����Vlog

A research group from ����Vlog’s College of Engineering and Computer Science, led by Arslan Munir, Ph.D., has developed a quantum machine learning framework for heart disease prediction that achieved more than 90% accuracy. Using clinical data from 918 patients, the research group systematically evaluated five quantum feature-mapping techniques and four quantum machine learning classifiers. 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.

The findings suggest the potential of quantum machine learning to capture complex patterns in clinical data and support more accurate disease prediction. The researchers used shallow quantum circuits designed for near-term quantum computing architectures, providing a foundation for future quantum-enabled healthcare applications.

“Our research demonstrates that quantum machine learning can serve as a powerful new paradigm for healthcare analytics,” said Munir. “By leveraging quantum feature representations and quantum-enhanced classifiers, we can model intricate relationships within clinical data more effectively, enabling highly accurate prediction of heart disease. As quantum technologies continue to mature, they have the potential to transform how we diagnose diseases, personalize treatments, and support clinical decision-making.”

Read the press release.