Gupta Riddhi S, Wood Carolyn E, Engstrom Teyl, Pole Jason D, Shrapnel Sally
School of Mathematics and Physics, The University of Queensland, St Lucia, 4067, QLD, Australia.
QDHeC. Centre for Health Services Research. Faculty of Medicine, The University of Queensland, Herston, 4006, QLD, Australia.
NPJ Digit Med. 2025 May 2;8(1):237. doi: 10.1038/s41746-025-01597-z.
The growth in digitization of health data provides opportunities for using algorithmic techniques for data analysis. This systematic review assesses whether quantum machine learning (QML) algorithms outperform existing classical methods for clinical decisioning or health service delivery. Included studies use electronic health/medical records, or reasonable proxy data, and QML algorithms designed for quantum computing hardware. Databases PubMed, Embase, IEEE, Scopus, and preprint server arXiv were searched for studies dated 01/01/2015-10/06/2024. Of an initial 4915 studies, 169 were eligible, with 123 then excluded for insufficient rigor. Only 16 studies consider realistic operating conditions involving quantum hardware or noisy simulations. We find nearly all encountered quantum models form a subset of general QML structures. Scalability of data encoding is partly addressed but requires restrictive hardware assumptions. Overall, performance differentials between quantum and classical algorithms show no consistent trend to support empirical quantum utility in digital health.
健康数据数字化的发展为使用算法技术进行数据分析提供了机会。本系统综述评估了量子机器学习（QML）算法在临床决策或医疗服务提供方面是否优于现有的经典方法。纳入的研究使用电子健康/医疗记录或合理的替代数据，以及为量子计算硬件设计的QML算法。检索了数据库PubMed、Embase、IEEE、Scopus和预印本服务器arXiv中2015年1月1日至2024年6月10日的研究。在最初的4915项研究中，169项符合条件，其中123项因严谨性不足而被排除。只有16项研究考虑了涉及量子硬件或噪声模拟的实际运行条件。我们发现几乎所有遇到的量子模型都是一般QML结构的一个子集。数据编码的可扩展性部分得到了解决，但需要严格的硬件假设。总体而言，量子算法和经典算法之间的性能差异没有显示出支持数字健康中经验性量子效用的一致趋势。
