Predictors of colorectal cancer survival using cox regression and random survival forests models based on gene expression data

Mohanad Mohammed; Innocent B Mboya; Henry Mwambi; Murtada K Elbashir; Bernard Omolo

doi:10.1371/journal.pone.0261625

Predictors of colorectal cancer survival using cox regression and random survival forests models based on gene expression data

PLoS One. 2021 Dec 29;16(12):e0261625. doi: 10.1371/journal.pone.0261625. eCollection 2021.

Authors

Mohanad Mohammed^{1

2}, Innocent B Mboya^{1

3}, Henry Mwambi¹, Murtada K Elbashir⁴, Bernard Omolo^{1

5

6}

Affiliations

¹ School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Pietermaritzburg, Scottsville, South Africa.
² Faculty of Mathematical and Computer Sciences, University of Gezira, Wad Madani, Sudan.
³ Department of Epidemiology and Biostatistics, Kilimanjaro Christian Medical University College (KCMUCo), Moshi, Tanzania.
⁴ College of Computer and Information Sciences, Jouf University, Sakaka, Saudi Arabia.
⁵ Division of Mathematics & Computer Science, University of South Carolina-Upstate, Spartanburg, United States of America.
⁶ School of Public Health, Faculty of Health Sciences, University of Witwatersrand, Johannesburg, South Africa.

Abstract

Understanding and identifying the markers and clinical information that are associated with colorectal cancer (CRC) patient survival is needed for early detection and diagnosis. In this work, we aimed to build a simple model using Cox proportional hazards (PH) and random survival forest (RSF) and find a robust signature for predicting CRC overall survival. We used stepwise regression to develop Cox PH model to analyse 54 common differentially expressed genes from three mutations. RSF is applied using log-rank and log-rank-score based on 5000 survival trees, and therefore, variables important obtained to find the genes that are most influential for CRC survival. We compared the predictive performance of the Cox PH model and RSF for early CRC detection and diagnosis. The results indicate that SLC9A8, IER5, ARSJ, ANKRD27, and PIPOX genes were significantly associated with the CRC overall survival. In addition, age, sex, and stages are also affecting the CRC overall survival. The RSF model using log-rank is better than log-rank-score, while log-rank-score needed more trees to stabilize. Overall, the imputation of missing values enhanced the model's predictive performance. In addition, Cox PH predictive performance was better than RSF.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Aged
Biomarkers, Tumor / genetics*
Colorectal Neoplasms* / genetics
Colorectal Neoplasms* / mortality
Female
Gene Expression Regulation, Neoplastic*
Humans
Male
Middle Aged
Risk Factors
Survival Analysis

Substances

Biomarkers, Tumor

Grants and funding

This work was funded by GSK Africa Non-Communicable Disease Open Lab through the DELTAS Africa Sub-Saharan African Consortium for Advanced Biostatistics (SSACAB) Grant No. 107754/Z/15/Z- training programme. The views expressed in this publication are those of the author(s) and not necessarily those of GSK. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.