Pan-Cancer Survival Classification With Clinicopathological and Targeted Gene Expression Features

Abstract

Prognostication for patients with cancer is important for clinical planning and management, but remains challenging given the large number of factors that can influence outcomes. As such, there is a need to identify features that can robustly predict patient outcomes. We evaluated 8608 patient tumor samples across 16 cancer types from The Cancer Genome Atlas and generated distinct survival classifiers for each using clinical and histopathological data accessible to standard oncology workflows. For cancers that had poor model performance, we deployed a random-forest-embedded sequential forward selection approach that began with an initial subset of the 15 most predictive clinicopathological features before sequentially appending the next most informative gene as an additional feature. With classifiers derived from clinical and histopathological features alone, we observed cancer-type-dependent model performance and an area under the receiver operating curve (AUROC) range of 0.65 to 0.91 across all 16 cancer types for 1- and 3-year survival prediction, with some classifiers consistently outperforming those for others. As such, for cancers that had poor model performance, we posited that the addition of more complex biomolecular features could enhance our ability to prognose patients where clinicopathological features were insufficient. With the inclusion of gene expression data, model performance for 3 select cancers (glioblastoma, stomach/gastric adenocarcinoma, ovarian serous carcinoma) markedly increased from initial AUROC scores of 0.66, 0.69, and 0.67 to 0.76, 0.77, and 0.77, respectively. As a whole, this study provides a thorough examination of the relative contributions of clinical, pathological, and gene expression data in predicting overall survival and reveals cancer types for which clinical features are already strong predictors and those where additional biomolecular information is needed.

Gray wolf‐student psychology optimization‐based deep long short term memory for survival prediction using cancer gene‐expression data

“…Though method was effective in all cases but, it failed to predict the organ where cancer is developed. Zhao et al 19 developed a machine learning techniques to characterize and analyze significance of pathological, and clinical features in detecting overall survival (OS) over 16 diverse cancer kinds. At last, an orthogonal method was used to elevate cox proportional‐hazards techniques to analyze drawbacks of prognostic models on OS.…”

Coupling Deep Imputation with Multitask Learning for Downstream Tasks on Genomics Data

“…The breadth of modalities in this space have stimulated an active research in combining multi-omics data for predicting end points such as survival, patient outcomes, and clinical features [1,2,3,4]. Important to mention are studies which included clinical features such as age and cancer type for survival predictions [5,6]. While these features have a relatively strong prognostic power for survival predictions, they can mask the value of -omics data which enable researchers to unravel the biology behind the disease.…”