Novel Quantum Computing Model Reaches Precision Milestone in Early Heart Disease Detection

Cardiovascular disease remains a major global health challenge, causing millions of deaths each year and imposing substantial healthcare costs. Early, accurate diagnosis is critical for improving outcomes and enabling timely intervention.

While conventional machine learning has shown promise in disease prediction, it often struggles with highly complex and nonlinear clinical data.

A research group from the College of Engineering and Computer Science at Florida Atlantic University, led by Arslan Munir, Ph.D., professor in FAU's Department of Electrical Engineering and Computer Science and director of the Intelligent Systems, Computer Architecture, Analytics, and Security (ISCAAS) Laboratory, have developed a novel quantum machine learning framework that significantly improves heart disease prediction, achieving more than 90% accuracy.

The study, published in the MDPI AI Journal (impact factor of 6.5), presents a comprehensive evaluation of quantum feature mapping and quantum classification techniques for heart disease prediction, and demonstrates the potential of quantum machine learning to enhance healthcare analytics and clinical decision support systems.

Using clinical data from 918 patients, the research group evaluated systematically five quantum feature mapping techniques and four quantum machine learning classifiers to identify the most effective approach for heart disease diagnosis. The best-performing model, a Quantum Support Vector Machine using Angle Encoding, achieved 90.26% accuracy, 92.16% sensitivity, 83.42% specificity, and an AUC of 0.93, highlighting its potential for accurate heart disease prediction.