Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN)

Investigating the Use of Quantum Feature Maps to Phenotype Asthma: A Comparative Study to Classical ML Phenotypes

V. Savithiri

Published Apr 16, 2026• 0 citations
Publisher

Abstract

Millions of individuals are affected by asthma globally in that there is an urgent need to have accurate prediction systems in order to allow an early intervention and increase the patient outcome. This paper provides an extensive comparison of classical machine learning models and quantum machine learning methods to predict asthma and assess their viability to be used in clinical practice. Our data consisted of 50,000 patient records, consisting of 16 clinical features (symptoms, demographics, and severity indicators) and applied six classical models (Random Forest, Gradient Boosting, Support Vector Machine, Neural Network, Logistic Regression, K-Nearest Neighbors). We used standardised preprocessing and evaluation procedures to test Quantum Support Vector Machine on$\mathbf{5 0, 0 0 0}$patient records. Quantum SVM was found to be most accurate with 75.69 and closely second with classical SVM, Gradient Boosting and Logistic Regression, which had 75.16. All the most effective models had the perfect recall$(100 \%)$, which provided complete coverage of the asthma cases. Random Forest and Neural Network had an accuracy of 74.91 and 75.06 respectively, whereas K-Nearest Neighbors had an accuracy of 70.49 %. Such predictive characteristics were the inability to inhale properly, dry cough, and age factor. Classical models had better computational time of 0.01-19.5 seconds to train and Quantum SVM took 45 seconds because of overhead in quantum circuit simulations. These results indicate that both classical ensemble and quantum models are clinically feasible to predict asthma, and classical models are ready to deploy the predictions in practice and quantum models have a potential in the future as quantum hardware advances. The study will enhance AI-facilitated healthcare innovation and will help in the better management of respiratory diseases.

DOI
10.1109/qpain69676.2026.11546061

Related papers

Predictive Intelligence to Early Intervention from Malaria: Comparative Study Between Quantum and Classical Machine Learning Paradigm

S Padmakala

Malaria is one of the global health threats that are of utmost concern, and it is paramount that the disease is identified early in time so that it can be treated and prevented to cause serious consequences. The study will provide a pioneering comparative study of quantum computing and classical machine learning to predict malaria, which will deal with healthcare diagnostics by using superior computational intelligence. Using a set of 1,622 patient records, including 15 clinical features, we compared the performance of three classical (Random Forest, Gradient Boosting and Support Vector Machine) and three quantum-inspired (Quantum Support Vector Classifier, Variational Quantum Classifier and Quantum Neural Network) classifiers using a large-scale clinical data set. The classical models performed exceptionally well with the Random Forest and Gradient Boosting models exhibiting 100 percent accuracy and quantum models performing well with QSVC with 97.85 percent accuracy based on dimensional reduction of features. Principal Component Analysis downsized the feature space by a factor of 15 to 8 dimensions and kept 63.51% variance, so that quantum circuit implementation is efficient. We find that classical ensemble methods are now more competitive than the quantum ones in malaria prediction, but quantum models are also competitive and use much less computing resources. The article identifies the practical applications in the resourcelimited healthcare facilities and lays the groundwork to hybrid quantum-classical architectures within the clinical decision support framework, which can advance to better patient outcomes and assist everyone to access high-quality healthcare services.

IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN)•Apr 16, 2026•1 citation

Quantum-Enhanced Feature Selection and Classification for Asthma Diagnosis Using a Variational Quantum Classifier

Noor E Fatima, Ghulam Nabi

Asthma remains a prevalent chronic respiratory disorder characterized by complex pathophysiological mechanisms and heterogeneous clinical manifestations. Accurate and timely diagnosis is critical for mitigating disease progression and optimizing patient outcomes. Conventional machine learning approaches often struggle with high-dimensional biomedical datasets, where redundant or irrelevant features can obscure discriminative patterns and degrade predictive performance. In this study, we propose a hybrid quantum-classical learning framework for asthma diagnosis that integrates Quantum Approximate Optimization Algorithm (QAOA)-based feature selection with a Variational Quantum Classifier (VQC) using angle embedding. The publicly available Asthma Disease Dataset from Kaggle, comprising demographic, lifestyle, environmental, and clinical variables, serves as the evaluation benchmark. The QAOA module exploits quantum parallelism, superposition, and entanglement to identify an optimal subset of predictive features, achieving an average dimensionality reduction of 73.3%. The selected features are subsequently encoded into quantum states and classified by a multi-layer VQC with chain entanglement. Simulations were conducted on a noiseless Pennylane default.qubit backend to assess the theoretical performance ceiling. Experimental results demonstrate that the proposed pipeline achieves an accuracy of 98.4%, surpassing classical baselines such as SVM, Random Forest, and MLP, while maintaining competitive precision, recall, and F1-scores. These findings underscore the potential of hybrid quantum-classical architectures for high-dimensional diagnostic tasks and lay the groundwork for future deployment of quantum-assisted clinical decision support systems in respiratory healthcare.

•Aug 18, 2025•0 citations

A comparative evaluation of quantum machine learning architectures for breast cancer classification using clinical and genomic data

Saartak Allena, Smrithy Girijakumari Sreekantan Nair, Balaji Chandrasekaran

Introduction: In recent years, high-dimensional clinical and genomic data have gained significant importance for prognosis and personalized medicine in breast cancer. But the use of quantum machine learning (QML) on such data is limited by the availability of few qubits, the computation time of quantum simulation, and dimensionality reduction. This work systematically compares several QML architectures for breast cancer classification in the presence of realistic and simulator constraints. Methods: The experiments were performed on a dataset of METABRIC breast cancer patients (2,509 patients). After handling missing values and one-hot encoding, there were 63 features in the processed data set. The feature space was reduced by Principal Component Analysis (PCA) to 12, 4 and 2 components for the implementations of quantum computers, respectively, with 56.10 ± 0.14%, 26.78 ± 0.57% and 16.23 ± 0.33% of the variance retained. Three QML models were tested: Quantum Neural Networks (QNN), Quantum K-Nearest Neighbors (QKNN), and Quantum Support Vector Machines (QSVM), with the models being simulated. Seven classical classification models were tested: Logistic Regression, SVM with RBF kernel, K-Nearest Neighbors, Random Forest, XGBoost, LightGBM and Multilayer Perceptron, both with PCA-matched and full 63-feature representation. All primary results are reported with 5-fold cross validation. Results: Among the evaluated QML architectures, QKNN using 12 principal components achieved the strongest performance, attaining an accuracy of **75.11% ± 3.76%**, an F1-score of **0.7088 ± 0.0433**, and a ROC-AUC of **0.8148 ± 0.0394**. Even though all of the QML models performed significantly poorly in comparison to classical models trained on the entire 63-feature data set, the latter models were able to achieve about **94% accuracy** with XGBoost, Random Forest, and Logistic Regression. The comparison also showed the effect of information loss due to PCA is significant in predictive performance in both classical and quantum models. Discussion: The results show that for high dimensional breast cancer data, currently available simulator-based QML models can learn meaningful patterns with limited quantum resources, but are not as effective as powerful classical machine learning models when complete feature representations are available. The study does not report any sort of quantum advantage or clinical use, but rather a benchmark of current QML architectures that has been rigorously calculated and repeated, with a focus on the impact of dimensionality reduction, validation approaches, and simulator limitations, as well as outlining challenges that need to be overcome prior to practical implementation on real quantum hardware.

Frontiers in Artificial Intelligence•Jul 29, 2026•1 citation

Feature Selection Using Quantum Feature Maps: Performance Analysis of Classical and Quantum Models on the Breast Cancer Dataset

Sevdanur Genç

In this study, the performance of classical and quantum machine learning models was compared using the Breast Cancer dataset, which consists of diagnostic data aimed at classifying breast tumor types. Breast cancer, being one of the most common and life-threatening cancers in women, requires accurate diagnostic tools for early detection and effective treatment. The primary objective of this study is to evaluate the accuracy of quantum-assisted models through quantum feature selection methods. Initially, classical machine learning algorithms such as Support Vector Machines (SVM), Decision Trees, Random Forests, and Logistic Regression were applied to the dataset for baseline analysis. Subsequently, a quantum feature map was constructed using the Cirq library, enabling feature transformation based on this map. The classification was performed using the SVM model with the quantum-transformed features. The Logistic Regression and SVM models demonstrated the highest performance among classical machine learning models, achieving an accuracy rate of 96.49%, followed by Random Forest at 94.74% and Decision Tree at 92.11%. In the context of quantum feature transformation, the model utilizing the top five selected features achieved an accuracy rate of 94.74%, in contrast to 98.25% for the model trained with all features. These findings underscore the potential of quantum feature maps in enhancing model performance compared to classical techniques. The results suggest that quantum computing may offer significant advantages when integrated into machine learning frameworks, particularly in domains such as medical diagnostics, where high accuracy is crucial.

•Oct 12, 2024•0 citations

Comparative Study of Quantum and Classical Machine Learning Models in Binary Classification

Anand Kumar Mishra, Ramanuj Awasthi

A potential path forward is Quantum Machine Learning (QML), which aims to leverage quantum computing in conjunction with classical machine learning to enhance computing efficiency and the expressiveness of models. In this paper, two different quantum classifiers - Variational Quantum Classifier (VQC) and Quantum Kernel Support Vector Machine (QSVM) - are compared with three classical classifiers as baseline classifiers - Logistic Regression, Support Vector Machine (SVM), and a Multi-Layer Perceptron (MLP) - on the Breast Cancer Wisconsin dataset. The quantum circuits were created in the PennyLane framework and simulated on a classical backend. However, in terms of accuracy, classical Logistic Regression performed better with an accuracy of 97.8%, classical SVM and QSVM with an accuracy of 95.6% each, although the Quantum VQC achieved a lower accuracy of 88.9% and had a recall of 100% for the benign class, though it correctly identified only 12 of the 17 malignant cases (a malignant-class recall of approximately 70.6%). The drawback of quantum models is the higher training time; however, since the quantum circuit needs to be classically simulated, the quantum SVM took 23.29 seconds compared to less than 0.01 seconds for the classical linear models. These results indicate that for small structured datasets, classifiers based on quantum computing have not yet surpassed well-tuned classical counterparts. In some respects (e.g., benign-class recall), they perform competitively, though not on malignant-class recall, where the VQC in particular performed worse than the classical baselines, which is worth further investigation on real quantum computers.

quant-pharXiv:2609.23476•Sep 22, 2026•0 citations

Performance Analysis of Quantum and Classical Machine Learning Models for Feature Selection and Classification of the Diabetes Health Indicators Dataset

Sevdanur Genç

The early detection and accurate classification of diabetes health indicators are crucial for effective disease management and prevention. This study aims to compare the performance of classical and quantum machine learning models in feature selection and classification on the Diabetes Health Indicators dataset. Initially, classical machine learning methods were employed to preprocess the data, including normalization and scaling, followed by feature selection using Lasso regression. Various traditional models, such as Logistic Regression, Decision Trees, Random Forests, Gradient Boosting, K-Nearest Neighbors, and Naive Bayes, were evaluated. Among these, the Logistic Regression model achieved the highest accuracy at $85 \%$, while other models also demonstrated competitive performance with accuracies ranging from $82 \%$ to $85 \%$. Subsequently, quantum machine learning techniques were applied using the selected features to assess their effectiveness. Quantum circuits were created using Cirq, and parameter optimization was performed through Quantum Feature Mapping and Quantum Feature Transformation. The Quantum Support Vector Machine (QSVM) model attained an accuracy of $84.33 \%$, showing potential for matching the performance of traditional models. The results suggest that quantum machine learning models can offer comparable accuracy to classical methods in the classification of diabetes health indicators. This study highlights the potential benefits of integrating quantum techniques in complex data processing and recommends further exploration in future research to fully harness the capabilities of quantum machine learning.

International Artificial Intelligence and Data Processing Symposium (IDAP)•Sep 21, 2024•4 citations
Millions of individuals are affected by asthma globally in that there is an urgent need to have accurate prediction systems in order to allow an early intervention and increase the patient outcome. This paper provides an extensive comparison of classical machine learning models and quantum machine learning methods to predict asthma and assess their viability to be used in clinical practice. Our data consisted of 50,000 patient records, consisting of 16 clinical features (symptoms, demographics, and severity indicators) and applied six classical models (Random Forest, Gradient Boosting, Support Vector Machine, Neural Network, Logistic Regression, K-Nearest Neighbors). We used standardised preprocessing and evaluation procedures to test Quantum Support Vector Machine on50,000\mathbf{5 0, 0 0 0}50,000patient records. Quantum SVM was found to be most accurate with 75.69 and closely second with classical SVM, Gradient Boosting and Logistic Regression, which had 75.16. All the most effective models had the perfect recall(100%)(100 \%)(100%), which provided complete coverage of the asthma cases. Random Forest and Neural Network had an accuracy of 74.91 and 75.06 respectively, whereas K-Nearest Neighbors had an accuracy of 70.49 %. Such predictive characteristics were the inability to inhale properly, dry cough, and age factor. Classical models had better computational time of 0.01-19.5 seconds to train and Quantum SVM took 45 seconds because of overhead in quantum circuit simulations. These results indicate that both classical ensemble and quantum models are clinically feasible to predict asthma, and classical models are ready to deploy the predictions in practice and quantum models have a potential in the future as quantum hardware advances. The study will enhance AI-facilitated healthcare innovation and will help in the better management of respiratory diseases.
Malaria is one of the global health threats that are of utmost concern, and it is paramount that the disease is identified early in time so that it can be treated and prevented to cause serious consequences. The study will provide a pioneering comparative study of quantum computing and classical machine learning to predict malaria, which will deal with healthcare diagnostics by using superior computational intelligence. Using a set of 1,622 patient records, including 15 clinical features, we compared the performance of three classical (Random Forest, Gradient Boosting and Support Vector Machine) and three quantum-inspired (Quantum Support Vector Classifier, Variational Quantum Classifier and Quantum Neural Network) classifiers using a large-scale clinical data set. The classical models performed exceptionally well with the Random Forest and Gradient Boosting models exhibiting 100 percent accuracy and quantum models performing well with QSVC with 97.85 percent accuracy based on dimensional reduction of features. Principal Component Analysis downsized the feature space by a factor of 15 to 8 dimensions and kept 63.51% variance, so that quantum circuit implementation is efficient. We find that classical ensemble methods are now more competitive than the quantum ones in malaria prediction, but quantum models are also competitive and use much less computing resources. The article identifies the practical applications in the resourcelimited healthcare facilities and lays the groundwork to hybrid quantum-classical architectures within the clinical decision support framework, which can advance to better patient outcomes and assist everyone to access high-quality healthcare services.
Asthma remains a prevalent chronic respiratory disorder characterized by complex pathophysiological mechanisms and heterogeneous clinical manifestations. Accurate and timely diagnosis is critical for mitigating disease progression and optimizing patient outcomes. Conventional machine learning approaches often struggle with high-dimensional biomedical datasets, where redundant or irrelevant features can obscure discriminative patterns and degrade predictive performance. In this study, we propose a hybrid quantum-classical learning framework for asthma diagnosis that integrates Quantum Approximate Optimization Algorithm (QAOA)-based feature selection with a Variational Quantum Classifier (VQC) using angle embedding. The publicly available Asthma Disease Dataset from Kaggle, comprising demographic, lifestyle, environmental, and clinical variables, serves as the evaluation benchmark. The QAOA module exploits quantum parallelism, superposition, and entanglement to identify an optimal subset of predictive features, achieving an average dimensionality reduction of 73.3%. The selected features are subsequently encoded into quantum states and classified by a multi-layer VQC with chain entanglement. Simulations were conducted on a noiseless Pennylane default.qubit backend to assess the theoretical performance ceiling. Experimental results demonstrate that the proposed pipeline achieves an accuracy of 98.4%, surpassing classical baselines such as SVM, Random Forest, and MLP, while maintaining competitive precision, recall, and F1-scores. These findings underscore the potential of hybrid quantum-classical architectures for high-dimensional diagnostic tasks and lay the groundwork for future deployment of quantum-assisted clinical decision support systems in respiratory healthcare.
Introduction: In recent years, high-dimensional clinical and genomic data have gained significant importance for prognosis and personalized medicine in breast cancer. But the use of quantum machine learning (QML) on such data is limited by the availability of few qubits, the computation time of quantum simulation, and dimensionality reduction. This work systematically compares several QML architectures for breast cancer classification in the presence of realistic and simulator constraints. Methods: The experiments were performed on a dataset of METABRIC breast cancer patients (2,509 patients). After handling missing values and one-hot encoding, there were 63 features in the processed data set. The feature space was reduced by Principal Component Analysis (PCA) to 12, 4 and 2 components for the implementations of quantum computers, respectively, with 56.10 ± 0.14%, 26.78 ± 0.57% and 16.23 ± 0.33% of the variance retained. Three QML models were tested: Quantum Neural Networks (QNN), Quantum K-Nearest Neighbors (QKNN), and Quantum Support Vector Machines (QSVM), with the models being simulated. Seven classical classification models were tested: Logistic Regression, SVM with RBF kernel, K-Nearest Neighbors, Random Forest, XGBoost, LightGBM and Multilayer Perceptron, both with PCA-matched and full 63-feature representation. All primary results are reported with 5-fold cross validation. Results: Among the evaluated QML architectures, QKNN using 12 principal components achieved the strongest performance, attaining an accuracy of **75.11% ± 3.76%**, an F1-score of **0.7088 ± 0.0433**, and a ROC-AUC of **0.8148 ± 0.0394**. Even though all of the QML models performed significantly poorly in comparison to classical models trained on the entire 63-feature data set, the latter models were able to achieve about **94% accuracy** with XGBoost, Random Forest, and Logistic Regression. The comparison also showed the effect of information loss due to PCA is significant in predictive performance in both classical and quantum models. Discussion: The results show that for high dimensional breast cancer data, currently available simulator-based QML models can learn meaningful patterns with limited quantum resources, but are not as effective as powerful classical machine learning models when complete feature representations are available. The study does not report any sort of quantum advantage or clinical use, but rather a benchmark of current QML architectures that has been rigorously calculated and repeated, with a focus on the impact of dimensionality reduction, validation approaches, and simulator limitations, as well as outlining challenges that need to be overcome prior to practical implementation on real quantum hardware.
In this study, the performance of classical and quantum machine learning models was compared using the Breast Cancer dataset, which consists of diagnostic data aimed at classifying breast tumor types. Breast cancer, being one of the most common and life-threatening cancers in women, requires accurate diagnostic tools for early detection and effective treatment. The primary objective of this study is to evaluate the accuracy of quantum-assisted models through quantum feature selection methods. Initially, classical machine learning algorithms such as Support Vector Machines (SVM), Decision Trees, Random Forests, and Logistic Regression were applied to the dataset for baseline analysis. Subsequently, a quantum feature map was constructed using the Cirq library, enabling feature transformation based on this map. The classification was performed using the SVM model with the quantum-transformed features. The Logistic Regression and SVM models demonstrated the highest performance among classical machine learning models, achieving an accuracy rate of 96.49%, followed by Random Forest at 94.74% and Decision Tree at 92.11%. In the context of quantum feature transformation, the model utilizing the top five selected features achieved an accuracy rate of 94.74%, in contrast to 98.25% for the model trained with all features. These findings underscore the potential of quantum feature maps in enhancing model performance compared to classical techniques. The results suggest that quantum computing may offer significant advantages when integrated into machine learning frameworks, particularly in domains such as medical diagnostics, where high accuracy is crucial.
A potential path forward is Quantum Machine Learning (QML), which aims to leverage quantum computing in conjunction with classical machine learning to enhance computing efficiency and the expressiveness of models. In this paper, two different quantum classifiers - Variational Quantum Classifier (VQC) and Quantum Kernel Support Vector Machine (QSVM) - are compared with three classical classifiers as baseline classifiers - Logistic Regression, Support Vector Machine (SVM), and a Multi-Layer Perceptron (MLP) - on the Breast Cancer Wisconsin dataset. The quantum circuits were created in the PennyLane framework and simulated on a classical backend. However, in terms of accuracy, classical Logistic Regression performed better with an accuracy of 97.8%, classical SVM and QSVM with an accuracy of 95.6% each, although the Quantum VQC achieved a lower accuracy of 88.9% and had a recall of 100% for the benign class, though it correctly identified only 12 of the 17 malignant cases (a malignant-class recall of approximately 70.6%). The drawback of quantum models is the higher training time; however, since the quantum circuit needs to be classically simulated, the quantum SVM took 23.29 seconds compared to less than 0.01 seconds for the classical linear models. These results indicate that for small structured datasets, classifiers based on quantum computing have not yet surpassed well-tuned classical counterparts. In some respects (e.g., benign-class recall), they perform competitively, though not on malignant-class recall, where the VQC in particular performed worse than the classical baselines, which is worth further investigation on real quantum computers.
The early detection and accurate classification of diabetes health indicators are crucial for effective disease management and prevention. This study aims to compare the performance of classical and quantum machine learning models in feature selection and classification on the Diabetes Health Indicators dataset. Initially, classical machine learning methods were employed to preprocess the data, including normalization and scaling, followed by feature selection using Lasso regression. Various traditional models, such as Logistic Regression, Decision Trees, Random Forests, Gradient Boosting, K-Nearest Neighbors, and Naive Bayes, were evaluated. Among these, the Logistic Regression model achieved the highest accuracy at 85%85 \%85%, while other models also demonstrated competitive performance with accuracies ranging from 82%82 \%82% to 85%85 \%85%. Subsequently, quantum machine learning techniques were applied using the selected features to assess their effectiveness. Quantum circuits were created using Cirq, and parameter optimization was performed through Quantum Feature Mapping and Quantum Feature Transformation. The Quantum Support Vector Machine (QSVM) model attained an accuracy of 84.33%84.33 \%84.33%, showing potential for matching the performance of traditional models. The results suggest that quantum machine learning models can offer comparable accuracy to classical methods in the classification of diabetes health indicators. This study highlights the potential benefits of integrating quantum techniques in complex data processing and recommends further exploration in future research to fully harness the capabilities of quantum machine learning.