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

Quantum Machine Intelligence

Unlocking the power of quantum computing in biomedical NLP for lung cancer diagnosis

Cyrille YetuYetu Kesiku, Begonya García-Zapirain, Adel Said Elmaghraby

Published Apr 15, 2026• 2 citations
Publisher

Abstract

Lung cancer remains the leading cause of cancer-related mortality worldwide, underscoring the urgent need for accurate, efficient, and interpretable early detection methods. Existing benchmark large language models (LLMs) like ClinicalBERT and BioBERT, despite their advancements in biomedical text analysis, face critical limitations including high computational costs, limited interpretability, and reliance on extensive annotated datasets hindering their clinical integration. To address these challenges, we propose the Hybrid Attention Quantum Long Short-Term Memory-Attention (A-QLSTM-A) model, a novel quantum-classical framework that combines quantum variational circuits with LSTM networks and dual attention mechanisms. This design enhances feature extraction, improves interpretability, and offers a more efficient architectural pathway. Evaluated on MIMIC-III discharge summaries and MIMIC-IV chest radiography reports, A-QLSTM-A achieved 98.32% and 83.67% accuracy, respectively, surpassing existing models. This study establishes a new benchmark for scalable, interpretable AI in precision medicine, offering a promising tool for early lung cancer detection and clinical decision support.

DOI
10.1007/s42484-026-00392-7

Related papers

Quantum AI Based Diagnosis System for Early Brain Tumor and Lung Cancer Detection

Dr. S. Gunasekaran

Early and correct diagnosis plays a key role in enhancing the outcome in brain tumor and lung cancer patients. Traditional Artificial Intelligence (AI) and Deep Learning (DL) models are handicapped by expensive computational costs and challenges in handling high-dimensional medical data. This research article presents a Quantum AI based Diagnostics System employing a hybrid quantum-classical computing model. The framework combines traditional feature preprocessing with the exponential power of quantum computing. For classification in brain tumors (e.g., LGGs/HGGs), the quantum core uses a Hybrid Quantum-Classical Integrated Neural Network (HQCINN) or Variational Quantum Classifier (VQC). For lung cancer prediction, the framework might employ quantum-enhanced clustering such as Quantum-Enhanced K-Medoids or optimization models such as Quantum --Genetic Binary Grey Wolf Optimizer (Q-GBGWO) with Extreme Learning Machines (ELM). This hybrid methodology is intended to achieve superior diagnostic efficacy and speed across both MRI and CT modalities, laying the groundwork for faster and more individualized clinical diagnostics.

International Journal for Research in Applied Science and Engineering Technology•Dec 10, 2025•0 citations

An enhanced hybrid deep learning-quantum variational classifier framework for large-scale data analytics

Yadlapti Suresh, Venu Gopal Gaddam, Challa Naga Venkata Jyothirmai +3 more

The rapid expansion of clinical data in modern healthcare requires analytical systems capable of uncovering intricate patterns and supporting accurate diagnostic decisions. Quantum machine learning (QML) offers significant potential for modeling higher-order feature interactions and accelerating computation beyond classical approaches. This paper introduces an improved hybrid architecture that fuses an inception-based attentional VGG (IAV) network with a quantum variational classifier (QVC) constructed using parameterized quantum circuits (PQCs). The framework begins with min-max normalization to stabilize heterogeneous clinical attributes and enhance training convergence. Deep discriminative features are then extracted through the IAV model, followed by quantum-driven classification using variational layers optimized by classical routines. The MIMIC-III clinical dataset is employed to validate the proposed system on large-scale healthcare records. Performance is measured using accuracy, precision, recall, and F1-score. The enhanced hybrid model achieves 97.28% accuracy, 97.16% precision, 96.65% recall, and a 97.38% F1-score, surpassing established methods including support vector machine (SVM) (89.23%), quantum support vector machine (QSVM) (90.13%), and QVKSVM (97.34%). The findings confirm that integrating deep learning with quantum variational optimization strengthens scalability, reduces computational overhead, and establishes a powerful foundation for next-generation healthcare analytics.

International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering•Jun 1, 2026•0 citations

Quantum-Enhanced Multimodal Fusion Networks for Integrated Cancer Diagnosis: Combining CT, Genomics, and Clinical Records

Sandeep Gupta, Kanad Ray, Shamim Kaiser +2 more

Diagnosis of cancer is one of the hardest problems faced in modern medicine and involves integrating different data sources such as medical images, genomic profiles and clinical records. Traditional machine learning methods have difficulty handling the high-dimensional and complex correlation properties of multimodal medical data. In view of this, we propose a new Quantum-Enhanced Multimodal Fusion Network (QEMFN) framework to break through traditional image–text matching based on quantum computing principles for CT imaging with genomic sequencing data and EHR information. Our approach utilizes variational quantum circuits for feature encoding, quantum kernel methods for crossmodal attention, and hybrid quantum–classical architectures for final classification. We realize the framework using Google Cirq quantum computing library and validate it on publicly available datasets including TCIA (The Cancer Imaging Archive), TCGA (The Cancer Genome Atlas), and MIMIC-III clinical database. The matched multimodal cohort comprises 847 lung cancer patients, 623 colorectal cancer patients, and 401 liver cancer patients with complete imaging, genomic, and clinical records, assembled via de-identified patient ID linkage across the three archives. The experiment takes steps toward the realization of quantum-enhanced diagnostic systems and offers a path for subsequent experimental confirmation. We theoretically analyze the potential quantum advantage, present detailed implementation details using Cirq, and describe a roadmap to clinical translation for quantum-enhanced diagnostic tools.

Algorithms•Apr 2, 2026•1 citation

Quantum Variational Transformer Model for Enhanced Cancer Classification

Don Roosan, Rubayat Islam Khan, Md Rahatul Ashakin +3 more

Accurate prediction of cancer type and primary tumor site is critical for effective diagnosis, personalized treatment, and improved outcomes. Traditional models struggle with the complexity of genomic and clinical data, but quantum computing offers enhanced computational capabilities. This study develops a hybrid quantum-classical transformer model, incorporating quantum attention mechanisms via variational quantum circuits (VQCs) to improve prediction accuracy. Using 30,000 anonymized cancer samples from the Genome Warehouse (GWH), data preprocessing included cleaning, encoding, and feature selection. Classical self-attention modules were replaced with quantum attention layers, with classical data encoded into quantum states via amplitude encoding. The model, trained using hybrid backpropagation and quantum gradient calculations, outperformed the classical transformer model, achieving 92.8% accuracy and an AUC of 0.96 compared to 87.5% accuracy and an AUC of 0.89. It also demonstrated 35% faster training and 25% fewer parameters, highlighting computational efficiency. These findings showcase the potential of quantum-enhanced transformers to advance biomedical data analysis, enabling more accurate diagnostics and personalized medicine.

arXiv:2506.21641•Advances in transdisciplinary engineering•Aug 26, 2025•24 citations

Quantum AI Framework for Early Blood Cancer Detection using Hybrid QSVM and Natural Language Processing

J. Senthil Kumar, Yogeswari M, Vaishaali B +1 more

Early detection of blood cancers such as leukemia, lymphoma, and myeloma is essential for improving patient survival rates and enabling timely treatment. Traditional diagnostic methods, including laboratory tests and invasive procedures, are often time-consuming and may fail to detect subtle early-stage abnormalities. To address these challenges, this study proposes a novel hybrid framework that integrates Quantum-Enhanced Natural Language Processing (QNLP) with a Hybrid Quantum Support Vector Machine (QSVM) for early blood cancer detection. The system transforms structured clinical data, including hematological parameters such as white blood cell count, hemoglobin, and platelet levels, into semantic textual representations. These representations are processed using transformer-based embeddings, preserving contextual medical information. Subsequently, quantum feature encoding techniques, such as angle and amplitude encoding, map the data into high-dimensional Hilbert spaces, enabling improved pattern recognition. The QSVM leverages quantum kernels to capture complex nonlinear relationships and enhance classification accuracy. The proposed framework achieves a superior classification accuracy of 99.32%, outperforming existing state-of-the-art leukemia detection models. The integration of classical NLP with quantum computing not only improves predictive performance but also ensures interpretability and scalability. This research contributes to the advancement of precision oncology by providing a non-invasive, efficient, and reliable diagnostic tool for early-stage blood cancer detection, ultimately supporting better clinical decision-making and patient outcomes.

International Conference on Cognitive Computing and Networking Systems (ICC-CNS)•Jun 1, 2026•0 citations

Quantum Machine Learning Framework Based on Quantum Support Vector Machines and Variational Quantum Circuits for Accurate Breast Cancer Classification and Prediction Using Clinical Diagnostic Dataset

Prakash Bethapudi, Durgesh Nandan

Early diagnosis is a critical issue in breast cancer treatment, as clinical diagnostic data is complex and nonlinear, and it is one of the top killers among women globally. In biomedical data, particularly with high dimensionality, traditional machine learning models frequently fall short due to challenges like over fitting, high computational cost, and limited ability to make accurate predictions. This study suggests a Hybrid Quantum Machine Learning model combining the Quantum Support Vector Machines (QSVM) and Variational Quantum Circuits (VQC) to enhance the classification and prediction of breast cancer accurately overcoming these challenges. A Breast Cancer Wisconsin Diagnostic Dataset was used for evaluation consisting of 569 clinical samples and 30 diagnostic features. For efficient quantum encoding, Principal Component Analysis was used to retain almost 95% of the variance with only 10 components. Results showed that the Z quantum feature map yielded 94.7% classification accuracy and the proposed Hybrid QSVM–VQC framework provided an accuracy of around 97.8% with the ROC–AUC almost reaching 1.00. The results highlight the great potential of hybrid quantum learning in the fields of diagnostic accuracy, nonlinear feature representation, and clinical prediction reliability.

•Sep 1, 2026•0 citations
Lung cancer remains the leading cause of cancer-related mortality worldwide, underscoring the urgent need for accurate, efficient, and interpretable early detection methods. Existing benchmark large language models (LLMs) like ClinicalBERT and BioBERT, despite their advancements in biomedical text analysis, face critical limitations including high computational costs, limited interpretability, and reliance on extensive annotated datasets hindering their clinical integration. To address these challenges, we propose the Hybrid Attention Quantum Long Short-Term Memory-Attention (A-QLSTM-A) model, a novel quantum-classical framework that combines quantum variational circuits with LSTM networks and dual attention mechanisms. This design enhances feature extraction, improves interpretability, and offers a more efficient architectural pathway. Evaluated on MIMIC-III discharge summaries and MIMIC-IV chest radiography reports, A-QLSTM-A achieved 98.32% and 83.67% accuracy, respectively, surpassing existing models. This study establishes a new benchmark for scalable, interpretable AI in precision medicine, offering a promising tool for early lung cancer detection and clinical decision support.
Early and correct diagnosis plays a key role in enhancing the outcome in brain tumor and lung cancer patients. Traditional Artificial Intelligence (AI) and Deep Learning (DL) models are handicapped by expensive computational costs and challenges in handling high-dimensional medical data. This research article presents a Quantum AI based Diagnostics System employing a hybrid quantum-classical computing model. The framework combines traditional feature preprocessing with the exponential power of quantum computing. For classification in brain tumors (e.g., LGGs/HGGs), the quantum core uses a Hybrid Quantum-Classical Integrated Neural Network (HQCINN) or Variational Quantum Classifier (VQC). For lung cancer prediction, the framework might employ quantum-enhanced clustering such as Quantum-Enhanced K-Medoids or optimization models such as Quantum --Genetic Binary Grey Wolf Optimizer (Q-GBGWO) with Extreme Learning Machines (ELM). This hybrid methodology is intended to achieve superior diagnostic efficacy and speed across both MRI and CT modalities, laying the groundwork for faster and more individualized clinical diagnostics.
The rapid expansion of clinical data in modern healthcare requires analytical systems capable of uncovering intricate patterns and supporting accurate diagnostic decisions. Quantum machine learning (QML) offers significant potential for modeling higher-order feature interactions and accelerating computation beyond classical approaches. This paper introduces an improved hybrid architecture that fuses an inception-based attentional VGG (IAV) network with a quantum variational classifier (QVC) constructed using parameterized quantum circuits (PQCs). The framework begins with min-max normalization to stabilize heterogeneous clinical attributes and enhance training convergence. Deep discriminative features are then extracted through the IAV model, followed by quantum-driven classification using variational layers optimized by classical routines. The MIMIC-III clinical dataset is employed to validate the proposed system on large-scale healthcare records. Performance is measured using accuracy, precision, recall, and F1-score. The enhanced hybrid model achieves 97.28% accuracy, 97.16% precision, 96.65% recall, and a 97.38% F1-score, surpassing established methods including support vector machine (SVM) (89.23%), quantum support vector machine (QSVM) (90.13%), and QVKSVM (97.34%). The findings confirm that integrating deep learning with quantum variational optimization strengthens scalability, reduces computational overhead, and establishes a powerful foundation for next-generation healthcare analytics.
Diagnosis of cancer is one of the hardest problems faced in modern medicine and involves integrating different data sources such as medical images, genomic profiles and clinical records. Traditional machine learning methods have difficulty handling the high-dimensional and complex correlation properties of multimodal medical data. In view of this, we propose a new Quantum-Enhanced Multimodal Fusion Network (QEMFN) framework to break through traditional image–text matching based on quantum computing principles for CT imaging with genomic sequencing data and EHR information. Our approach utilizes variational quantum circuits for feature encoding, quantum kernel methods for crossmodal attention, and hybrid quantum–classical architectures for final classification. We realize the framework using Google Cirq quantum computing library and validate it on publicly available datasets including TCIA (The Cancer Imaging Archive), TCGA (The Cancer Genome Atlas), and MIMIC-III clinical database. The matched multimodal cohort comprises 847 lung cancer patients, 623 colorectal cancer patients, and 401 liver cancer patients with complete imaging, genomic, and clinical records, assembled via de-identified patient ID linkage across the three archives. The experiment takes steps toward the realization of quantum-enhanced diagnostic systems and offers a path for subsequent experimental confirmation. We theoretically analyze the potential quantum advantage, present detailed implementation details using Cirq, and describe a roadmap to clinical translation for quantum-enhanced diagnostic tools.
Accurate prediction of cancer type and primary tumor site is critical for effective diagnosis, personalized treatment, and improved outcomes. Traditional models struggle with the complexity of genomic and clinical data, but quantum computing offers enhanced computational capabilities. This study develops a hybrid quantum-classical transformer model, incorporating quantum attention mechanisms via variational quantum circuits (VQCs) to improve prediction accuracy. Using 30,000 anonymized cancer samples from the Genome Warehouse (GWH), data preprocessing included cleaning, encoding, and feature selection. Classical self-attention modules were replaced with quantum attention layers, with classical data encoded into quantum states via amplitude encoding. The model, trained using hybrid backpropagation and quantum gradient calculations, outperformed the classical transformer model, achieving 92.8% accuracy and an AUC of 0.96 compared to 87.5% accuracy and an AUC of 0.89. It also demonstrated 35% faster training and 25% fewer parameters, highlighting computational efficiency. These findings showcase the potential of quantum-enhanced transformers to advance biomedical data analysis, enabling more accurate diagnostics and personalized medicine.
Early detection of blood cancers such as leukemia, lymphoma, and myeloma is essential for improving patient survival rates and enabling timely treatment. Traditional diagnostic methods, including laboratory tests and invasive procedures, are often time-consuming and may fail to detect subtle early-stage abnormalities. To address these challenges, this study proposes a novel hybrid framework that integrates Quantum-Enhanced Natural Language Processing (QNLP) with a Hybrid Quantum Support Vector Machine (QSVM) for early blood cancer detection. The system transforms structured clinical data, including hematological parameters such as white blood cell count, hemoglobin, and platelet levels, into semantic textual representations. These representations are processed using transformer-based embeddings, preserving contextual medical information. Subsequently, quantum feature encoding techniques, such as angle and amplitude encoding, map the data into high-dimensional Hilbert spaces, enabling improved pattern recognition. The QSVM leverages quantum kernels to capture complex nonlinear relationships and enhance classification accuracy. The proposed framework achieves a superior classification accuracy of 99.32%, outperforming existing state-of-the-art leukemia detection models. The integration of classical NLP with quantum computing not only improves predictive performance but also ensures interpretability and scalability. This research contributes to the advancement of precision oncology by providing a non-invasive, efficient, and reliable diagnostic tool for early-stage blood cancer detection, ultimately supporting better clinical decision-making and patient outcomes.
Early diagnosis is a critical issue in breast cancer treatment, as clinical diagnostic data is complex and nonlinear, and it is one of the top killers among women globally. In biomedical data, particularly with high dimensionality, traditional machine learning models frequently fall short due to challenges like over fitting, high computational cost, and limited ability to make accurate predictions. This study suggests a Hybrid Quantum Machine Learning model combining the Quantum Support Vector Machines (QSVM) and Variational Quantum Circuits (VQC) to enhance the classification and prediction of breast cancer accurately overcoming these challenges. A Breast Cancer Wisconsin Diagnostic Dataset was used for evaluation consisting of 569 clinical samples and 30 diagnostic features. For efficient quantum encoding, Principal Component Analysis was used to retain almost 95% of the variance with only 10 components. Results showed that the Z quantum feature map yielded 94.7% classification accuracy and the proposed Hybrid QSVM–VQC framework provided an accuracy of around 97.8% with the ROC–AUC almost reaching 1.00. The results highlight the great potential of hybrid quantum learning in the fields of diagnostic accuracy, nonlinear feature representation, and clinical prediction reliability.