Interpretable Cox-Guided Risk Stratification for Specialized Expert Learning in Pan-Cancer Survival Prediction

Manal Mohammed AL-Tamimi^1,2,*, Siti Norul Huda Sheikh Abdullah^1,*, Mohammad Khatim Hasan¹, Mohammed Azmi Al-Betar^3,4, Maw Shin Sim⁵, Abdulrahman Mohammed AL-Tamimi¹
1 Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia
2 Faculty of Administrative Science, Hadhramout University, AL-Mukalla, Yemen
3 Artificial Intelligence Research Center (AIRC), College of Engineering and Information Technology, Ajman University, Ajman, United Arab Emirates
4 Hourani Center for Applied Scientific Research, Al-Ahliyya Amman University, Amman, Jordan
5 Department of Pharmaceutical Life Sciences, Faculty of Pharmacy, Universiti Malaya, Kuala Lumpur, Malaysia
* Corresponding Author: Manal Mohammed AL-Tamimi. Email: email ; Siti Norul Huda Sheikh Abdullah. Email: email
(This article belongs to the Special Issue: Artificial Intelligence Models in Healthcare: Challenges, Methods, and Applications)

Computer Modeling in Engineering & Sciences https://doi.org/10.32604/cmes.2026.079891

Received 09 February 2026; Accepted 15 April 2026; Published online 07 May 2026

Abstract

Pan-cancer survival prediction remains a major challenge in personalized oncology due to profound tumor heterogeneity and the complexity of high-dimensional molecular data. Diverse risk profiles across cancer types and noisy, sparse features hinder deep learning models from capturing robust prognostic patterns. Prior pan-cancer studies predominantly focus on multimodal integration or unimodal gene expression analysis, leaving other informative modalities such as Copy Number Variation (CNV) and miRNA expression underexplored. We introduce a new formulation of mixture-of-experts (MoE) survival modeling that recasts expert assignment as a clinically interpretable risk-space decomposition problem. The proposed framework, CoxGuided-SE, constructs an ordered prognostic risk axis from a Cox proportional hazards model trained on clinical covariates, then uses quantile-based thresholds to deterministically stratify patients into risk-homogeneous groups and route them to specialized subnetworks. This design replaces black-box neural routing with a transparent, statistically principled alternative, preventing expert collapse without auxiliary regularization. Evaluated on 33 cancer types from TCGA across four modalities independently, namely clinical features, mRNA expression, miRNA expression, and CNV, CoxGuided-SE achieved substantial gains on high-dimensional genomic data, improving both discrimination and calibration. The most pronounced improvement occurred for CNV, widely considered one of the most challenging modalities for survival modeling, with a 24% increase in discrimination over the strongest baseline. The framework offers two-level interpretability: transparent patient routing based on clinical severity, and expert-specific feature importance within each subgroup. Feature-level analyses further confirm that experts learn complementary and non-redundant representations within each risk stratum. These results provide both a high-performing survival prediction framework and a principled explanation of when and why expert specialization is effective, advancing interpretable and trustworthy clinical AI for pan-cancer prognosis.

Keywords

Survival prediction; mixture-of-experts; Cox proportional hazards; pan-cancer prognosis; deep learning; multi-omics; risk stratification; interpretable AI

Downloads
- Full-Text PDF
Citation Tools
- BibTex
- EndNote
- RIS

169

View
37

Download
0

Like

Machine Learning Techniques for Intrusion Detection Systems in SDN-Recent Advances, Challenges and Future Directions
Gulshan Kumar, Hamed Alqahtani
LaNets: Hybrid Lagrange Neural Networks for Solving Partial Differential Equations
Ying Li, Longxiang Xu, Fangjun...
Optimizing Big Data Retrieval and Job Scheduling Using Deep Learning Approaches
Bao Rong Chang, Hsiu-Fen Tsai,...
Slope Collapse Detection Method Based on Deep Learning Technology
Xindai An, Di Wu, Xiangwen Xie,...
Intelligent Traffic Scheduling for Mobile Edge Computing in IoT via Deep Learning
Shaoxuan Yun, Ying Chen

Interpretable Cox-Guided Risk Stratification for Specialized Expert Learning in Pan-Cancer Survival Prediction

Abstract

Keywords

169

37

0

Further Information

Guidelines

Follow Us

Join Us

Contact Us

WhatsApp:

Share Link