Using machine learning method for classification body mass index of people for clinical decision

Introduction: Body mass index (BMI) is an acceptable method to measure overweight and obesity among the population. Objectives: The aim of this study was evaluating application machine learning algorithms for classifying body clinical purposes. Patients Methods: In descriptive study, we selected dataset 1316 people who randomly from all area Ardabil city in Iran. Dataset included demographic anthropometric data. Classification such as random forest (RF), Gaussian Naive Bayes (GNB), decision tree (DT), support vector machines (SVM), multi-layer perceptron (MLP), K-nearest neighbors (KNN) logistic regression (LR) with 10-fold cross-validation were conducted classify data based on BMI. performance evaluated precision, recall, mean squared errors (MSE) accuracy indices. All programing done by Python 3.7 Jupyter Notebook. Results: According BMI, 603(45.8%) samples normal 713 (54.2%) at-risk. precision RF, GNB, DT, SVM, MLP, KNN LR at risk 0.93, 0.86, 0.99, 0.82, 100, 0.82 0.99 respectively. Additionally, 95%, 83%, 100%, 82%, 82% 100 %. Conclusion: comparison showed that, LR, MLP DT had higher than other detecting