A Novel Effective Forecasting Model Developed Using Ensemble Machine Learning For Early Prognosis of Asthma Attack and Risk Grade Analysis

Abstract

Research curiosity enlarging the concern of clinician and researchers towards combination of medical science together with artificial intelligence to develop cost effective predictive model for asthma exacerbation. To accumulate the classification consequences, extensively known ensemble machine learning methods pivotal to artificial intelligence techniques are investigated and novel predictive model developed using catboost classifier that produced comparatively improved outcomes to predict the occurrence of asthma and asthma risk grade. Proposed model result is compared with other classifiers which are Support vector machine (SVM), K-Nearest neighbors (KNN), Logistic regression, Adaboost classifier, Gradient boosting classifier, Random forest, Decision tree. Model regulated classification accuracy as high as 93% with datasets selected for formation of early prognosis model of asthma disease by embracing only 20% of the features in the reduced feature set.