm Intelligence Advances Deep Survival Network for Prognostic Radiomics Signatures in Four Solid Cancers

Authors

Qasem Al-Tashi
Maliazurina B Saad
Ajay Sheshadri
Carol C Wu
Joe Y Chang
Bissan Al-Lazikani
Christopher Gibbons
Natalie I Vokes
Jianjun Zhang
J Jack Lee
John V Heymach
David Jaffray
Seyedali Mirjalili
Jia Wu

Publication Date

8-11-2023

Journal

Patterns

Abstract

Survival models exist to study relationships between biomarkers and treatment effects. Deep learning-powered survival models supersede the classical Cox proportional hazards (CoxPH) model, but substantial performance drops were observed on high-dimensional features because of irrelevant/redundant information. To fill this gap, we proposed SwarmDeepSurv by integrating swarm intelligence algorithms with the deep survival model. Furthermore, four objective functions were designed to optimize prognostic prediction while regularizing selected feature numbers. When testing on multicenter sets (n = 1,058) of four different cancer types, SwarmDeepSurv was less prone to overfitting and achieved optimal patient risk stratification compared with popular survival modeling algorithms. Strikingly, SwarmDeepSurv selected different features compared with classical feature selection algorithms, including the least absolute shrinkage and selection operator (LASSO), with nearly no feature overlapping across these models. Taken together, SwarmDeepSurv offers an alternative approach to model relationships between radiomics features and survival endpoints, which can further extend to study other input data types including genomics.

Keywords

prognostic biomarkers, radiomics signatures, cancer, survival analysis, CoxPH, deepsurv, swarm intelligence, meta-heuristic, feature selection, SwarmDeepSurv

Comments

Supplementary Materials

PMID: 37602223