Improving Breast Cancer Survival Analysis through Competition-Based Multidimensional Modeling

Erhan Bilal, Janusz Dutkowski, Justin Guinney, In Sock Jang, Benjamin A. Logsdon, Gaurav Pandey, Benjamin A. Sauerwine, Yishai Shimoni, Hans Kristian Moen Vollan, Brigham H. Mecham, Oscar M. Rueda, Jorg Tost, Christina Curtis, Mariano J. Alvarez, Vessela N. Kristensen, Samuel Aparicio, Anne-Lise Børresen-Dale, Carlos Caldas, Andrea Califano, Stephen H. Friend et al. (4 additional authors not shown)

Abstract: Author Summary We developed an extensible software framework for sharing molecular prognostic models of breast cancer survival in a transparent collaborative environment and subjecting each model to automated evaluation using objective metrics. The computational framework presented in this study, our detailed post-hoc analysis of hundreds of modeling approaches, and the use of a novel cutting-edge data resource together represents one of the largest-scale systematic studies to date assessing the factors influencing accuracy of molecular-based prognostic models in breast cancer. Our results demonstrate the ability to infer prognostic models with accuracy on par or greater than previously reported studies, with significant performance improvements by using state-of-the-art machine learning approaches trained on clinical covariates. Our results also demonstrate the difficultly in incorporating molecular data to achieve substantial performance improvements over clinical covariates alone. However, improvement was achieved by combining clinical feature data with intelligent selection of important molecular features based on domain-specific prior knowledge. We observe that ensemble models aggregating the information across many diverse models achieve among the highest scores of all models and systematically out-perform individual models within the ensemble, suggesting a general strategy for leveraging the wisdom of crowds to develop robust predictive models.