Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM63510
Volume:
10 |
5 |
May 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Master of Computer Applications
Bapuji Institute of Engineering and Technology, Davanagere
Master of Computer Applications
Bapuji Institute of Engineering and Technology, Davanagere
Artificial Intelligence has significantly transformed the healthcare domain by enabling intelligent systems capable of assisting users in early health assessment. This paper presents an AI-based Health Diagnosis Assistant that analyzes user-provided symptoms and generates possible disease conditions using the Gemini Generative AI API. The system accepts symptom input through a simple web interface and processes it using a pre-trained large language model without requiring custom dataset training. The proposed system provides possible health conditions, general remedies, and guidance on when medical consultation is required. To improve usability, the application also supports secure user authentication and stores diagnosis history using MongoDB Atlas for future reference. The frontend is developed using ReactJS, while the backend is implemented with Node.js and TypeScript, ensuring scalable and maintainable communication with the AI service. This system is especially useful in regions with limited access to healthcare professionals, enabling users to obtain preliminary health insights quickly. The developed solution serves as a decision-support tool for early symptom analysis and health awareness, while not replacing professional medical diagnosis. Experimental results demonstrate fast response generation, reliable history management, and a user-friendly healthcare assistance platform.
KEYWORDS
The proposed Gen AI Health Diagnosis Assistant using Gemini API successfully provides an intelligent and user-friendly platform for preliminary symptom-based disease prediction. By integrating Generative AI, the system can understand symptoms entered in natural language and generate possible disease conditions, preventive measures, and recommendations for medical consultation in real time. Compared with traditional rule-based healthcare systems, the proposed solution offers better flexibility, faster response generation, secure history storage, and improved user interaction through a modern web interface. The experimental results confirm that the system effectively supports early health awareness and assists users in obtaining quick preliminary medical guidance. This makes the proposed model highly suitable for real-world healthcare assistance, especially in situations where immediate doctor consultation is not available. Future enhancements can include voice-based symptom input, multilingual support, wearable sensor integration, and telemedicine connectivity, making the system more intelligent, accessible, and practical for next-generation digital healthcare services.
[1] Brown J. & Davis L. (2022). Artificial Intelligence in Healthcare: Applications and Challenges. Springer Publications. [2] Patel S. & Mehta R. (2021). “Machine Learning for Medical Diagnosis Systems.” IEEE Access Journal. [3] Nguyen T. (2020). “AI-Powered Symptom Analysis and Disease Prediction.” International Journal of Health Informatics. [4] Singh P. (2022). Applications of deep learning in medical imaging and health data analytics. Academic Press. [5] Kaur R. & Sharma M. (2021). “AI-Based Virtual Health Assistants: Current Trends and Future Directions.” Elsevier Journal of Biomedical Engineering. [6] World Health Organization. (2023). AI and Digital Transformation in Healthcare. WHO Publications. [7] Kumar V. & Gupta N. (2021). “A Review on AI-based Healthcare Systems and Future Prospects.” Journal of Artificial Intelligence Research.
Publication Date
5/19/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...