Secure and Privacy-Preserving Automated Machine Learning Operations into End-to-End Integrated IoT-Edge-Artificial Intelligence-Blockchain Monitoring System for Diabetes Mellitus Prediction

Aug 6, 2026

Upload by Logic

Diabetes Mellitus remains a leading global cause of death and can produce severe complications when left untreated, creating a strong need for reliable early prediction. This paper presents an end-to-end IoT-edge-AI-blockchain system that predicts diabetes using clinical risk factors. Blockchain enables a unified, secure, and privacy-preserving view of patients’ data across hospitals. Comparative experiments evaluate sensor and measurement options and show random forest outperforms logistic regression and SVM, with additional effects from feature selection and balancing.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages41

Reading Time1 h 43 min

AccessFree to download

Abstract

Keywords

1. Introduction

arXiv :2211 .07643v2 [ cs .LG] 18 Aug 2023 Secure and Privacy-Preserving Automated Machine Learning Operations into End-to-End Integrated IoT-Edge-Artificial Intelligence-Blockchain Monitoring System for Diabetes Mellitus Prediction Alain Hennebellea , Leila Ismaila,b,c,∗, Huned Materwalab,c , Juma Al Kaabid,e , Priya Ranjanf, Rajiv Janardhanang a School of Computing and Information Systems, The University of Melbourne, Australia b Intelligent Distributed Computing and Systems (INDUCE) Research Laboratory, Department of Computer Science and Software Engineering, College of Information Technology, United Arab Emirates University, United Arab Emirates c National Water and Energy Center, United Arab Emirates University, United Arab Emirates d College of Health Sciences, Department of Internal Medicine, United Arab Emirates University, United Arab Emirates eMediclinic, Al Ain, Abu Dhabi, United Arab Emirates fBhubaneswar Institute of Technology, India g Faculty of Medical & Health Sciences, SRM Institute of Science & Technology, India Abstract Diabetes Mellitus, one of the leading causes of death worldwide, has no cure to date and can lead to severe health complications, such as retinopathy, limb amputation, cardiovascular diseases, and neuronal disease, if left untreated. Consequently, it becomes crucial to take precautionary measures to avoid/predict the occurrence of diabetes. Machine learning approaches have been proposed and evaluated in the literature for diabetes prediction. This paper proposes an IoT-edge-Artificial Intelligence (AI)-blockchain system for diabetes prediction based on risk factors. The proposed system is underpinned by the blockchain to obtain a cohesive view of the risk factors data from patients across different hospitals and to ensure security and privacy of the user’s data. Furthermore, we provide a comparative analysis of different medical sensors, devices, and methods to measure and collect the risk factors values in the system. Numerical experiments and comparative analysis were carried out between our proposed system, using the most accurate random forest (RF) model, and the two most used state-of-the-art machine learning approaches, Logistic Regression (LR) and Support Vector Machine (SVM), using three real-life diabetes datasets. The results show that the proposed system using RF predicts diabetes with 4.57% more accuracy on average compared to LR and SVM, with 2 .87 times more execution time. Data balancing without feature selection does not show significant improvement. The performance is improved by 1.14% and 0.02% after feature selection for PIMA Indian and Sylhet datasets respectively, while it reduces by 0 .89% for MIMIC III. Keywords: Artificial Intelligence (AI), Blockchain, Diabetes Mellitus Type 2, Diagnosis, 1. Introduction Diabetes Mellitus, commonly referred to as diabetes, is one of the top 10 leading causes of death globally [1] . It is a metabolic disease in which the body does not produce enough insulin or body cells do not appropriately respond to insulin, leading to increased blood sugar levels [2] . There are three main types of diabetes, type 1 and type 2 diabetes mellitus, and gestational diabetes [3] . According to a report by the International Diabetes Federation, 537 million adults (i.e., 1 in every 10 people), between the ages of 20-79 years, worldwide were having diabetes in 2021 [4] . Furthermore, this number is predicted to reach 643 million by 2030 and 783 million by 2045 . In 2021, diabetes was responsible for 6 .7 million deaths and caused at least USD 966 billion in health expenditure [4] . The etiopathology of type 2 diabetes mellitus has been linked to dynamic interactions between lifestyle, medical conditions, hereditary, psychosocial, and demographic risk factors [3] . Diabetes if not treated at an early stage can lead to severe complications such as retinopathy, limb amputation, cardiovascular diseases, and neuronal disease [5

FAQs

What is the core objective of the proposed system for diabetes management?

The system predicts diabetes incidence by analyzing diabetes risk factors obtained through medical sensors and devices, then using an accurate machine learning model for prediction.

How does blockchain contribute to security and privacy in the system?

Blockchain stores medical records, machine learning model parameters, and prediction results on a distributed ledger, supporting security, privacy, auditability, traceability, transparency, and trust across hospitals.

Which machine learning approach achieved the best diabetes prediction performance?

The random forest (RF) model produced the best results, predicting diabetes with higher average accuracy than logistic regression (LR) and support vector machine (SVM) in the conducted experiments.

Aug 6, 2026

Upload by Logic