Improving Breast Cancer Survival Analysis through Competition-Based Multidimensional Modeling

Abstract

Breast cancer is the most common malignancy in women and is responsible for hundreds of thousands of deaths annually. As with most cancers, it is a heterogeneous disease and different breast cancer subtypes are treated differently. Understanding the difference in prognosis for breast cancer based on its molecular and phenotypic features is one avenue for improving treatment by matching the proper treatment with molecular subtypes of the disease. In this work, we employed a competition-based approach to modeling breast cancer prognosis using large datasets containing genomic and clinical information and an online real-time leaderboard program used to speed feedback to the modeling team and to encourage each modeler to work towards achieving a higher ranked submission. We find that machine learning methods combined with molecular features selected based on expert prior knowledge can improve survival predictions compared to current best-in-class methodologies and that ensemble models trained across multiple user submissions systematically outperform individual models within the ensemble. We also find that model scores are highly consistent across multiple independent evaluations. This study serves as the pilot phase of a much larger competition open to the whole research community, with the goal of understanding general strategies for model optimization using clinical and molecular profiling data and providing an objective, transparent system for assessing prognostic models.

Stabilizing Sparse Cox Model Using Statistic and Semantic Structures in Electronic Medical Records

“…In this paper, we utilize statistical and semantic relations in EMR data to stabilize a sparse Cox model for predicting readmission. Unlike recent work that concentrate on getting better features during model learning [21,22], we focus on stabilizing the features selected by the model. The model is validated on two different retrospective cohorts.…”

Association between Gene Expression, Clinical Factors and Survival in Patients with Breast Cancer

“…A number of studies (Faradmal et al, 2012;Abadi et al, 2014;Bilal et al, 2013), investigated the role of clinically associated factors such as, age at menopause, age at diagnosis, stage of the disease, tumor size, histological grade, type of therapy received (hormone therapy, radiotherapy, or chemotherapy), and family history on patient's survival. Similarly a number of studies (Martin and Weber, 2000;Apostolou and Fostira, 2013;Ciriello et al, 2015), addressed association of genes and their mutations with occurrences of breast cancer.…”

Using High-Throughput Transcriptomic Data for Prognosis: A Critical Overview and Perspectives

“…Frustratingly, the plethora of existing "omic" methods (see reviews in refs. [1][2][3][4][5] have not provided significant advance over prognosis based on classical clinical indicators (6), even though the acute need for improved prognostic tools was fully recognized and extensively addressed with several approved and commercially available products (see reviews for breast cancer in ref. 7, and for glioblastoma in refs.…”