Boosting Ensemble Machine Learning Approach for Covid-19 Death Prediction

It is critical for physicians to correctly classify patients during a plague and determine who deserves minimal health assistance. Machine learning methods have been presented reliably forecast the severity of COVID-19 disease. Previous research has often tested different machine algorithms evaluated performance under methods. may be necessary try several combinations discover optimal prediction model get best results. This aimed train boosting ensemble Artificial Neural Networks (ANN) choose that predicted how long would survive Covid19 infection. The dataset this study was obtained through kaggle.com. contains blood samples from 4313 retrospectively find relevant measures overall mortality. Out 48 parameters, only 16 selected parameters were considered using information gain weight each parameter. 5-fold cross-validation employed on training data set, Receiver Operating Characteristic (ROC) curves created verify better algorithms' independent algorithm choice criteria. models XGBoost, CatBoost, LightBGM achieved an accuracy 98%, AdaBoost 96%, 93% ANN, respectively, implying ANN lower than approaches.