Obesity prediction using machine learning techniques

Abstract

Currently, safeguarding the community is vital in terms of finding solution to health related problems which can be achieved through medical research using the advent of technology. Obesity has become worldwide health concern as it is becoming a threat to the future. It is the most common health problems all over the world. Thousands of diseases as well as risks and death are associated to it. An early prediction of a disease will help both doctors and patients to act and minimize if not total eradication of the root cause or work on preventing the disease symptom from further deterioration. Going through patient’s medical history is one of the methods of identifying a disease which most time consuming as processing manually and it comes with an error-prone analyses and expense. Therefore, there is need to scientifically develop a predicting model of the occurrence of the disease or its existence using an automated technique as it is becoming a need of the day. In this research work, we used machine learning techniques on a public clinical available dataset to predict obesity status using different machine learning algorithms. Five machine learning algorithms were applied. Gboost Classifier, Random Forest Classifier, Decision Tree Classifier, K-Nearest Neighbor and Support Vector Machine and the model has shown promising results with as Gboost classifier achieves the highest accuracy of 99.05% as compared to other classifiers. Meanwhile, the K-Nearest Neighbor gave the relatively strong accuracy of 95.74%.

Predicting Obesity Levels with High Accuracy: Insights from a CatBoost Machine Learning Model

“…Yi et al [40] employed deep learning with convolutional neural networks (CNNs) for obesity prediction based on body images, achieving an accuracy of 91.7%. While innovative, their approach relies on visual data rather than the demographic, lifestyle, and health-related features used in our study Muse et al [18] used a combination of feature selection techniques and ML algorithms, including support vector machines and artificial neural networks, for obesity prediction. Their best-performing model achieved an accuracy of 93.2%, comparable to the CatBoost model's performance.…”

“…Kivrak et al (2017) employed convolutional neural networks (CNNs) on body images, achieving 91.7% accuracy [16]. Musa et al (2022) used ensemble learning methods, finding that gradient boosting reached 88.6% accuracy [17]. Maharana and Pradhan (2019) combined feature selection techniques with ML algorithms, where a genetic algorithm and SVM achieved 93.2% accuracy [18].…”

“…Musa et al (2022) used ensemble learning methods, finding that gradient boosting reached 88.6% accuracy [17]. Maharana and Pradhan (2019) combined feature selection techniques with ML algorithms, where a genetic algorithm and SVM achieved 93.2% accuracy [18]. Pouladzadeh et al (2016) developed a mobile app using CNNs to predict obesity from food images with 89.4% accuracy [19].…”

Implementation of K-Nearest Neighbors, Naïve Bayes Classifier, Support Vector Machine and Decision Tree Algorithms for Obesity Risk Prediction

“…According to earlier studies on the prediction of obesity status in 2022 by M.F. Anisat et al, the K-Nearest Neighbors (K-NN) algorithm technique offers a comparatively high accuracy of 95.74% [1]. Additionally, research on methods for classifying obesity levels was conducted in 2022 by Garba Salisu The study's findings show that, in terms of accuracy and precision, the Decision Tree method performs better than the Naïve Bayes algorithm [11].…”

“…Obesity is one of the most prevalent health issues in the world, and it's frequently linked to thousands of serious illnesses and even death. Owing to its growing risk to coming generations, this illness has emerged as a worldwide health issue [1]. The definition of obesity, as provided by the World Health Organization (WHO), is "an abnormal or excessive accumulation of fat that can impair health."…”