Scholarlink

<p>The Atherogenic Index of Plasma (AIP) is emerging as a valuable marker in cardiovascular risk profiling, particularly among patients with Acute Myocardial Infarction (AMI). The present study investigates the association between AIP and a range of clinical parameters while introducing a novel predictive approach using Support Vector Regression (SVR). A cohort of 340 individuals, including 267 AMI patients and 73 healthy controls, were analyzed for biochemical parameters such as: lipid profile, fasting blood glucose, blood pressure, uric acid, and creatinine. Pearson correlation analysis identified significant relationships between AIP and LDL-C (r = 0.429, <i>p</i> &lt; 0.001), total cholesterol (r = 0.14, <i>p</i> = 0.01), and fasting blood glucose (r = 0.108, <i>p</i> = 0.047), whereas other parameters showed no significant correlations (<i>p</i> &gt; 0.05). Z-test results further confirmed significant differences in AIP levels between AMI and non-AMI groups, smokers and non-smokers, and individuals with and without diabetes (<i>p</i> &lt; 0.05). The novelty of the present study lies in the application of SVR to predict AIP using commonly available clinical and biochemical parameters, even in the absence of triglycerides (TG) and HDL values, which are traditionally required for AIP calculation. The model achieved robust performance, with an R<sup>2</sup> of 0.8062, RMSE of 0.0714, and MAE of 0.2053, thus effectively capturing complex nonlinear relationships. This machine learning-based approach offers a promising tool for early cardiovascular risk assessment, particularly in settings with limited access to full lipid profiles. By affirming AIP as a predictive biomarker rather than merely a diagnostic lipid index, the study emphasizes explicit clinical relevance of AIP in expediting cardiovascular risk assessment.</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

Predicting Atherogenic Index of Plasma Using Support Vector Regression for Cardiovascular Risk Assessment

  • 期刊论文

  • 发表日期：

    2025年10月21日

查看全文
  • Tamanna Maji,
  • Arpit Mehrotra

摘要

The Atherogenic Index of Plasma (AIP) is emerging as a valuable marker in cardiovascular risk profiling, particularly among patients with Acute Myocardial Infarction (AMI). The present study investigates the association between AIP and a range of clinical parameters while introducing a novel predictive approach using Support Vector Regression (SVR). A cohort of 340 individuals, including 267 AMI patients and 73 healthy controls, were analyzed for biochemical parameters such as: lipid profile, fasting blood glucose, blood pressure, uric acid, and creatinine. Pearson correlation analysis identified significant relationships between AIP and LDL-C (r = 0.429, p < 0.001), total cholesterol (r = 0.14, p = 0.01), and fasting blood glucose (r = 0.108, p = 0.047), whereas other parameters showed no significant correlations (p > 0.05). Z-test results further confirmed significant differences in AIP levels between AMI and non-AMI groups, smokers and non-smokers, and individuals with and without diabetes (p < 0.05). The novelty of the present study lies in the application of SVR to predict AIP using commonly available clinical and biochemical parameters, even in the absence of triglycerides (TG) and HDL values, which are traditionally required for AIP calculation. The model achieved robust performance, with an R2 of 0.8062, RMSE of 0.0714, and MAE of 0.2053, thus effectively capturing complex nonlinear relationships. This machine learning-based approach offers a promising tool for early cardiovascular risk assessment, particularly in settings with limited access to full lipid profiles. By affirming AIP as a predictive biomarker rather than merely a diagnostic lipid index, the study emphasizes explicit clinical relevance of AIP in expediting cardiovascular risk assessment.