构建和验证机器学习模型,以基于非侵入性指标预测冠心病风险
Bo Wu1, Kang Huang1, Xin Hong1
1Department of Cardiovascular Surgery, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, 330006, China.
Computer methods and programs in biomedicine
|December 7, 2025
概括
一个新的机器学习模型使用临床数据准确预测冠心病 (CHD) 风险. 这种工具有助于早期查和预防心血管疾病,这是导致死亡的主要原因.
科学领域:
- 心脏病学 心脏病学
- 机器学习 机器学习
- 公共卫生 公共卫生
背景情况:
- 冠心病 (CHD) 是全球主要的死亡原因.
- 早期发现和干预对于管理心血管疾病至关重要.
- 本研究的重点是开发用于CHD风险预测的机器学习 (ML) 模型.
研究的目的:
- 开发和评估冠心病 (CHD) 风险的预测模型.
- 确定导致心脏病风险的关键临床特征.
- 创建一个用户友好的工具,用于早期的CHD查.
主要方法:
- 利用行为风险因素监测系统 (BRFSS) 数据集用于模型开发和内部验证.
- 采用了八个机器学习算法,包括光梯度增强机 (LightGBM).
- 在外部验证了最佳模型,使用国家健康和营养检查调查 (NHANES) 数据集和SHAP分析来确定特征的重要性.
主要成果:
- 轻GBM模型在内部验证中实现了0.825的AUC,在外部验证中达到0.851.
- 确定的主要预测因素包括年龄,性别,高血压和脂质失调.
- 基于LightGBM模型开发了一个基于Web的计算器,用于基于LightGBM模型的CHD风险预测.
结论:
- 基于LightGBM的CHD风险预测模型表现出高准确度.
- 这个模型显示了早期查和预防冠心病的巨大潜力.
- 开发的工具可以帮助医疗保健专业人员识别高风险个体.
更多相关视频
相关概念视频
Coronary Artery Disease IV: Preventive Measures
575
Effective preventive measures for coronary artery disease (CAD) focus on controlling modifiable risk factors, including cholesterol abnormalities and lifestyle changes.Cholesterol ManagementFirst, the Mediterranean diet and the American Heart Association advocate for maintaining low-density lipoprotein (LDL) cholesterol levels below 100 mg/dL, with a more stringent recommendation of below 70 mg/dL for individuals at high risk. LDL cholesterol, often termed "bad cholesterol," can lead to the...
575
Coronary Artery Disease I: Introduction
850
Coronary Artery Disease (CAD): An Overview with Scientific InsightsCoronary Artery Disease (CAD), often referred to as C-A-D, is a prevalent blood vessel disorder classified under the broader category of atherosclerosis. Atherosclerosis is a pathological process characterized by the hardening and narrowing of arteries due to the accumulation of atherosclerotic plaques. These plaques are composed of cholesterol, fatty substances, inflammatory cells, calcium, and fibrin, reducing blood flow to...
850


