Quantum Machine Learning for Early Disease Diagnosis: A Systematic Review and Public Health Innovation Perspective
1 Master's in Information Technology Management, St Francis College, New York, USA.
2 Master's in Information System Security, University of the Cumberlands, Williamsburg, Kentucky, USA.
3 Master’s of Science in Information Technology, Washington University of Science & Technology (WUST), Virginia, USA.
4 Master of Science in Information Technology (MSIT), Washington University of Science and Technology, Alexandria, Virginia, USA.
5 Master's in Information Technology and Management, Campbellsville University, Kentucky, USA.
6 Master's in Information Technology, Washington University of Science and Technology, Virginia, USA.
7 Professor of Cybersecurity, Washington University of Science and Technology, Virginia, USA.
Review Article
World Journal of Advanced Research and Reviews, 2023, 19(01), 1668-1674
Publication history:
Received on 31 May 2023; revised on 23 July 2023; accepted on 29 July 2023
Abstract:
Prompt diagnosis of disease is a key determinant in reducing mortality, improving patient care and decreasing healthcare costs. Despite the success of classical machine learning (ML) in improving predictive modeling across oncology, cardiology, and neurology, growing data dimensionality and computational complexity remain ongoing barriers. Quantum computing based on superposition and entanglement is a promising computational paradigm that shows potential advantages in high-dimensional pattern recognition and kernel-based learning. This review aims to systematically summarize preliminary work on quantum machine learning (QML) with empirical applications for early disease diagnosis, focusing on its theoretical underpinnings in addition to its algorithmic design and use in healthcare. We then frame the discussion with respect to quantum support vector machines and variational quantum classifiers, quantum kernels, as well as hybrid quantum–classical architectures. We further evaluate existing hardware constraints in the noisy intermediate-scale quantum (NISQ) era and appraise translational maturity for integration into public health. While clinical deployment is still far from broad, hybrid QMLs are proving useful in low-data and complex-feature contexts. We end with research challenges, regulatory guidance, and strategic directions towards enabling quantum-enhanced precision diagnostics aligned with U.S. public health innovation initiatives.
Keywords:
Quantum Machine Learning; Quantum SVM; classifiers; Quantum modelling
Full text article in PDF:
Copyright information:
Copyright © 2023 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0