An Early Detection of Asthma Using BOMLA Detector

Abstract

Asthma is a chronic and airway-induced disease, causing the incidence of bronchus inflammation, breathlessness, wheezing, is drastically becoming life-threatening. Even in the worst cases, it may destroy the quality to lead. Therefore, early detection of asthma is urgently needed, and machine learning can help identify asthma accurately. In this paper, a novel machine learning framework, namely BOMLA (Bayesian Optimisation-based Machine Learning framework for Asthma) detector has been proposed to detect asthma. Ten classifiers have been utilized in the BOMLA detector, where Support Vector Classifier (SVC), Random Forest (RF), Gradient Boosting Classifier (GBC), eXtreme Gradient Boosting (XGB), and Artificial Neural Network (ANN) are state-of-the-art classifiers. In contrast, Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QLDA), Naive Bayes (NB), Decision Tree (DT), and K-Nearest Neighbor (KNN) are conventional popular classifiers. ADASYN algorithm has also been employed in the BOMLA detector to eradicate the issues created due to the imbalanced dataset. It has even been attempted to delineate how the ADASYN algorithm affects the classification performance. The highest accuracy (ACC) and Matthews’s correlation coefficient (MCC) for an Asthma dataset provide 94.35% and 88.97%, respectively, using BOMLA detector when SVC is adapted, and it has been increased to 96.52% and 93.04%, respectively, when ensemble technique is adapted. The one-way analysis of variance (ANOVA) has also been performed in the 10-fold cross-validation to measure the statistical significance. A decision support system has been built as a potential application of the proposed system to visualize the probable outcome of the patient. Finally, it is expected that the BOMLA detector will help patients in their early diagnosis of asthma.

Keywords

• Classification
• clinical and non-clinical data
• asthma
• ADASYN
• ANOVA