Machine Learning With K-Means Dimensional Reduction for Predicting Survival Outcomes in Patients With Breast Cancer

Abstract

Objective:Despite existing prognostic markers, breast cancer prognosis remains a difficult subject due to the complex relationships between many contributing factors and survival. This study seeks to integrate multiple clinicopathological and genomic factors with dimensional reduction across machine learning algorithms to compare survival predictions.Methods:This is a secondary analysis of the data from a prospective cohort study of female patients with breast cancer enrolled in the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC). We constructed a series of predictive models: ensemble models (Gradient Boosting and Random Forest), support vector machine (SVM), and artificial neural networks (ANN) for 5-year survival based on clinicopathological and gene expression data after K-means clustering with K-nearest-neighbor (KNN) classification. Model performance was evaluated by receiver operating characteristic (ROC) curve, accuracy, and calibration slope (CS). Model stability was assessed over 10 random runs in terms of ROC, accuracy, CS, and variable importance.Results:The analytic cohort is composed of 1874 patients with breast cancer. Overall, the median age was 62 years; the 5-year survival rate was 75%. ROC and accuracy were not significantly different between models (ROC and accuracy around 0.67 and 0.72 across models, respectively). However, ensemble methods resulted in better fit (CS) with stable measures of variable importance across 10 random training/validation splits. K-means clustering of gene expression profiles on training data points along with KNN classification of validation data points was a robust method of dimensional reduction. Furthermore, the gene expression cluster with the highest mortality risk was an influential factor in model prediction.Conclusions:Using machine learning methods to construct predictive models for 5-year survival in patients with breast cancer, we demonstrated discrimination ability across models with new insight into the stability and utility of dimensional reduction on genomic features in breast cancer survival prediction.

A Translational Pipeline for Overall Survival Prediction of Breast Cancer Patients by Decision-Level Integration of Multi-Omics Data

“…Authors found that all methods tested, including gradient boosting, random forest, artificial neural networks, and support vector machine, performed rather similarly with accuracy and AUC of .72 and .67, respectively. Importantly, this study demonstrates that classification methods may not matter as much as the quality of the data itself [6]. Goli et al developed a breast cancer survival prediction model using clinical and pathological data using support vector regression and found similar positive results.…”

“…Zhao et al created and compared various survival prediction models using different types of popular classification algorithms with a high dimensional dataset of breast cancer patients. Authors demonstrated that all models performed similarly and consistently [6].…”

Graphical Model and Clustering-Regression based Methods for Causal Interactions: Breast Cancer Case Study

“…The best algorithm was Diana that gave the best number of clusters. In [20], applied K-means and K-nearest-neighbor on data of gene expression to predicting breast cancer survival. The fitting calibration slope gave the best outcome.…”

Deep learning based feature-level integration of multi-omics data for breast cancer patients survival analysis

“…Various models have been developed for survival prediction in large and heterogeneous cancer datasets. For example, Zhao et al have tested various classification algorithms to predict 5-year breast cancer survival by integrating gene expression data with clinical and pathological factors [11]. Authors find that various classification methods (e.g., gradient boosting, random forest, artificial neural networks, and support vector machine) have similar accuracy and area under the curve (AUC) of 0.72 and 0.67, respectively.…”

“…Authors find that various classification methods (e.g., gradient boosting, random forest, artificial neural networks, and support vector machine) have similar accuracy and area under the curve (AUC) of 0.72 and 0.67, respectively. This study demonstrates that classification methods may not matter as much as the quality of the data itself [ 11 ]. Goli et al have developed a breast cancer survival prediction model with clinical and pathological data using support vector regression and find similar positive results [ 12 ].…”