Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{204007,
        author = {Manoj Dhiman},
        title = {Quantum Machine Learning for Alzheimer’s Disease Diagnosis: A Critical Appraisal of Quantum-Advantage Claims},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {799-807},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204007},
        abstract = {Quantum machine learning (QML) has been advanced as a route to faster and more accurate diagnosis of Alzheimer’s disease (AD), and a rapidly growing body of primary studies reports near-perfect classification accuracies. This paper systematically identifies peer-reviewed primary studies applying genuine quantum methods to AD or mild cognitive impairment diagnosis and critically appraises the evidential basis of their quantum-advantage claims. Following PRISMA 2020, six databases were searched, yielding 865 records; fifteen studies met all criteria. Everyone was executed on a classical simulator, none reported unambiguous results on real quantum hardware, and only one modelled device noise. Datasets were frequently very small and ten of the eleven MRI-based studies used slice-level rather than subject-level splits, creating a tangible data-leakage risk. Seven studies reported accuracies at or above 98%, yet classical baselines were weak or effectively absent in a substantial minority, and only five of fifteen reported any measure of statistical uncertainty. The most methodologically careful study found an advantage smaller than its own error bars, and another reported near-chance performance. The AD-specific QML literature does not currently provide credible evidence of a quantum advantage; we propose a reporting standard to place the field on a sounder evidential footing.},
        keywords = {Alzheimer’s disease, data leakage, neuroimaging, quantum machine learning, systematic review.},
        month = {June},
        }