Fathima M Dhilsath, Raja S P, Jayanthi K, Hariharan R
Department of Information Technology, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai, Tamil Nadu, India.
School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India.
Inflamm Res. 2025 May 31;74(1):88. doi: 10.1007/s00011-025-02039-y.
Cardiovascular diseases (CVD) are a leading cause of morbidity and mortality globally, highlighting the urgent need for accurate risk prediction to improve early intervention and management. Traditional models have difficulty capturing the complex interactions between risk factors, which limits their predictive power.
This paper proposes the OptiStack Classifier, an optimized stacking framework developed to enhance CVD risk prediction through ensemble feature engineering and machine learning techniques.
The model uses dimensionality reduction and ensemble feature engineering methods, including polynomial expansion, binning and domain-specific feature transformation, to improve data representation. Principal Component Analysis (PCA) is used to dimensionality reduction, improving computational efficiency. A stacking framework integrates multiple machine learning algorithms as base learners, with Logistic Regression acting as the meta-classifier. Bayesian Optimization is applied for hyperparameter tuning, further boosting predictive performance.
The proposed model shows significant improvements in predicting CVD risk, helping with early diagnosis and prevention, which can lead to better health outcomes for patients.
心血管疾病（CVD）是全球发病和死亡的主要原因，凸显了准确风险预测以改善早期干预和管理的迫切需求。传统模型难以捕捉风险因素之间的复杂相互作用，这限制了它们的预测能力。
本文提出了OptiStack分类器，这是一种通过集成特征工程和机器学习技术开发的优化堆叠框架，用于增强心血管疾病风险预测。
该模型使用降维和集成特征工程方法，包括多项式扩展、分箱和特定领域特征转换，以改善数据表示。主成分分析（PCA）用于降维，提高计算效率。一个堆叠框架集成多个机器学习算法作为基学习器，逻辑回归作为元分类器。应用贝叶斯优化进行超参数调整，进一步提高预测性能。
所提出的模型在预测心血管疾病风险方面显示出显著改进，有助于早期诊断和预防，可为患者带来更好的健康结果。
