Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69024
Volume:
10 |
11 |
Nov 2026
Pages:
1-8
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.
Department of Artificial Intelligence and Data Science
INDIAN INSTITUTE OF INFORMATION TECHNOLOGY , KURNOOL
Department of Artificial Intelligence and Data Science
INDIAN INSTITUTE OF INFORMATION TECHNOLOGY , KURNOOL
Children’s wellness is influenced by interconnected factors such as nutrition, sleep, physical activity, screen exposure and emotional well-being. Conventional tracking applications commonly present isolated measurements or generic advice, making it difficult for parents to interpret several lifestyle indicators together. This paper presents HEALTH LLM, a transformer-driven wellness companion that converts a child-specific profile into structured, understandable wellness guidance. The application is implemented using Python and Streamlit. A Pydantic data model validates profile information, including age, gender, height, weight, sleep duration, screen time, activity level, eating habits, mood and reported symptoms. The validated profile is transformed into a structured prompt and submitted to OpenAI’s GPT-4o-mini model through the OpenAI API. The response is requested in a structured JSON format and presented as a wellness score, daily plan, nutrition advice, physical activity suggestions, mental-wellness support, risk assessment and parent/guardian guidance. The project report documents functional operation using sample child profiles and demonstrates an end-to-end workflow from data entry to recommendation display. The system is intended for preventive wellness education and decision support; it is not a diagnostic tool and has not been clinically validated. The paper describes its architecture, implementation, observed functionality, limitations and directions for responsible extension.
KEYWORDS
This paper presented HEALTH LLM, a transformer-driven personalized wellness companion for children. The implemented prototype combines a Streamlit interface, Pydantic-based profile validation, structured prompt generation, GPT-4o-mini integration and a categorized recommendation dashboard. It accepts multiple child wellness indicators and produces a consolidated report covering a wellness score, daily plan, nutrition, physical activity, mental-wellness support, risk information and parent/guardian guidance. The project demonstrates an end-to-end software workflow for presenting AI-generated wellness information in an accessible format. The present work is limited to functional demonstration using sample profiles and does not establish clinical validity, diagnostic capability or measurable health outcomes. Future work should include evaluation by pediatric healthcare professionals, a predefined test protocol, systematic assessment of factuality and harmful outputs, and usability testing with intended users. Further extensions may include multilingual interaction, voice input, carefully governed wearable-device integration and longitudinal tracking with explicit consent. A safety layer that detects urgent symptom descriptions and directs users to appropriate professional services should also be investigated. Any future deployment involving children should follow applicable privacy, consent and healthcare requirements.
[1] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention Is All You Need,” in Proc. Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017, pp. 5998–6008. [2] T. B. Brown et al., “Language Models are Few-Shot Learners,” in Proc. Advances in Neural Information Processing Systems (NeurIPS), vol. 33, 2020, pp. 1877–1901. [3] R. Miotto, F. Wang, S. Wang, X. Jiang, and J. T. Dudley, “Deep learning for healthcare: Review, opportunities and challenges,” Briefings in Bioinformatics, vol. 19, no. 6, pp. 1236–1246, 2018. [4] K. Singhal, T. Tu, J. Gottweis et al., “Toward expert-level medical question answering with large language models,” Nature Medicine, vol. 31, pp. 943–950, 2025, doi: 10.1038/s41591-024-03423-7. [5] M. Sallam, “The utility of ChatGPT in healthcare education, research, and practice: Systematic review on the promising perspectives and valid concerns,” Healthcare, vol. 11, no. 6, Art. no. 887, 2023, doi: 10.3390/healthcare11060887.
Publication Date
11/16/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
1
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...