Predicting Diabetes with Integrated Health-Lifestyle Fusion

Diabetes mellitus stands as a pervasive health concern globally, demanding proactive strategies for early detection and personalised management. This research pioneers a comprehensive approach integrating health indicators with lifestyle factors, encompassing daily habits, dietary preferences, and exercise regimens, to develop a robust predictive model for diabetes risk assessment. Leveraging machine learning methodologies, particularly Support Vector Machines (SVM) for classification, the study amalgamates diverse datasets to create a predictive model that accurately discerns an individual's susceptibility to diabetes. Furthermore, the research introduces an innovative embedded system device that utilises this predictive model to offer real-time, tailored recommendations. This device assimilates user-input data, predicts diabetes risk, and generates personalised suggestions displayed through an intuitive interface, guiding individuals toward healthier dietary choices and optimised workout routines. The integration of health indicators and lifestyle elements not only enhances predictive accuracy but also empowers individuals with actionable insights for proactive diabetes management. The outcomes of this research transcend conventional risk assessment methodologies, marking a significant advancement in personalised preventive healthcare strategies.