Citation :

Guda Vanitha, Srujana Inturi, M Venkata Krishna Reddy, T Suvarna Kumari, Golla Manasa, "AI-IOT Enabled Health Advisory Chatbot for Diabetics using RAG model," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 9, pp. 91-102, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I9P108

Abstract

Diabetes is one of the most common chronic diseases that requires regular monitoring to avoid complications. While the IoT devices can only track health data like blood glucose, heart rate, and temperature, they often ignore the Body Mass Index (BMI), which is a major risk factor for Type 2 diabetes. BMI is a powerful measure to understand if a person is underweight, normal, overweight, or obese. A high BMI is closely linked with obesity, and obesity directly contributes to insulin resistance. Without monitoring the BMI, patients may control sugar levels but miss the biggest lifestyle problem. An AI-IoT health monitoring system for diabetic patients has been developed that not only tracks blood glucose, heart rate, and temperature but also calculates the Body Mass Index (BMI). A RAG-powered chatbot is integrated so that patients can ask questions, understand the readings, and receive personalized guidance for diet, exercise, and medication. The Dexcom G6 sensor is used to measure blood glucose, the MAX30100 sensor for heart rate and SpO₂, and the LM35 sensor for body temperature. A smart weighing scale is added to record weight, and the patient’s height is stored in the system. By using weight and height, the BMI is calculated. Then all data is processed by Arduino Nano, which will receive raw signals from sensors and then convert them into meaningful health values. The Arduino Nano sends the processed data to Node MCU, which is connected to the internet via Wi-Fi and transfers it to the cloud platform. Cloud platform receives the data and displays it on a web dashboard. A RAG chatbot is used to retrieve trusted medical documents and generate personalized recommendations. Patients can use the web dashboard to view readings and chat with the assistant for explanations. Patients are able to track glucose levels along with BMI in real time. The RAG chatbot explains the results in simple words and suggests lifestyle tips and exercises, helping individuals reduce confusion about diabetes and encouraging self-care.

Keywords

MAX30100, LM35, Arduino Nano, Node MCU, Body Mass Index (BMI), Machine learning algorithm, RAG model, Health chatbot, Large Language Models (LLMs), FAISS, Sentence transformers.

References

[1] Dingqiao Wang et al., “Enhancement of the Performance of Large Language Models in Diabetes Education through Retrieval-Augmented Generation: Comparative Study,” Journal of Medical Internet Research, vol. 26, pp. 1-12, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Anthony Kelly et al., “The Effectiveness of a Custom AI Chatbot for Type 2 Diabetes Mellitus Health Literacy: Development and Evaluation Study,” Journal of Medical Internet Research, vol. 27, pp. 1-20, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Lameck Mbangula Amugongo et al., “Retrieval Augmented Generation for Large Language Models in Healthcare: A Systematic Review,” PLOS Digital Health, vol. 4, no. 6, pp. 1-33, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Siru Liu, Allison B McCoy, and Adam Wright, “Improving Large Language Model Applications in Biomedicine with Retrieval-Augmented Generation: A Systematic Review, Meta-Analysis, and Clinical Development Guidelines,” Journal of the American Medical Informatics Association, vol. 32, no. 4, pp. 605-615, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Y. Bhanu Sree et al., “Retrieval-Augmented Generation based       Large Language Model Chatbot for Improving Diagnosis for Physical and Mental Health,” 2024 6^th International Conference on Electrical, Control and Instrumentation Engineering, Pattaya, Thailand, pp. 1-8, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Waqar Hussain, and John Grundy, “Advice for Diabetes Self-Management by Chatgpt Models: Challenges and Recommendations,” arXiv preprint arXiv, pp. 1-13, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Flavia Voiculescu et al., “Natural Language AI Models and Pediatric Type 1 Diabetes:                Can Chatbots Help with Diabetes Self-Management and Patient Education?,” JMIR Diabetes, vol. 10, pp. 1-4, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Moshe Shegal et al., “Conversational Agent Interventions in Diabetes Care: A Systematic Review,” Diabetes Research and Clinical Practice, vol. 228, pp. 1-13, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Dung Dao et al., “LLM-Powered Multimodal AI Conversations for Diabetes Prevention,” Proceedings of the 1^st ACM Workshop on AI-Powered Q&A Systems for Multimedia, Association for Computing Machinery, New York, NY, USA, pp. 1-6, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Tindra Jargenstedt, and Elin Nilsson, “Applying and Evaluating Large Language Models for Triage at a Paediatric Emergency Department in a Swedish Hospital,” Gothenburg University Publications Electronic Archive, pp. 1-132, 2025.
[Google Scholar] [Publisher Link]

[11] Mohamed Khalifa, and Mona Albadawy “Artificial Intelligence for Diabetes: Enhancing Prevention, Diagnosis, and Effective Management,” Computer Methods and Programs in Biomedicine Update, vol. 5, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Omid Kohandel Gargari, and Gholamreza Habibi “Enhancing Medical AI with Retrieval-Augmented Generation: A Mini Narrative Review,” Digit Health, vol. 11, pp. 1-7, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Jaedong Lee et al., “Enhancing Large Language Model Reliability: Minimizing Hallucinations with Dual Retrieval-Augmented Generation based on the Latest Diabetes Guidelines,” Journal of Personalized Medicine, vol. 14, no. 12, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Awais Khan Nawabi et al., “D-Care: A Multi-Tone LLM-based Chatbot Assistant for Diabetes Patients,” Biostec Healthinf, vol. 2, pp. 766-773, 2025.
[Google Scholar]

[15] Aurélia Naoko Naef et al., “Impact of Digital Health Interventions for Adolescents with Type 1 Diabetes Mellitus on Health Literacy: A Systematic Review,” BMC Endocrine Disorders, vol. 23, no. 1, pp. 1-21, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Lukas Lindstrøm et al., “The Potential of Large Language Model-based Chatbot Solutions for Supplementary Counseling in Gestational Diabetes Care,” Journal of Diabetes Science and Technology, vol. 18, no. 5, pp. 1247-1248, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Rui Yang et al., “Retrieval-Augmented Generation for Generative Artificial Intelligence in Health Care,” Npj Health Systems, vol. 2, no. 1, pp. 1-5, 2025.
[CrossRef] [Google Scholar] [Publisher Link] 

[18] David J. Bunnell et al., “Bridging AI and Healthcare: A Scoping Review of Retrieval-Augmented Generation-Ethics, Bias, Transparency, Improvements, and Applications,” medRxiv, pp. 1-35, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Özgür Uğur et al., “Guided Decoding and its Critical Role in Retrieval-Augmented Generation,” 2025 33^rd Signal Processing and Communications Applications Conference (SIU), Sile, Istanbul, Turkiye, pp. 1-4, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Mahyar Abbasian et al., “Knowledge-Infused LLM-Powered Conversational Health Agent: A Case Study for Diabetes Patients,” 2024 46^th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA, pp. 1-4, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Matthew R. DeVerna et al., “The Invisible Risks of AI-Generated Health Information,” arXiv preprint, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Yein Choi et al., “Enhanced Retrieval-Augmented Generation using Low-Rank Adaptation,” Applied Sciences, vol. 15, no. 8, pp. 1-19, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Mohammed Al-Garadi et al., “Large Language Models in Healthcare,” arXiv preprint arXiv, pp. 1-18, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Salliah Shafi Bhat, Gufran Ahmad Ansari, and Mohd Dilshad Ansari, “Performance Analysis of Machine Learning based on Optimized Feature Selection for Type II Diabetes Mellitus,” Multimedia Tools and Applications, vol. 84, no. 8, pp. 4945-4964, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Ayodeji Akinsoji Okubanjo et al., “Development of a Low-Cost IoT-based E-Health Monitoring System for Diabetic Patients,” Journal of Electrical Systems and Information Technology, vol. 11, no. 1, pp. 1-20, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Isfafuzzaman Tasin et al., “Diabetes Prediction using Machine Learning and Explainable AI Techniques,” Healthcare Technology Letters, vol. 10, no. 1-2, pp. 1-10, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Hosam El-Sofany et al., “A Proposed Technique using Machine Learning for the Prediction of Diabetes Disease through a Mobile App,” International Journal of Intelligent Systems, vol. 2024, no. 1, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Harish Kanthathasan, and Muditha Tissera, “A Knowledge-Driven Approach for Enhancing Chronic Condition Accessibility with Large Language Models and Semantic Search,” 2025 9^th International Symposium on Innovative Approaches in Smart Technologies (ISAS), Gaziantep, Turkiye, pp. 1-5, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Swathi Buragadda et al., “A Comprehensive System for Diabetes Management and Prediction using AI-Driven Chatbot and Machine Learning Models,” 2025 International Conference on Inventive Computation Technologies (ICICT), Kirtipur, Nepal, pp. 97-103, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[30] M.A. Aizat Rahmat et al., “GluQo: IoT-based Non-Invasive Blood Glucose Monitoring,” Journal of Telecommunication, Electronic and Computer Engineering, vol. 9, no. 3-9, pp. 71-75, 2017.
[Google Scholar] [Publisher Link]

[31] Mohammed H. Al-Jammas et al., “A Non-Invasive Blood Glucose Monitoring System,” Computers in Biology and Medicine, vol. 191, 2025.
[CrossRef] [Google Scholar] [Publisher Link]