Enhanced super-resolution generative adversarial network augmented convolution neural network for pneumonia prognosis in India: promising health policy implications

Tapan Kumar () and R. L. Ujjwal ()
Additional contact information
Tapan Kumar: USIC&T, Guru Gobind Singh Indraprastha University
R. L. Ujjwal: USIC&T, Guru Gobind Singh Indraprastha University

International Journal of System Assurance Engineering and Management, 2025, vol. 16, issue 4, No 7, 1438-1450

Abstract: Abstract Pneumonia is one of the leading causes of death globally. The healthcare industry is revolutionizing with Artificial Intelligence (AI) and data analytics applications. However, healthcare professionals are still struggling with pneumonia due to the unavailability of efficient AI-based assessments and the lack of diverse datasets for training AI models. This problem must be addressed to forecast early and accurately detect pneumonia. Analysis of chest X-rays is one effective solution, but they require trained healthcare professionals, who are less available in rural areas in India. The objective of this research is to propose a novel approach that integrates an Enhanced Super-Resolution Generative Adversarial Network with a Convolution Neural Network for early detection and prognosis of Pneumonia. This paper will also highlight two significant gaps: the lack of high-resolution images and the unavailability of diverse datasets to train AI models. The proposed hybrid model has been applied to 11,000 Chest X-ray images collected from various radiology centres and labs in India. In this model, high-resolution images generated by the Enhanced Super-Resolution Generative Adversarial Network are used as input for further classification by the Convolutional Neural Network. The model outperformed the traditional model, and performance was evaluated based on average accuracy, validation accuracy, and validation loss, with results of 91.53 percent, 87.98 percent, and 10.25 percent, respectively. The model successfully addresses the gap identified. The collected dataset has also been evaluated against three pre-trained deep learning models, VGG16, ResNet, and DenseNet, achieving an average accuracy of 0.79, 0.62, and 0.58 without fine-tuning. The result has implications for the healthcare industry and the government of India in policy-making. It provides precise suggestions for stakeholders or researchers, which will be key for launching further research in this uncharted territory.

Keywords: Generative adversarial network; Convolution neural network; Healthcare policy; Pneumonia; Lungs disease; Radiograph (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s13198-025-02757-w Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:ijsaem:v:16:y:2025:i:4:d:10.1007_s13198-025-02757-w

Ordering information: This journal article can be ordered from
http://www.springer.com/engineering/journal/13198

DOI: 10.1007/s13198-025-02757-w

Access Statistics for this article

International Journal of System Assurance Engineering and Management is currently edited by P.K. Kapur, A.K. Verma and U. Kumar

More articles in International Journal of System Assurance Engineering and Management from Springer, The Society for Reliability, Engineering Quality and Operations Management (SREQOM),India, and Division of Operation and Maintenance, Lulea University of Technology, Sweden
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().