A Transductive Approach to Survival Ranking for Cancer Risk Stratification

Ethar Alzaid, Muhammad Dawood, Fayyaz Minhas
Proceedings of the 18th Machine Learning in Computational Biology meeting, PMLR 240:101-109, 2024.

Abstract

How can we stratify patients into subgroups based on their expected survival in a purely data-driven manner? Identifying cancer patients at higher risk is crucial in planning personalized treatment to improve patient survival outcomes. The main challenge with existing approaches is the underlying complexity of handling censoring in the survival data and manually setting a precise threshold to stratify patients into risk groups. In this paper, a Transductive Survival Ranking (TSR) model for patient risk stratification is proposed. The model handles samples in pairs to make use of instances with censored survival information. It incorporates unlabeled test samples in the training process to maximize the margin between their predicted survival scores resulting in automatic patient stratification into subgroups without the need for any additional post-processing or manual threshold selection. The model was evaluated on several datasets with varying sets of covariates, and all stratification were significant ($p < 0.05$) with high concordance indices of up to 0.78 in Disease Specific Survival and 0.75 in Overall Survival.

Cite this Paper

BibTeX
@InProceedings{pmlr-v240-alzaid24a, title = {A Transductive Approach to Survival Ranking for Cancer Risk Stratification}, author = {Alzaid, Ethar and Dawood, Muhammad and Minhas, Fayyaz}, booktitle = {Proceedings of the 18th Machine Learning in Computational Biology meeting}, pages = {101--109}, year = {2024}, editor = {Knowles, David A. and Mostafavi, Sara}, volume = {240}, series = {Proceedings of Machine Learning Research}, month = {30 Nov--01 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v240/alzaid24a/alzaid24a.pdf}, url = {https://proceedings.mlr.press/v240/alzaid24a.html}, abstract = {How can we stratify patients into subgroups based on their expected survival in a purely data-driven manner? Identifying cancer patients at higher risk is crucial in planning personalized treatment to improve patient survival outcomes. The main challenge with existing approaches is the underlying complexity of handling censoring in the survival data and manually setting a precise threshold to stratify patients into risk groups. In this paper, a Transductive Survival Ranking (TSR) model for patient risk stratification is proposed. The model handles samples in pairs to make use of instances with censored survival information. It incorporates unlabeled test samples in the training process to maximize the margin between their predicted survival scores resulting in automatic patient stratification into subgroups without the need for any additional post-processing or manual threshold selection. The model was evaluated on several datasets with varying sets of covariates, and all stratification were significant ($p < 0.05$) with high concordance indices of up to 0.78 in Disease Specific Survival and 0.75 in Overall Survival.} }
Endnote
%0 Conference Paper %T A Transductive Approach to Survival Ranking for Cancer Risk Stratification %A Ethar Alzaid %A Muhammad Dawood %A Fayyaz Minhas %B Proceedings of the 18th Machine Learning in Computational Biology meeting %C Proceedings of Machine Learning Research %D 2024 %E David A. Knowles %E Sara Mostafavi %F pmlr-v240-alzaid24a %I PMLR %P 101--109 %U https://proceedings.mlr.press/v240/alzaid24a.html %V 240 %X How can we stratify patients into subgroups based on their expected survival in a purely data-driven manner? Identifying cancer patients at higher risk is crucial in planning personalized treatment to improve patient survival outcomes. The main challenge with existing approaches is the underlying complexity of handling censoring in the survival data and manually setting a precise threshold to stratify patients into risk groups. In this paper, a Transductive Survival Ranking (TSR) model for patient risk stratification is proposed. The model handles samples in pairs to make use of instances with censored survival information. It incorporates unlabeled test samples in the training process to maximize the margin between their predicted survival scores resulting in automatic patient stratification into subgroups without the need for any additional post-processing or manual threshold selection. The model was evaluated on several datasets with varying sets of covariates, and all stratification were significant ($p < 0.05$) with high concordance indices of up to 0.78 in Disease Specific Survival and 0.75 in Overall Survival.
APA
Alzaid, E., Dawood, M. & Minhas, F.. (2024). A Transductive Approach to Survival Ranking for Cancer Risk Stratification. Proceedings of the 18th Machine Learning in Computational Biology meeting, in Proceedings of Machine Learning Research 240:101-109 Available from https://proceedings.mlr.press/v240/alzaid24a.html.

Related Material