Prediction of Diabetes in Females of Pima Indian Heritage: A Complete Supervised Learning Approach

• DOI: 10.17762/turcomat.v12i10.4958
• Publication Date: 2021-04-28
• Authors: Sourav Kumar Bhoi
• Keywords: F1 score; AdaBoost; Supervised Learning

Nowadays, diabetes is a common disease that affects millions of people over the world, and women are mostly affected by this disease. Recent healthcare studies have applied various innovative advanced technologies to diagnose predict their based on clinical data. One such machine learning (ML) in which diagnosis prediction can be made more accurately. In paper, designed model predicts females Pima Indians heritage taking dataset. Here, problem considered as binary classification problem. Therefore, supervised algorithms been used, tree (CT), support vector (SVM), k-Nearest Neighbour (k-NN), Naive Bayes (NB), Random Forest (RF), Neural Network (NN), AdaBoost (AB) Logistic Regression (LR). We use female diabetic dataset from Kaggle UCI data repository k-fold cross-validation carry out process training testing. determine area under curve (AUC), accuracy (CA), F1, precision recall results all compare them best algorithm suitable for prediction. For this, we Orange 3.24.1 open-source platform generate results, uses Python libraries. From it concluded LR performs better comparison other