Quantum-Enhanced Multi-Modal Cardiac Biomarker Analysis for Cardiovascular Disease Risk Prediction

College

College of Engineering & Technology (Batten)

Department

Electrical and Computer Engineering

Graduate Level

Doctoral

Presentation Type

No Preference

Abstract

Cardiovascular disease (CVD) remains a major global health challenge, necessitating advanced predictive models for early detection and risk assessment. This paper presents a quantum-enhanced machine learning framework for multi-modal cardiac biomarker analysis. The model integrates quantum feature encoding with a deep learning-based classification pipeline. Multi-modal data from imaging, electrophysiological signals, and genetic biomarkers are mapped into quantum-enhanced feature spaces using Cirq. These transformed features are then fed into a hybrid quantum-classical neural network (QNN) to improve prediction accuracy. The proposed approach is benchmarked against classical machine learning methods such as Support Vector Machines (SVM) and Random Forest (RF). Results show the potential of quantum computing in advancing precision medicine by leveraging high-dimensional feature transformations.

Keywords

Quantum Machine Learning, Cardiovascular Disease Prediction, Quantum Neural Networks, Multi-Modal Biomarker Analysis, Hybrid Quantum-Classical Models, Quantum Feature Encoding, Explainable AI (XAI)

This document is currently not available here.

Share

COinS
 

Quantum-Enhanced Multi-Modal Cardiac Biomarker Analysis for Cardiovascular Disease Risk Prediction

Cardiovascular disease (CVD) remains a major global health challenge, necessitating advanced predictive models for early detection and risk assessment. This paper presents a quantum-enhanced machine learning framework for multi-modal cardiac biomarker analysis. The model integrates quantum feature encoding with a deep learning-based classification pipeline. Multi-modal data from imaging, electrophysiological signals, and genetic biomarkers are mapped into quantum-enhanced feature spaces using Cirq. These transformed features are then fed into a hybrid quantum-classical neural network (QNN) to improve prediction accuracy. The proposed approach is benchmarked against classical machine learning methods such as Support Vector Machines (SVM) and Random Forest (RF). Results show the potential of quantum computing in advancing precision medicine by leveraging high-dimensional feature transformations.