EUVIMEDEUVIMED entdecken
Crossref

A Comparative Performance Analysis of Machine Learning Models for Cardiovascular Disease Prediction Using Hyper Parameter Tuning

Maitri Bhavsar, Manish Patel

SPU - Journal of Science, Technology and Management Research · 01.07.2026 · 35-42

DOI: 10.63766/spujstmr.26.000071 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SPU - Journal of Science, Technology and Management Research, online erschienen am 01.07.2026. Verfasst von Maitri Bhavsar und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cardiovascular disease (CVD) remains one of the leading causes of mortality worldwide, demanding reliable and early prediction systems. This study proposes an optimized machine learning framework that integrates advanced data pre processing, dimensionality reduction, class balancing, and hyper parameter tuning to enhance CVD prediction accuracy. A combined dataset of 920 patient records from multiple clinical sources was cleaned, standardized, and processed using Principal Component Analysis (PCA) to reduce redundancy and multi collinearity among correlated medical attributes. Class imbalance was addressed using SMOTE, significantly improving minority class sensitivity. Six machine learning classifiers including Random Forest, Gradient Boosting, SVC, Decision Tree, AdaBoost, and an Ensemble Classifier were trained and evaluated under four configurations: with or without PCA and with or without hyper parameter tuning via Grid SearchCV. Results demonstrate that the integration of PCA and tuning consistently improvedmodel performance, with the Ensemble Classifier and Random Forest achieving accuracies and F1-scores. Significant improvements in recall and ROC-AUC values indicate better discriminatory power, especially for disease positive cases. Overall, the proposed pipeline provides a robust, generalizable approach for CVD prediction and highlights the importance of dimensionality reduction, data balancing, and parameter optimization in developing clinically reliable diagnostic models.

Zitieren

APA

Bhavsar, M., & Patel, M. (2026). A Comparative Performance Analysis of Machine Learning Models for Cardiovascular Disease Prediction Using Hyper Parameter Tuning. SPU - Journal of Science, Technology and Management Research, 35-42. https://doi.org/10.63766/spujstmr.26.000071

Vancouver

Bhavsar M, Patel M. A Comparative Performance Analysis of Machine Learning Models for Cardiovascular Disease Prediction Using Hyper Parameter Tuning. SPU - Journal of Science, Technology and Management Research. 2026:35-42. doi:10.63766/spujstmr.26.000071

BibTeX
@article{Bhavsar2026,
  author = {Bhavsar, Maitri and Patel, Manish},
  title = {A Comparative Performance Analysis of Machine Learning Models for Cardiovascular Disease Prediction Using Hyper Parameter Tuning},
  journal = {SPU - Journal of Science, Technology and Management Research},
  year = {2026},
  pages = {35--42},
  doi = {10.63766/spujstmr.26.000071}
}
Kostenlos starten →