Interaction Driven Quantum Kernel Support Vector Machine Framework for Robust Cardiovascular Risk Detection

Authors

  • Pavithra R Author
  • Dr. S. Srividhya Author

Keywords:

Quantum Kernel Support Vector Machine - Cardiovascular Disease Risk Prediction - Quantum Feature Encoding - Interaction Aware Representation - Clinical Data Classification

Abstract

Cardiovascular diseases remain a major challenge in healthcare, requiring accurate and early risk identification to support preventive intervention. Reliable prediction demands models capable of capturing complex relationships among physiological and lifestyle attributes. Conventional machine learning approaches face limitations in representing nonlinear dependencies within clinical data. To address this challenge, a Quantum Kernel Support Vector Machine (QK-SVM) framework is proposed for cardiovascular risk classification. The approach transforms clinical features into quantum states through parametric encoding, enabling interaction aware representation using entanglement mechanisms. A Quantum Feature Interaction Index is introduced to quantify relational dependencies among encoded attributes, strengthening similarity evaluation. The resulting quantum kernel matrix reflects enriched feature interactions and supports margin-optimized classification within a high-dimensional space. The framework maintains alignment with clinical data characteristics while enhancing representation fidelity and decision boundary formation. This structured integration of quantum feature mapping and support vector learning establishes an effective methodology for cardiovascular risk screening in intelligent healthcare systems.

Downloads

Download data is not yet available.

Downloads

Published

2026-09-22

How to Cite

Interaction Driven Quantum Kernel Support Vector Machine Framework for Robust Cardiovascular Risk Detection. (2026). Minimax Theory and Its Applications, 11(2s), 907-927. https://journalmta.com/index.php/jmta/article/view/462