Home / Current Issue / Paper 1717966
Machine Learning-Based Early Detection of Diabetes Using Lifestyle Data
Subject area: Science,Engineering and Technology · Area of research: Machine Learning
DOI: https://doi.org/10.64388/IREV9I11-1717966
Abstract
Diabetes mellitus is one of the most common chronic diseases in the world, causing significant morbidity and mortality from complications such as diabetes retinopathy, nephropathy, neuropathy, and cardiovascular abnormalities. Early detection is crucial for decreasing complications and improving patient outcomes. In recent years, machine learning (ML), deep learning (DL), and Internet of Things (IoT)-based technologies have emerged as potential diabetes prediction and management strategies. Traditional machine learning algorithms such as Logistic Regression, Support Vector Machines (SVM), and Random Forest (RF) have shown consistent performance on structured clinical datasets, whereas deep learning models, particularly Convolutional Neural Networks (CNNs), have achieved high accuracy in image-based diagnosis such as retinal analysis. However, previous research has a key weakness in that it relies too heavily on clinical datasets and fails to incorporate lifestyle-related aspects such as nutrition, physical activity, sleep patterns, and stress levels. Furthermore, many approaches lack real-time adaptability and customisation. This report provides a detailed evaluation of over 35 research publications and reveals major holes in current methodologies. A hybrid machine learning system is suggested, combining lifestyle data, clinical factors, and IoT-based real-time monitoring. The suggested approach intends to improve prediction accuracy, enable early diagnosis, and deliver individualized healthcare recommendations, all of which will help to progress intelligent and preventative healthcare systems.
Keywords
Machine Learning, Diabetes Prediction, Lifestyle Data, Early Detection, Healthcare Analytics, IoT, Deep Learning, Predictive Modeling.
How to cite this paper
@article{1717966,
author = {Harini R, Prof. Rakshitha B S},
title = {Machine Learning-Based Early Detection of Diabetes Using Lifestyle Data},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {2627-2630},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1717966.pdf},
abstract = {Diabetes mellitus is one of the most common chronic diseases in the world, causing significant morbidity and mortality from complications such as diabetes retinopathy, nephropathy, neuropathy, and cardiovascular abnormalities. Early detection is crucial for decreasing complications and improving patient outcomes. In recent years, machine learning (ML), deep learning (DL), and Internet of Things (IoT)-based technologies have emerged as potential diabetes prediction and management strategies. Traditional machine learning algorithms such as Logistic Regression, Support Vector Machines (SVM), and Random Forest (RF) have shown consistent performance on structured clinical datasets, whereas deep learning models, particularly Convolutional Neural Networks (CNNs), have achieved high accuracy in image-based diagnosis such as retinal analysis. However, previous research has a key weakness in that it relies too heavily on clinical datasets and fails to incorporate lifestyle-related aspects such as nutrition, physical activity, sleep patterns, and stress levels. Furthermore, many approaches lack real-time adaptability and customisation. This report provides a detailed evaluation of over 35 research publications and reveals major holes in current methodologies. A hybrid machine learning system is suggested, combining lifestyle data, clinical factors, and IoT-based real-time monitoring. The suggested approach intends to improve prediction accuracy, enable early diagnosis, and deliver individualized healthcare recommendations, all of which will help to progress intelligent and preventative healthcare systems.},
keywords = {Machine Learning, Diabetes Prediction, Lifestyle Data, Early Detection, Healthcare Analytics, IoT, Deep Learning, Predictive Modeling.},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1717966}
}