Background. Speech and audio understanding underpin affective computing, human–computer interaction, and clinical decision support. Classical deep-learning systems for tasks such as speech emotion recognition (SER) are increasingly bound by data demand, parameter scale, and cross-corpus brittleness. Quantum machine learning (QML) offers a complementary paradigm for high-dimensional, temporally structured signals but has not been systematically synthesised. Methods. We conducted a PRISMA-aligned systematic review of QML methods applied to speech and audio understanding. Six databases (IEEE Xplore, ACM, Scopus, Web of Science, PubMed, arXiv) were searched for studies published between January 2019 and April 2026. Of 2,623 deduplicated records, 55 were confirmed as primary (Tier-1) evidence, with 272 retained as adjacent or backbone evidence. Each Tier-1 study was scored against an eight-question quality instrument and entered into a comprehensive comparison matrix. Results. The corpus splits into 16 SER studies, 24 other speech tasks, and 15 general audio and music studies. Variational and parameterised quantum circuits (18 studies), quantum kernel methods (9), and quantum convolutional networks (8) dominate. Three structural weaknesses recur: aggressive classical preprocessing precedes quantum encoding in nearly every study; 26/55 score zero on NISQ-noise consideration; only 2 perform a formal significance test for the central quantum-versus-classical comparison. Conclusion. The field is in early but rapid and uneven growth (with annual outputs ranging from 2 to 16 papers across 2019–2025) but not yet ready to displace classical foundation models. We synthesise a method-by-task taxonomy and three-horizon research roadmap, and operationalise an eight-item benchmarking protocol as a community call to address recurrent reliability gaps and help raise the floor of QML–audio research.
Background. Speech and audio understanding underpin affective computing, human–computer interaction, and clinical decision support. Classical deep-learning systems for tasks such as speech emotion recognition (SER) are increasingly bound by data demand, parameter scale, and cross-corpus brittleness. Quantum machine learning (QML) offers a complementary paradigm for high-dimensional, temporally structured signals but has not been systematically synthesised. Methods. We conducted a PRISMA-aligned systematic review of QML methods applied to speech and audio understanding. Six databases (IEEE Xplore, ACM, Scopus, Web of Science, PubMed, arXiv) were searched for studies published between January 2019 and April 2026. Of 2,623 deduplicated records, 55 were confirmed as primary (Tier-1) evidence, with 272 retained as adjacent or backbone evidence. Each Tier-1 study was scored against an eight-question quality instrument and entered into a comprehensive comparison matrix. Results. The corpus splits into 16 SER studies, 24 other speech tasks, and 15 general audio and music studies. Variational and parameterised quantum circuits (18 studies), quantum kernel methods (9), and quantum convolutional networks (8) dominate. Three structural weaknesses recur: aggressive classical preprocessing precedes quantum encoding in nearly every study; 26/55 score zero on NISQ-noise consideration; only 2 perform a formal significance test for the central quantum-versus-classical comparison. Conclusion. The field is in early but rapid and uneven growth (with annual outputs ranging from 2 to 16 papers across 2019–2025) but not yet ready to displace classical foundation models. We synthesise a method-by-task taxonomy and three-horizon research roadmap, and operationalise an eight-item benchmarking protocol as a community call to address recurrent reliability gaps and help raise the floor of QML–audio research.
Objectives: The convergence of quantum computing, quantum machine learning, and quantum mechanical principles represents an emerging paradigm in medical physics. Classical methods encounter hard limits in treatment planning, molecular-scale drug simulation, and medical image interpretation. The four quantum phenomena superposition, entanglement, quantum tunneling, and quantum coherence offer distinct routes around these barriers through both hardware sensing and algorithmic frameworks.To systematically identify, appraise, and synthesise evidence on applications of quantum computing, quantum machine learning, and quantum mechanical principles in medical physics, mapping the evidence base, assessing clinical readiness, and proposing a research roadmap.Materials and Methods: A PRISMA 2020-compliant systematic search was conducted across PubMed/MEDLINE, Scopus, IEEE Xplore, Web of Science, arXiv, and bioRxiv (January 2015 – March 2026). Two independent reviewers screened 5,248 identified records. After deduplication, screening, and eligibility assessment, 133 studies were included in the qualitative synthesis and 89 in the quantitative performance comparison. Methodological quality was assessed using a modified CLAIM checklist and QUADAS-2 framework.Results: Four application clusters emerged. Superposition underpins hyperpolarized ¹³C MRI (technology readiness level (TRL) 7) and hybrid quantum CNN architectures. Entanglement enables OPM-MEG neuroimaging (TRL 6–7) and quantum kernel classification. Quantum tunneling drives radiotherapy optimisation (TRL 4–5). Quantum coherence supports variational algorithms for drug discovery (TRL 2–3) and quantum dot theranostics (TRL 3–4). Hybrid quantum–classical methods outperformed classical baselines, though most studies showed high risk of bias.Conclusions: Quantum-enhanced sensing and hybrid quantum–classical treatment planning are credible near-term clinical translation targets. Fault-tolerant drug simulation and large-scale quantum AI await hardware maturation beyond 2030. Critical enablers include standardised benchmarking, quantum-specific regulatory guidance, and equity planning.
This research project presents a PRISMA-guided systematic literature review exploring the application of quantum machine learning (QML) in oncology, a rapidly growing field with fragmented evidence. The study synthesizes peer-reviewed studies from six databases (ACM, IEEE, MDPI, Scopus, Wiley, and PubMed) published between 2020 and 2026, screening 212 records and selecting 49 studies for analysis. The review examines clinical tasks, cancer domains, QML architectures, challenges, and future directions, revealing that current research mainly focuses on classification and detection, particularly in breast cancer and brain tumors, using hybrid quantum-classical models. Despite promising results, progress is limited by hardware constraints, simulator dependence, and insufficient clinical validation. The findings provide a clear overview of current QML trends and highlight future priorities, including real quantum hardware testing, diverse clinical datasets, standardized benchmarking, and stronger collaboration between computing and oncology communities.
Quantum Machine Learning (QML) has emerged as a promising interdisciplinary paradigm that integrates quantum computing and machine learning to address limitations of classical approaches in processing complex high-dimensional heterogeneous and imbalanced medical data. This study presents a systematic literature review of QML applications in healthcare based on 94 primary studies published between 2020 and April 2025. The review follows Kitchenham’s guidelines and the PRISMA framework to ensure rigor transparency and reproducibility. Seven research questions were formulated to examine publication trends sources datasets topics quantum model categories algorithms methods and evaluation metrics. Findings reveal a sharp increase in publication activity after 2023 indicating growing academic interest in healthcare-oriented QML. Medical imaging datasets were most frequently used followed by signal-based and tabular datasets with 86.5% of studies relying on public data. Hybrid classical-quantum approaches including CNN-QSVM Quantum Neural Networks and Variational Quantum Classifiers were dominant because they combine classical feature extraction with quantum-enhanced learning. However most studies were conducted in simulation environments rather than real hardware reflecting NISQ limitations including noise decoherence limited qubits and circuit depth constraints. Many results used small curated or imbalanced datasets raising concerns regarding generalizability reproducibility and clinical validity. Although numerous studies reported high accuracy standardized evaluation protocols external validation and uncertainty assessment remain limited. Overall QML in healthcare remains exploratory with substantial potential but significant barriers. This review highlights progress gaps and future directions emphasizing clinically representative datasets robust benchmarking interpretable noise-resilient models and real-hardware implementation to support trustworthy deployment in healthcare systems worldwide settings today.
Quantum machine learning (QML) has emerged as a promising approach for analyzing the complex, high-dimensional data encountered in oncology, yet research in this area remains fragmented. This systematic literature review synthesizes current applications of QML in cancer care. Following PRISMA guidelines, six databases were searched for peer-reviewed English-language studies published between 2020 and 2026. Of the 212 records identified, 49 studies met the inclusion criteria after screening and quality assessment. The findings show that QML research is dominated by classification and detection tasks, while segmentation is beginning to emerge. Breast cancer and brain tumors are the most frequently investigated domains. Hybrid quantum-classical models, particularly quantum kernel methods, quantum neural networks, and quantum convolutional neural networks, are the predominant approaches. The main barriers to adoption are hardware limitations, including quantum noise, limited qubit availability, and reliance on simulators. Overall, QML in oncology remains in its early stages of development, with limited clinical validation, insufficient model interpretability, and little evidence of a clear quantum advantage. Future research should prioritize evaluation on real quantum hardware, larger and more diverse clinical datasets, standardized benchmarking against classical methods, and closer collaboration between computer scientists and oncology experts to facilitate clinical translation.
Abstract This study explores Quantum AI’s potential in enhancing Speech Emotion Recognition (SER) systems. Our primary objective is to evaluate the performance of quantum-inspired algorithms compared to classical machine-learning approaches in accurately identifying and classifying emotions from speech signals. We hypothesise that quantum computing techniques can improve the efficiency and accuracy of emotion recognition, particularly in handling complex, highdimensional acoustic data. We developed a hybrid quantum-classical model that combines quantum-inspired neural networks with traditional feature extraction techniques. Our approach utilises quantum circuits for data encoding and quantum variational algorithms for classification. We implemented quantum versions of support vector machines (QSVM) and quantum approximate optimisation algorithms (QAOA) for emotion classification tasks. These quantum methods were compared against a hybrid Convolutional Neural Network and Long Short Term (LSTM). The hybrid network is called a Convolutional Long Short Term network(CLSTM). The study employed a custom dataset for speech emotion recognition. We prepossessed the audio data to extract relevant acoustic features, including mel-frequency cepstral coefficients (MFCCs), pitch, and energy. In contrast, our implemented quantum-inspired model for this corpus showed lower performance, with the highest training accuracy of 30%, struggling with most emotions but performing best with ’Trust’. These varied results across different implementations suggest that while Quantum AI techniques show promise in advancing speech emotion recognition, their effectiveness may depend on the specific dataset, language, and model architecture used. Finally, the speed of a simulated quantum network is shown to outperform current methods in terms of matrix multiplication by leaps and bounds.
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.