Diabetes Risk Prediction and Classification using Machine Learning Techniques

Diabetes mellitus, a chronic-metabolic disorder, presents a significant global health challenge due to its increasing prevalence and associated complications. Timely prediction of diabetes can enable proactive interventions, thereby mitigating its adverse effects on individuals and healthcare systems. Recently, Machine learning (ML) techniques have emerged as a promising tool for diabetes prediction, leveraging data-driven approaches to enhance accuracy and efficiency. This research study evaluates the efficacy of various ML algorithms, including Support Vector Machine, K Nearest Neighbour, Random Forest, Logistic Regression, and Decision Tree, in predicting diabetes. Through comprehensive experimentation, this study compares the performance of these algorithms in diabetes prediction, revealing that Logistic Regression outperforms others in terms of accuracy. Furthermore, this study also investigates two different methodologies for ML-based classification tasks: traditional ML workflow and ML pipeline. The resultant findings demonstrate that the ML pipeline-based classification approach exhibits high performance when compared with streamlined ML processes for enhanced predictive outcomes. The significance of this research study lies in its contribution to advancing diabetes prediction methodologies, leveraging the power of machine learning to optimize diabetes prediction process.