机器学习预测和SHAP解释性分析心力衰竭风险在患有高尿路血病的患者
Tian-Ming Gan1, Shi-Rong Wang1, Guan-Lian Mo1
1Department of Cardiology, The First Affiliated Hospital of Guilin Medical University, Guilin, Guangxi, China.
Frontiers in cardiovascular medicine
|December 17, 2025
概括
使用六个指标的简单模型可以预测心力衰竭 (HF) 风险在患有高尿路血症的患者. 这种工具有助于早期识别和干预心血管健康.
科学领域:
- 心脏病学 心脏病学
- 腎臟病學 (nephrology) 是一種醫學.
- 公共卫生 公共卫生
背景情况:
- 心血管疾病,特别是心力衰竭 (HF),对全球健康造成重大负担.
- 高尿路血是已知的风险因素,增加了对HF的易感性.
- 目前的高频风险预测模型是复杂的,阻碍了临床应用.
研究的目的:
- 开发一个简单的,可解释的风险评估模型,对高尿血病患者的HF.
- 确定可访问的临床指标,用于风险分层的日常使用.
- 解决对管理心血管风险的实际工具的需求.
主要方法:
- 利用了NHANES数据 (2005年至2020年3月),其中包括1,603名患有高尿血症的成年人.
- 应用各种机器学习模型 (SVM,随机森林,物流回归,XGBoost) 进行预测.
- 使用精度,灵敏度,F1得分和ROC AUC评估模型性能;使用SHAP来确定特征的重要性.
主要成果:
- 支持矢量机 (SVM) 模型表现出卓越的性能.
- 确定了关键预测因素:慢性病,冠心病,高血压,血清,血清度和久坐时间.
- 这六个指标在高尿血症队列中显示出HF的显著预测能力.
结论:
- 提出了一种简单,可解释的工具,用于高尿素血症患者的高尿素风险分层.
- 该模型整合了六个易于获得的临床实用性指标.
- 建议进一步验证,但该模型显示了早期HF检测和干预的潜力.
相关概念视频
Heart Failure IV: Classification and Diagnostic Evaluation
293
Heart failure can be classified in various ways, with the most common classifications based on physical activity limitations, disease progression, severity, and treatment strategies.The Functional Classification of Heart Failure divides patients into four categories based on physical activity limitation due to symptom burden.Class I: Patients in this class have cardiac disease but no physical activity limitations. Ordinary activities like walking, climbing stairs, or routine tasks do not cause...
293
Heart Failure I: Introduction
660
Heart failure refers to a clinical syndrome caused by structural or functional cardiac disorders that prevent the heart from pumping an adequate amount of blood to meet the body's metabolic needs. This condition often arises from myocardial infarction or ischemia, leading to decreased cardiac output, reduced tissue perfusion, impaired gas exchange, fluid volume imbalance, and decreased functional ability.Heart failure can result from disruptions in the mechanisms that regulate cardiac output...
660


