Evaluasi Model Klasifikasi Algoritma Terbimbing Kuantitatif terhadap Penyakit Diabetes

Abstract

Diabetes is a medical condition characterized by a persistent metabolic disorder resulting in elevated glucose levels in the bloodstream. This ailment has a profound impact on various bodily organs, including the heart, blood vessels, eyes, kidneys, and nervous system. One significant factor contributing to the rise in diabetes cases is the delay in diagnosing the condition. The objective of this study was to assess different algorithms for the detection of diabetes. The research involved an imbalanced dataset, necessitating the application of oversampling techniques like Synthetic Minority Over-sampling Technique (SMOTE) to address this imbalance. Two classification methods, namely Support Vector Machine (SVM) and Logistic Regression (LR), were employed in this investigation. The study findings revealed that when the K-Fold Cross Validation technique was combined with the SMOTE method, the Support Vector Machine (SVM) model exhibited superior levels of accuracy, precision, and recall in comparison to the Logistic Regression (LR) model, also utilizing the SMOTE technique. Nonetheless, if K-Fold Cross Validation was conducted without implementing the SMOTE technique, the results demonstrated that Logistic Regression outperformed the Support Vector Machine (SVM) model in terms of accuracy, precision, and recall.