Loading
Lung Cancer Research Studies / Chemotherapy-induced Cardiotoxicity and Mitigation / GDF15 and Related Biomarkers · Journal article
Frontiers in Oncology · August 12, 2026
Encouraging direction, but not yet definitive.
This retrospective study developed an XGBoost machine learning model to predict 1- to 3-year cardiovascular event risk in breast cancer patients using electronic health records from 31,878 patients. The model achieved an AUC of 0.790 and identified endocrine therapy, anemia management therapy, and cerebrovascular disease history as top predictors, while supporting short-term cardiac function decline as a precursor to long-term adverse events. However, the model requires prospective external validation before clinical deployment.
Retrospective cohort study with machine learning model development and internal cross-validation. Breast cancer patients from electronic medical records database; specific inclusion and exclusion criteria not stated.. Intervention: Machine learning model integrating baseline and treatment variables to predict cardiovascular event risk. Compared with: Five models compared; XGBoost identified as optimal. n = 31,878.
Among 31,878 breast cancer patients, 3,960 (12.4%) experienced cardiovascular events XGBoost model demonstrated best discriminative performance with AUC = 0.790 Top three predictors identified via SHAP analysis: endocrine therapy, anemia management therapy, and history of cerebrovascular disease
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
This model could assist clinicians in identifying breast cancer patients at high short-term and long-term cardiovascular risk to enable targeted monitoring and preventive interventions. However, prospective external validation in independent cohorts is essential before clinical implementation.
A real result from a sound but limited retrospective study using machine learning on electronic health records; the model shows good discriminative performance (AUC 0.790) but lacks prospective validation and independent external testing.
As stated by the source record.
Quoted from the source exactly as published.
This model could assist clinicians in identifying breast cancer patients at high short-term and long-term cardiovascular risk to enable targeted monitoring and preventive interventions. However, prospective external validation in independent cohorts is essential before clinical implementation.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Purpose This study aimed to develop and validate an interpretable machine learning model to predict the 1- to 3-year risk of cardiovascular events in breast cancer patients by integrating baseline and treatment variables, while preliminarily investigating the potential association between short-term cardiac function decline and long-term adverse cardiovascular events. Methods We analyzed electronic medical records from 31,878 breast cancer patients. A composite cardiovascular event outcome was used. Predictors were selected via a two-step process: removing highly correlated variables (|r|≥0.7) and applying LASSO regression with 10-fold cross-validation, which refined 62 initial variables down to 18. Five models were built and compared using the area under the receiver operating characteristic curve (AUC-ROC). The optimal model was interpreted using SHapley Additive exPlanations (SHAP). Results Among 31,878 breast cancer patients, 3,960 (12.4%) experienced cardiovascular events. The XGBoost model demonstrated the best overall discriminative performance (AUC = 0.790). SHAP analysis identified endocrine therapy, anemia management therapy, and history of cerebrovascular disease as the top three predictors. Crucially, short-term decline in cardiac function was also selected as a significant predictor, supporting its role as a precursor to long-term events. Model robustness was confirmed via sensitivity analysis.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.