基于机器学习的模型用于预测使用眼科和临床变量在KNHANES中的心血管风险
Yuqi Zhang1,2, Sijin Li3,4, Weijie Wu3
1School of Computer Science & Engineering, Beihang University, Beijing, China.
BioData mining
|April 21, 2024
概括
这项研究开发了一种非侵入性机器学习模型,使用眼科学和临床数据来预测心血管疾病风险. 该模型有效地识别出具有高甘油三糖指数 (TyG) 或血动脉质指数 (AIP) 的个体,有助于早期风险评估.
科学领域:
- 心血管疾病风险预测预测
- 眼科和临床数据整合.
- 机器学习在医疗保健中的应用.
背景情况:
- 三甘油糖指数 (TyG) 和血动脉质指数 (AIP) 与心血管疾病 (CVD) 风险之间确立的相关性.
- 确定了对非侵入性和快速心血管疾病风险预测方法的研究缺口.
- 需要使用可访问的患者数据的先进预测模型.
研究的目的:
- 开发和验证用于预测心血管风险的机器学习模型.
- 用眼科测量和临床问卷作为输入变量.
- 评估模型在预测高TyG指数或AIP水平方面的有效性.
主要方法:
- 利用来自韩国国家健康和营养检查调查 (KNHANES) (2008-2012) 的数据.
- 训练了25个机器学习算法,对32,122名参与者的眼科和临床数据进行了训练.
- 使用接收器操作特征曲线 (AUC) 下的面积,准确性,精度,回忆和F1分数来评估模型性能.
主要成果:
- 性能最好的模型确定了TyG指数截止值 (8.0,8.75,8.93) 和AIP截止值 (0.318,0.34),具有高AUC (0.809-0.911).
- 内部和外部验证表明,Tyg-index和AIP的预测能力一致.
- 观察到某些截止值的预测准确度存在基于性别的显著差异,在TyG-index 8.93.9上表现几乎相同.
结论:
- 为心血管风险预测开发了一种简单,有效和非侵入性机器学习模型.
- 该模型证明了在一般人群中识别高风险个体的显著临床价值.
- 眼科与临床数据相结合,为快速和非侵入性健康评估提供了一个有希望的途径.
更多相关视频
相关概念视频
01:23Assessment of the Cardiovascular System I: Subjective Data
323
A thorough health history and physical assessment are essential for identifying cardiovascular disease (CVD) symptoms and distinguishing them from other health issues.
Initial Enquiry
Ask the patient about their primary concern and thoroughly explore all reported symptoms.
Medical History
Investigate past illnesses affecting the cardiovascular system, such as angina, anemia, rheumatic fever, congenital heart disease, stroke, thrombophlebitis, dysrhythmias, varicosities
Inquire about symptoms...
Initial Enquiry
Ask the patient about their primary concern and thoroughly explore all reported symptoms.
Medical History
Investigate past illnesses affecting the cardiovascular system, such as angina, anemia, rheumatic fever, congenital heart disease, stroke, thrombophlebitis, dysrhythmias, varicosities
Inquire about symptoms...
323
01:19Blood Studies for Cardiovascular System II: CRP, Hcy, and Cardiac Natriuretic Peptide Markers
81
Cardiac biomarkers are critical in diagnosing, prognosing, and managing cardiovascular diseases. Routine measurement of specific biomarkers such as B-type natriuretic peptide (BNP), C-reactive protein (CRP), and homocysteine (Hcy) is common practice in clinical settings to evaluate heart function and predict cardiovascular events.
These markers indicate stress or strain on the heart muscle:
Natriuretic Peptides (BNP)
Cardiac myocytes produce these hormones in response to ventricular stretching...
These markers indicate stress or strain on the heart muscle:
Natriuretic Peptides (BNP)
Cardiac myocytes produce these hormones in response to ventricular stretching...
81