Early and accurate anomaly detection in Intensive Care Unit (ICU) monitoring is vital for improving patient outcomes and reducing mortality. Traditional machine learning techniques often face challenges in handling the noisy, high-dimensional, and limited datasets characteristic of ICU physiological signals. In this study, we present an early investigation of a quantum-enhanced framework employing a classically simulated Quantum Support Vector Machine (QSVM) to improve the detection of critical anomalies in real-world ICU time-series data. Utilizing the publicly available PhysioNet 2012 Challenge dataset, we extract comprehensive statistical and temporal features from vital signs including heart rate, blood pressure, respiratory rate, and oxygen saturation. Our QSVM model leverages a quantum kernel mapped via Qiskit’s ZZFeatureMap and is rigorously benchmarked against classical machine learning classifiers such as Support Vector Machines with radial basis function kernels, Random Forest, and XGBoost. Experimental results demonstrate that the QSVM shows competitive and robust classification performance, particularly excelling in scenarios with limited and noisy data, with an AUC of 0.92, particularly excelling in scenarios with limited and noisy data. Furthermore, the quantum kernel’s ability to implicitly project data into a high-dimensional Hilbert space provides enhanced separability of complex physiological patterns. This work constitutes one of the first simulation-based applications of quantum machine learning to critical care anomaly detection, underscoring the promise of hybrid quantum-classical approaches for advancing real-time clinical decision support systems.
Early and accurate anomaly detection in Intensive Care Unit (ICU) monitoring is vital for improving patient outcomes and reducing mortality. Traditional machine learning techniques often face challenges in handling the noisy, high-dimensional, and limited datasets characteristic of ICU physiological signals. In this study, we present an early investigation of a quantum-enhanced framework employing a classically simulated Quantum Support Vector Machine (QSVM) to improve the detection of critical anomalies in real-world ICU time-series data. Utilizing the publicly available PhysioNet 2012 Challenge dataset, we extract comprehensive statistical and temporal features from vital signs including heart rate, blood pressure, respiratory rate, and oxygen saturation. Our QSVM model leverages a quantum kernel mapped via Qiskit’s ZZFeatureMap and is rigorously benchmarked against classical machine learning classifiers such as Support Vector Machines with radial basis function kernels, Random Forest, and XGBoost. Experimental results demonstrate that the QSVM shows competitive and robust classification performance, particularly excelling in scenarios with limited and noisy data, with an AUC of 0.92, particularly excelling in scenarios with limited and noisy data. Furthermore, the quantum kernel’s ability to implicitly project data into a high-dimensional Hilbert space provides enhanced separability of complex physiological patterns. This work constitutes one of the first simulation-based applications of quantum machine learning to critical care anomaly detection, underscoring the promise of hybrid quantum-classical approaches for advancing real-time clinical decision support systems.
Sepsis and the development of multi-organ failure still constitute significant causes of death in the ICU, hence the necessity to develop predictive systems that could detect the fact of subtle physiological deviations before clinical deterioration. Despite the potential of classical machine learning models, including logistic regression, random forests and deep neural networks to predict sepsis, they frequently encounter challenges with large-dimensional ICU time-series data, nonlinear interaction of features and ability to predict sepsis at an early stage. These also models are sensitive to missing values and have limited cross-hospital generalizability and high rates of false-alarms which makes them difficult to implement in clinical settings, this paper proposes a Quantum-Assisted Early Warning System (QAEWS) based on quantum feature encoding and hybrid quantum-classical based learning models that provides better early sepsis and organ dysfunction detection. Amplitude and phase encoding the ICU physiological measures, lab measurements, and short-term vital sign traces are encoded into quantum-enhanced representations, which allow complexer modeling of complicated time-dependent relationships in a high-dimensional Hilbert space. The predictive architecture combines the Quantum Support Vector Machines (QSVM) and Quantum Neural Networks (QNN) and supplemented by the classical neural layers to improve classification accuracy and false alerts. Model performance was compared with the Logistic Regression, Random Forest, XGBoost, and LSTM models using the same feature sets in the MIMIC-IV and eICU datasets. The quantum-assisted framework achieved a 7–12% increase in AUROC, a 14–18% reduction in false alarms, and provided predictions 1.5–2.8 hours earlier than classical baselines. Sensitivity at 85% specificity improved by 10–15%. These results demonstrate that quantum-enhanced feature spaces offer superior discrimination of early sepsis patterns, establishing QAEWS as a robust and clinically valuable approach for real-time ICU early warning.
Cardiovascular disease (CVD) is the leading cause of global mortality, with over 19.8 million deaths recorded in 2022, underscoring the urgent necessity for precise early-stage computational diagnostic techniques. The traditional machine learning approaches tend to fail in the nonlinear feature interactions of high-dimensional clinical data. This paper provides a Quantum Support Vector Machine (QSVM) framework that uses a fidelity-based quantum kernel, calculated using PennyLane Lightning, and a qubit simulator to map patient data into a high-dimensional Hilbert space, enabling complex feature interactions that are unattainable with traditional kernels. The model was tested on a publicly available UCI-based heart disease dataset that included 1,025 patient records and 13 clinical features, such as chest pain type, ST depression, maximum heart rate, and thalassemia test results, with a near-balanced distribution between the classes (51.3% positive, 48.7% negative). All 13 features were represented in quantum states with a Hadamard-RY feature map applied to 13 qubits, and quantum pipelining was used to perform batch executions of the feature map and reduce simulation overhead. The QSVM achieved 93.90% accuracy, outperforming the classical SVM baseline, which achieved 92.50% on the same dataset. Complexity analysis shows O(d) depth, linear qubit scaling, and NISQ-compatible scalable quantum biomedical diagnostics.
Timely clinical intervention at the early stage for detecting widespread psychological health issues such as depression and anxiety is essential. Conventional diagnostic approaches that are generally based on subjective questionnaires face limitations which can result in delays as well as imprecisions. Current data-driven methodologies employ features that are extracted from multiple sources (behavioural surveys, clinical attributes and physiological signals excluding EEG and ECG). Although known classical ML models such as RF and LR are effective, the limitations of these models on capturing extremely complex non-linear issues result in their performance being limited. This performance upper bound is validated by the combined classical benchmark accuracy of 86.59%. This paper introduces a new quantum hybrid support vector machine (QSVM) framework, and shows how it can dramatically improve prediction accuracy on such mental health conditions. The system uses a hybrid design, in which the classical processing part computes and sends out a processed feature map to be quantum mapped into a Q exponentially larger-dimensional Hilbert space through quantum kernel methods (Quantum Feature Maps). By taking advantage of the quantum effects, the QSVM implicitly computes kernels that are difficult for classical machines and allows achieving better classification boundaries. The accuracy of QSVM is critically evaluated against the RF and LR benchmarks. Thus The Hybrid QSVM shows preliminary signs of quantum advantage, particularly in precision and kernel separability, although accuracy remains comparable to classical baselines. Validation on real quantum hardware will be required to establish practical quantum advantage.
Quantum machine learning (QML) offers a promising framework for analyzing complex, high-dimensional biomedical data, yet rigorous benchmarking on real-world clinical datasets remains limited. In this study, we evaluate a quantum support vector machine (QSVM) for agitation detection using the Technology Integrated Health Management (TIHM) smart-home dementia dataset. The proposed QSVM uses a 13-qubit fidelity-based feature map with two degrees of freedom in angle encoding to process the same 26 features used by the strongest classical baselines under a subject-independent evaluation protocol. Across seven ID-disjoint trials, the QSVM achieves a weighted F1-score of0.92±0.06, with consistently high precision of0.93±0.06and recall of0.91±0.06. These results demonstrate that quantum kernel methods can match or exceed state-of-the-art classical performance while providing a reproducible benchmark for cognitive-health prediction. This work lays the foundation for future exploration of hybrid quantum–classical models and clinical decision-support applications in behavioral health monitoring.
Classical machine learning, extensively utilized across diverse domains, faces limitations in speed, efficiency, parallelism, and processing of complex datasets. In contrast, quantum machine learning algorithms offer significant advantages, including exponentially faster computations, enhanced data handling capabilities, inherent parallelism, and improved optimization for complex problems. In this study, we used the entanglement enhanced quantum kernel in a quantum support vector machine to train complex respiratory datasets. Compared to classical algorithms, our findings reveal that quantum support vector machine (QSVM) performs better with higher accuracy (45%) for complex respiratory datasets while maintaining comparable performance with linear datasets in contrast to their classical counterparts executed on a 2-qubit system. Through our study, we investigate the efficacy of the QSVM-Kernel algorithm in harnessing the enhanced dimensionality of the quantum Hilbert space for effectively training complex datasets.
Cardiovascular diseases remain the leading cause of mortality globally, necessitating accurate diagnostic tools for early detection and intervention. This paper presents a comprehensive comparative and hybrid analysis of quantum and classical machine learning models for heart disease prediction using the UCI Cleveland dataset. We implement classical baseline models including Logistic Regression, Random Forest, Support Vector Machine (SVM), and XGBoost, alongside quantum models: Quantum Support Vector Machine (QSVM) with statevector fidelity kernels, Variational Quantum Classifier (VQC) with data-reuploading ansätze, and Quantum Convolutional Neural Networks (QCNN) with parametric pooling. The primary contribution is the development of a hybrid quantum classical ensemble meta-classifier that fuses predictions from all classical and quantum learners using XGBoost as a meta learner. Experiments conducted in Google Colab using Qiskit 1.2+ and Penny Lane 0.36+ demonstrate that the proposed hybrid ensemble achieves superior performance with 98.33accuracy, 100perfect AUC-ROC of 1.0, substantially outperforming standalone classical models (best: 88.33(best: 80hybrid model’s superiority. These results underscore the potential of quantum feature spaces combined with classical decision boundaries in healthcare prediction systems, and demonstrate the immediate utility of hybrid quantum-classical integration in medical diagnostics on near-term quantum hardware.