开发和验证一种基于机器学习的预测模型,用于中年和年轻人的冠心病风险
Yifan Deng1, Yahui Li2, Jiapei Gao3
1Northern Jiangsu People's Hospital Affiliated to Yangzhou University, Yangzhou 225001, China; Northern Jiangsu People's Hospital, Yangzhou, Jiangsu Province, China; Medical College of Yangzhou University, Yangzhou, Jiangsu Province, China.
机器学习模型准确地预测了中国成年人早期冠心病 (PCHD) 风险. 后勤回归和支持向量机器模型为早期PCHD识别和干预提供了宝贵的工具.
科学领域:
- 心脏病学 心脏病学
- 医疗信息学 医疗信息学
- 机器学习 机器学习
背景情况:
- 冠心病 (CHD) 发病率在年轻人群中正在增加.
- 有效的风险预测模型对于二次性心血管疾病预防至关重要.
- 开发早期冠心病 (PCHD) 的快速风险评估工具至关重要.
研究的目的:
- 在中国人群中开发PCHD的临床预测模型.
- 使用机器学习算法来进行PCHD风险分层.
- 确定早期PCHD检测的关键预测因素.
主要方法:
- 一项对1276名接受冠状动脉血管造影的患者进行的回顾性队列研究.
- 使用拉索回归和交叉验证进行特征选择.
- 评估七个监督学习算法,包括后勤回归 (LR) 和支持矢量机器 (SVM).
主要成果:
- 拉索回归确定了PCHD的9个潜在预测因素.
- LR (AUC:0.82) 和SVM模型显示出强大的预测性能.
- 诺米图和SHAP图被用于可视化和解释LR和SVM模型,分别.
结论:
- 基于LR的名录和SVM-SHAP模型在临床上对PCHD风险分层有用.
- 这些模型可以早期识别高风险个体.
- 基于模型预测,可以实施有针对性的预防性干预.
更多相关视频
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
06:16Signal Acquisition, Score Interpretation, and Economics of a Non-Invasive Point-of-Care Test for Coronary Artery Disease
Published on: August 9, 2024
相关概念视频
Coronary Artery Disease IV: Preventive Measures
Coronary Artery Disease I: Introduction
Coronary Artery Disease II: Pathophysiology
Coronary Artery Disease III: Clinical Manifestations
Acute Coronary Syndrome III: Diagnostic Studies
Blood Studies for Cardiovascular System I: Cardiac Biomarkers
The essential diagnostic tools for detecting myocardial necrosis and monitoring individuals suspected of having acute coronary syndrome (ACS) include:
Troponins
Troponins, particularly cardiac troponins I and T, are the most precise and sensitive markers of myocardial injury. They are detectable within 4-6 hours of myocardial injury and remain...
