Prediction of Intensive Care Cases for COVID-19 Pandemic in Malaysia: An Artificial Neural Networks Approach

Abstract

Coronavirus 2019 (COVID-19) pandemic in Malaysia is a part of the ongoing worldwide pandemic. The emergence of COVID-19 has led to high demand for intensive care services worldwide. However, the severity of COVID-19 patients that need intensive care unit (ICU) treatments requires details investigation. This study aims to predict the number of ICU cases due to COVID-19 disease in Malaysia. The prediction was done based on the data related to new, recovered, and treated cases which were collected from the website of the Ministry of Health Malaysia started from April until August 2020. Artificial Neural Networks Multilayers Perceptron Backpropagation (ANN-MLP-BPP) model was developed for predicting ICU cases based on the usage of the real set of data. The ANN-MLP-BPP model was validated by splitting the data into 80% for training and 20% for testing. The results show that with the increase in the number of undertreated cases, the number of predicted ICU will also be increased. The predicted ICU admission is almost equivalent to a 1 percent increment of the number of cases undertreated. These findings may help the frontline physicians in planning and handling the facilities management during the COVID-19 pandemic situation in the future.