Extreme gradient boosting machine learning method for predicting medical treatment in patients with acute bronchiolitis

Abstract Acute bronchiolitis is the most common lower respiratory tract infection of infancy. About 2% of infants under 12 months of age hospitalized with this condition each epidemic season. The choice of the correct treatment is important for the evolution of the disease. Therefore, a prediction model for medical treatment identification based on extreme gradient boosting (XGB) machine learning (ML) method is proposed in this paper. Four supervised machine learning algorithms including a k-nearest neighbours (KNN), decision tree (DT), Gaussian Naive Bayes (GNB) and support vector machine (SVM) were compared with the proposed XGB method. The performance of these methods was then tested implementing a standard 10-fold cross-validation process. The results indicate that the XGB has the best prediction accuracy (94%), high precision (>0.94) and high recall (>0.94). The KNN, SVM, and DT approaches also present moderate prediction accuracy (>87), moderate specificity (>0.87) and moderate sensitivity (>0.87). The GNB algorithm show relatively low classification performance. Based on these results for classification performance and prediction accuracy, the XGB is a solid candidate for a correct classification of patients to be treated. These findings suggest that XGB systems trained with clinical data may serve as a new tool to assist in the treatment of patients with acute bronchiolitis.