Deep Learning Endowed Generative Models: Revolutionizing Viral Disease Identification and Analysis with AI-Driven Decision Support
- Version
- Download 0
- File Size 686.67 KB
- File Count 1
- Create Date 1 July 2025
- Last Updated 1 July 2025
Deep Learning Endowed Generative Models: Revolutionizing Viral Disease Identification and Analysis with AI-Driven Decision Support
1. Taresh Singh 2. Mayank Chauhan 3. Himanshu Bartwal 4. Tarkeshwar Barua
Department of computer Science and Engineering, Roorke Institute of Technology, Rookee, India Email: tareshsingh@gmail.com
Department of Computer Science and Engineering APEX, Chandigarh Group of Colleges Jhanjeri Mohali, India, Email:Chauhan.mayank614@gmail.com
Department of CSE-AIML, Pranveer Singh Institute of Technology Kanpur, India, Email: bartwalhimanshu@gmail.com
Department of Computer Science and Engineering, Roorke Institute of Technology, Rookee, India, Email: tbarua1@gmail.com
Abstract: Viral disease detection involves identifying and diagnosing infections caused by viruses within biological samples or communities. These illnesses pose significant challenges to global healthcare systems, necessitating rapid and accurate detection methods for effective control and management. This survey paper examines how deep learning-enhanced generative models, combined with AI-supported decision-making systems, are transforming the field of viral disease detection and analysis. Although numerous studies highlight the potential of AI and deep learning in healthcare, our comprehensive review reveals critical limitations that need to be addressed to fully leverage these technologies. We highlight the issue of limited methodological diversity, where an overreliance on literature reviews weakens the depth and rigor of primary research methods. Additionally, we identify challenges such as publication bias, lack of empirical validation, and insufficient consideration of future research directions as common obstacles hindering progress in this field. Our survey also points out concerns about dependence on specific datasets, limited interdisciplinary perspectives, inadequate discussion of ethical implications, and a lack of comparisons with traditional methods. By addressing these issues, researchers and healthcare professionals can enhance the credibility, applicability, and impact of their work, thereby advancing AI and deep learning applications in healthcare and improving viral disease detection and analysis practices.
Keywords: Viral Disease Detection, Deep Learning Technologies, AI-Driven Decision Support Systems, Methodological Diversity, Publication Bias, Empirical Validation, Future Directions and Overcoming Challenges.
Download