Application of Machine Learning Models for Early Detection and Accurate Classification of Type 2 Diabetes

Abstract

Early detection of diabetes is essential to prevent serious complications in patients. The purpose of this work is to detect and classify type 2 diabetes in patients using machine learning (ML) models, and to select the most optimal model to predict the risk of diabetes. In this paper, five ML models, including K-nearest neighbor (K-NN), Bernoulli Naïve Bayes (BNB), decision tree (DT), logistic regression (LR), and support vector machine (SVM), are investigated to predict diabetic patients. A Kaggle-hosted Pima Indian dataset containing 768 patients with and without diabetes was used, including variables such as number of pregnancies the patient has had, blood glucose concentration, diastolic blood pressure, skinfold thickness, body insulin levels, body mass index (BMI), genetic background, diabetes in the family tree, age, and outcome (with/without diabetes). The results show that the K-NN and BNB models outperform the other models. The K-NN model obtained the best accuracy in detecting diabetes, with 79.6% accuracy, while the BNB model obtained 77.2% accuracy in detecting diabetes. Finally, it can be stated that the use of ML models for the early detection of diabetes is very promising.

An enhanced diabetes prediction amidst COVID-19 using ensemble models

“…As a more sophisticated imputation technique, k-NN was applied to predict missing values based on similar data points. This method takes into account the relationships between attributes, ensuring that the imputed value is consistent with other attributes of the dataset ( 32 ). We opted for k-Nearest Neighbors (k-NN) imputation due to its effectiveness in handling datasets where similarity between instances suggests a correlation, as is common in medical data.…”

“…This visual validation confirms that the median imputation has addressed the issue of zero values in the specified columns, resulting in a dataset that likely better represents the real-world distribution of these attributes. Algorithm 1 offers a structured representation of the imputation process, starting with identifying zeros, performing median imputation, and then using k-NN for a more advanced imputation ( 32 , 33 ).…”

Predicting Obesity in Nutritional Patients using Decision Tree Modeling

“…A DT is a nonparametric supervised learning algorithm that can be used for both classification and regression tasks. It has a hierarchical tree structure consisting of root nodes, branches, internal nodes, and leaf nodes [32], [33], [34]. Depending on the available features, both types of nodes perform evaluations by forming homogeneous subsets represented, by leaf nodes or end nodes.…”

Improving industrial security device detection with convolutional neural networks

“…The following are nonlinear activation functions such as ReLU. These layers learn to recognize simple image patterns and features such as edges, texture, and color [24].  Reduction layer: a reduction layer is usually added after the convolution layer to improve computational efficiency and reduce the size of the resulting features.…”