<p>Supervised Machine Learning Predictive Analytics For Triple-Negative Breast Cancer Death Outcomes</p>

Abstract

ObjectiveTo use machine learning algorithms to predict the death outcomes of patients with triple-negative breast cancer, 5 years after discharge.Methods1570 stage I-III breast cancer patients receiving treatment from Sun Yat-sen Memorial Hospital were analyzed. Machine learning was used to predict the death outcomes of patients with triple-negative breast cancer, 5 years after discharge.ResultsThe results showed that platelets, LMR (lymphocyte-to-monocyte ratio), age, PLR (the platelet-to-lymphocyte ratio) and white blood cell counts accounted for a significant weight in the 5-year prognosis of triple-negative breast cancer patients. The results of model prediction indicated that rankings for accuracy among the training group (from high to low) were forest, gbm, and DecisionTree (0.770335, 0.760766, 0.751994, 0.737640 and 0.734450, respectively). For AUC value (high to low), they were forest, Logistic and DecisionTree (0.896673, 0.895408, 0.776836, 0.722799 and 0.702804, respectively). The highest MSE value for DecisionTree was 0.2656, and the lowest MSE value for forest was 0.2297. In the test group, accuracy rankings (from high to low) were DecisionTree, and GradientBoosting (0.748408, 0.738854, 0.738854, 0.732484 and gbm, respectively). For AUC value (high to low), the rankings were GradientBoosting, gbm, and DecisionTree (0.731595, 0.715438, 0.712767, 0.708348 and 0.691960, respectively). The maximum MSE value for gbm was 0.2707, and the minimum MSE value for DecisionTree was 0.2516.ConclusionThe machine learning algorithm can predict the death outcomes of patients with triple-negative breast cancer 5 years after discharge. This can be used to estimate individual outcomes for patients with triple-negative breast cancer.

Breast Cancer Subtypes Classification with Hybrid Machine Learning Model

“…Similar types of hybrid models have been applied in Alba et al, Moteghaed et al, and Zu et al 47 48 49 50 for breast cancer diagnosis, prediction, and classification. Recently, Xu et al 51 investigated the performance of supervised learning models like logistic regression, decision tree, random forest, gradient boosting, and light GBM with clinicopathological parameters for predicting 5-year survival analysis of TNBC patients at Sun Yat-sen Memorial Hospital, China. Hybrid models combine with different heterogeneous ML techniques and take the advantage of overcoming the weakness of individual models by integrating the complementary features of all the models involved.…”

Practice of the new supervised machine learning predictive analytics for glioma patient survival after tumor resection: Experiences in a high-volume Chinese center

“…Gradient Boosting (GB) is one of the supervised ML algorithms. Although it was strange for medical workers, this ML algorithm did have a good performance in medical scenes, such as predicting the survival outcome of triple-negative breast cancer (12) and the recurrence of colorectal cancer (13). So far, studies seldom used Gradient Boosting to analyze and predict glioma prognosis.…”

Cuproptosis-related risk score based on machine learning algorithm predicts prognosis and characterizes tumor microenvironment in head and neck squamous carcinomas

“…Machine learning algorithm has achieved many successes in its application to the fields of medicine and biology. For example, it has been used to predict the survival outcomes of triple-negative breast cancer 14 , the recurrence of colorectal cancer 15 , and the prognostic analysis of glioma 16 . These studies have utilized common clinical variables to construct non-linear models, which have demonstrated stronger predictive performance than linear models.…”