Abstract: Diabetes mellitus, a chronic metabolic disorder marked by elevated blood glucose levels, is a growing global health issue with rising prevalence rates. Early detection and prediction are essential for preventing serious complications and improving patient outcomes. This study provides an in-depth analysis of diabetes prediction using machine learning techniques, emphasizing the identification of critical risk factors and the creation of highly accurate predictive models. Leveraging diverse datasets that include demographic data, lifestyle behaviors, and medical history, machine learning algorithms such as decision trees, support vector machines, and neural networks are applied. The results reveal the effectiveness of these models in accurately assessing diabetes risk, offering a valuable resource for healthcare professionals. Furthermore, the research addresses challenges such as data imbalance, feature selection, and model interpretability, providing strategies to enhance the reliability and scalability of predictive systems. The findings underscore the transformative potential of artificial intelligence in healthcare, enabling timely interventions, reducing medical costs, and improving patient well-being.
Keywords: Machine Learning, Support Vector Machine (SVM), Decision Trees, Logistic Regression, Random Forest
Precision, Accuracy
|
DOI:
10.17148/IJARCCE.2024.131113
