A hybrid Inception-attention VGG and quantum variational learning framework for scalable healthcare data analytics

Thumukunta Praveen Kumar, Gaddam Venugopal, Pramod Kumar Irlapati, Athinarayanasamy Muthukrishnan, Divvela Srinivasa Rao, Thotakura Venkata Sai Krishna, Choutupalli Lavanya Susanna

Abstract


The rapid expansion of clinical data requires analytical frameworks capable of handling high-dimensional, heterogeneous, and noisy medical information. Classical deep learning models provide strong feature extraction capabilities but are often computationally intensive and prone to scalability limitations. Conversely, quantum machine learning (QML) offers enhanced representational capacity but suffers from hardware constraints and noise sensitivity. To address these shortcomings, this paper proposes a hybrid deep learning–quantum processing architecture integrating an Inception-attention-based visual geometry group (VGG) network for multiscale feature extraction with a quantum variational classifier (QVC) optimized using parameterized quantum circuits (PQCs). Clinical data from the MIMIC-III dataset undergo min–max normalization, multi-resolution convolutional feature extraction, and quantum-enhanced classification. Experiments demonstrate superior performance compared to classical support vector machine (SVM), quantum support vector machines (QSVM), quantum kernel support vector machine (QKSVM), quantum variational support vector machine (QVSVM), and quantum variational kernel support vector machine (QVKSVM) models. The proposed framework achieves 98.79% accuracy, 98.67% precision, 98.15% recall, and 98.88% F1-score, representing a subtle 0.3% improvement over existing quantum-assisted hybrid models. These results demonstrate the effectiveness of the proposed hybrid framework within the adopted classical–quantum simulation environment and motivate further validation on real near-term quantum hardware.

Keywords


Inception-attention visual geometry group; Large-scale healthcare analytics; Parameterized quantum circuits; Quantum machine learning; Variational quantum classifier

Full Text:

PDF


DOI: https://doi.org/10.11591/eei.v15i6.12099

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Bulletin of EEI Statistics

Bulletin of Electrical Engineering and Informatics (BEEI)
ISSN: 2089-3191 , e-ISSN: 2302-9285
This journal is published by the Institute of Advanced Engineering and Science (IAES) .