IoT-Enabled Machine Learning for Enhanced Diagnosis of Diabetes and Heart Disease in Resource-Limited Settings

Diabetes and heart disease are complex and widespread health issues that significantly impact global well-being. Timely and accurate diagnosis is vital for effective management and treatment. However, in regions with limited access to medical professionals, achieving swift assessments becomes challenging. To address this crucial healthcare need, this study proposes an innovative approach that leverages the synergy of Internet of Things (IoT) technology and machine learning techniques. By integrating IoT capabilities into a web-based application, medical laboratory results can be seamlessly connected and analyzed in real-time, enabling healthcare providers, pharmacies, and patients to access critical information remotely. This study makes use of Support Vector Machines (SVM) and logical regression algorithms. The dataset was acquired from Kaggle, and preprocessing was done to ensure robustness. The models achieve a result, with the Support Vector Machine (SVM) model achieving 83.5% accuracy and the logical regression model reaching 81.9% accuracy. Moreover, the models demonstrate favorable precision, f1-score, and recall metrics, validating their reliability in diagnosing diabetes and heart disease. This IoT-driven web application exemplifies the potential to transform healthcare accessibility and quality, contributing to the advancement of the Sustainable Development Goal 3 (Good Health and Well-being). The integration of IoT and machine learning technologies showcases how innovative solutions can effectively address global health challenges, fostering a brighter future for healthcare worldwide.