Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM67734
Volume:
10 |
10 |
Oct 2026
Pages:
1-6
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.
Information Technology
Prof.Ram Meghe College of Engineering and Management
Information Technology
Prof.Ram Meghe College of Engineering and Management
Information Technology
Prof.Ram Meghe College of Engineering and Management
Information Technology
Prof.Ram Meghe College of Engineering and Management
Information Technology
Prof.Ram Meghe College of Engineering and Management
Information Technology
Prof.Ram Meghe College of Engineering and Management
Taking care of your own health is a daily job. You have to keep your reports in order, understand what the numbers mean, remember to take medicines on time, keep an eye on long-term conditions, and decide which health advice is worth trusting. In the last few years, progress in artificial intelligence (AI), machine learning (ML), large language models (LLMs), optical character recognition (OCR) and retrieval-augmented generation (RAG) has made it possible to help with many of these tasks. In this paper we review twelve studies that cover four areas: personal health agents and LLM-based coaching, ML models for disease risk prediction, OCR for medical reports, and RAG for biomedical question answering. Our main observation is that each area works well on its own, but they are rarely put together. Existing systems also tend to explain things poorly to ordinary patients, ignore the user's own records, and say little about safety, fairness and keeping users interested over time. Based on this, we describe a concept called the AI Personalized Healthcare Assistant (APHA). It is one app that offers chat support, report analysis, disease risk estimates, personal lifestyle advice, medicine reminders and secure health records. We see APHA as a tool that helps doctors and patients, not one that replaces doctors. The biggest challenges we found are data privacy, bias, wrong answers from LLMs, and user engagement.
KEYWORDS
AI-driven personalized healthcare assistants are a promising way to manage everyday health. Existing research already offers strong building blocks: personal health agents, ML-based risk prediction, OCR-based report digitization and RAG-based biomedical question answering. However, most current systems are narrow and disconnected, and important problems remain in integration, patient-friendly interpretation, use of personal data, safety, fairness and evaluation. The APHA concept shows how these pieces can be joined into one patient-centred platform that offers conversational guidance, report analysis, risk estimation, lifestyle recommendations, medicine reminders and secure record storage. In the future, such systems must be private, clinically reliable, fair, engaging and closely connected with healthcare professionals, so that they strengthen human care instead of replacing it. The next step is to build a working prototype and test it against clear benchmarks.
[1] A. J. Thirunavukarasu, D. S. J. Ting, K. Elangovan, L. Gutierrez, T. F. Tan, and D. S. W. Ting, "Large language models in medicine," Nature Medicine, vol. 29, pp. 1930–1940, 2023. [2] S. Tian, Q. Jin, L. Yeganova, et al., "Opportunities and challenges for ChatGPT and large language models in biomedicine and health," Briefings in Bioinformatics, vol. 25, bbad493, 2024. [3] J. Cosentino, et al., "A personal health large language model for sleep and fitness coaching," Nature Medicine, vol. 31, pp. 3394–3403, 2025. [4] X. Xu and A. Heydari, "The anatomy of a personal health agent," Google Research, 2025. [5] L. Stuhlmann, M. A. Saxer, and J. Fürst, "Efficient and reproducible biomedical question answering using retrievalaugmented generation," arXiv preprint, 2025. [6] X. Ren, D. Dou, X. He, F. Cui, and J. Zhao, "A serialization method for digitizing the image-based medical laboratory report," Digital Health, 2025. [7] M. Kaczmarek, et al., "Predicting major adverse cardiac events in diabetes and chronic kidney disease," Cardiovascular Diabetology, vol. 24, art. 76, 2025. [8] M. Abbasian, I. Azimi, A. M. Rahmani, and R. Jain, "Conversational health agents: A personalized LLM-powered agent framework," arXiv preprint, 2023. [9] G. d. P. Souza, G. Melo, and D. Schneider, "Tailoring treatment in the age of AI: A systematic review of large language models in personalized healthcare," Informatics, vol. 12, art. 113, 2025. [10] "Retrieval-augmented generation for large language models in healthcare: A systematic review," PLOS Digital Health, 2025.
Publication Date
10/9/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
9
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...