Scholarlink

<p>Triple-negative breast cancer (TNBC) patients often ential hypertension, yet how systemic vascular stress synergizes with tumor aggressiveness to drive early recurrence remains poorly understood. A cohort of 549 TNBC patients with comorbid hypertension was analyzed. Fifteen multidimensional clinical and hemodynamic features were extracted. We constructed and compared four machine learning models, employing SHapley Additive exPlanations (SHAP) on the optimal model to decode non-linear interactions. XGBoost demonstrated superior discriminative performance for predicting early recurrence (AUC = 0.840), significantly outperforming logistic regression (<i>P</i> = 0.004). SHAP dependence analysis revealed profound non-linear thresholds, with relapse risk escalating exponentially when systolic blood pressure exceeded 140&#xa0;mmHg. Furthermore, SHAP interaction tensors identified a robust synergistic effect between widened pulse pressure and tumor invasiveness (e.g., tumor size and lymphovascular invasion), indicating that arterial stiffness critically exacerbates malignant dissemination. These findings suggest that systemic hemodynamic stress and endothelial injury synergistically amplify the inherent aggressiveness of TNBC. The interpretable XGBoost framework provides a reliable, multidimensional risk stratification tool to guide personalized cardio-oncology management and safely triage low-risk patients.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Interpretable machine learning reveals the synergistic impact of essential hypertension on early recurrence in triple-negative breast cancer

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月26日

查看全文
  • Zhenhong Du,
  • Gang Tu,
  • Lingfeng Tang

摘要

Triple-negative breast cancer (TNBC) patients often ential hypertension, yet how systemic vascular stress synergizes with tumor aggressiveness to drive early recurrence remains poorly understood. A cohort of 549 TNBC patients with comorbid hypertension was analyzed. Fifteen multidimensional clinical and hemodynamic features were extracted. We constructed and compared four machine learning models, employing SHapley Additive exPlanations (SHAP) on the optimal model to decode non-linear interactions. XGBoost demonstrated superior discriminative performance for predicting early recurrence (AUC = 0.840), significantly outperforming logistic regression (P = 0.004). SHAP dependence analysis revealed profound non-linear thresholds, with relapse risk escalating exponentially when systolic blood pressure exceeded 140 mmHg. Furthermore, SHAP interaction tensors identified a robust synergistic effect between widened pulse pressure and tumor invasiveness (e.g., tumor size and lymphovascular invasion), indicating that arterial stiffness critically exacerbates malignant dissemination. These findings suggest that systemic hemodynamic stress and endothelial injury synergistically amplify the inherent aggressiveness of TNBC. The interpretable XGBoost framework provides a reliable, multidimensional risk stratification tool to guide personalized cardio-oncology management and safely triage low-risk patients.