A machine learning–Based model to predict early death among bone metastatic breast cancer patients: A large cohort of 16,189 patients

Abstract

Purpose: This study aims to develop a prediction model to categorize the risk of early death among breast cancer patients with bone metastases using machine learning models.Methods: This study examined 16,189 bone metastatic breast cancer patients between 2010 and 2019 from a large oncological database in the United States. The patients were divided into two groups at random in a 90:10 ratio. The majority of patients (n = 14,582, 90%) were served as the training group to train and optimize prediction models, whereas patients in the validation group (n = 1,607, 10%) were utilized to validate the prediction models. Four models were introduced in the study: the logistic regression model, gradient boosting tree model, decision tree model, and random forest model.Results: Early death accounted for 17.4% of all included patients. Multivariate analysis demonstrated that older age; a separated, divorced, or widowed marital status; nonmetropolitan counties; brain metastasis; liver metastasis; lung metastasis; and histologic type of unspecified neoplasms were significantly associated with more early death, whereas a lower grade, a positive estrogen receptor (ER) status, cancer-directed surgery, radiation, and chemotherapy were significantly the protective factors. For the purpose of developing prediction models, the 12 variables were used. Among all the four models, the gradient boosting tree had the greatest AUC [0.829, 95% confident interval (CI): 0.802–0.856], and the random forest (0.828, 95% CI: 0.801–0.855) and logistic regression (0.819, 95% CI: 0.791–0.847) models came in second and third, respectively. The discrimination slopes for the three models were 0.258, 0.223, and 0.240, respectively, and the corresponding accuracy rates were 0.801, 0.770, and 0.762, respectively. The Brier score of gradient boosting tree was the lowest (0.109), followed by the random forest (0.111) and logistic regression (0.112) models. Risk stratification showed that patients in the high-risk group (46.31%) had a greater six-fold chance of early death than those in the low-risk group (7.50%).Conclusion: The gradient boosting tree model demonstrates promising performance with favorable discrimination and calibration in the study, and this model can stratify the risk probability of early death among bone metastatic breast cancer patients.

Breast Cancer Prediction using Machine Learning Models

“…10 and Table IV show that the performance of each model was successful in cancer prediction accuracy. These results showed superiority in the same ML models in [24] and [26] where the Bagging and K-NN models achieved a performance of 96.47% and 96.40% in predicting Breast Cancer. These results do not determine that one is better than the other, on the contrary, the performance rate varies according to different factors, and one of them is the volume of data with which it is trained.…”

“…For this, they used three parameters such as age, cell type with cancer, and cell interface receptors. Also, in [24] developed a predictive model to categorize people with breast cancer using the logistic regression (LR) model, GB model, decision tree (DT), and RF model. Obtaining the following results for the LR model 81.9%; GBT with 82%; RF with 82.8%, respectively.…”

Machine learning-based prediction of hospital prolonged length of stay admission at emergency department: a Gradient Boosting algorithm analysis

“…Several studies, including (Kong et al, 2020 ; Jo et al, 2021 ; Wu et al, 2021 ; Xiong et al, 2022 ), have shown that the GB classifier outperforms other algorithms in predicting PLoS, with reported accuracy, AUC, and Brier score ranging from 75.3 to 82.9%, 0.74 to 0.873, and 0.122 to 0.156, respectively. Our study's findings are consistent with these results.…”

A Predictive Model for the Early Death of Breast Cancer With Synchronous Liver Metastases: A Population-Based Study

“…Many studies have explored early death in breast cancer patients, but there are no studies on early death in breast cancer patients with liver metastases. [11][12][13] This study aims to address this gap by exploring prognostic factors and constructing a columnar plot to identify early death in breast cancer patients with liver metastases. This represents the first such study to our knowledge.…”