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

Abstract

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