Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 8 (2022) > Article

DOI: 10.14704/nq.2022.20.8.NQ44230

COVID-19 Mortality Prediction using Machine Learning Methods

Akashdeep Singh Rana, Dr.Harmeet Singh, Dr.VijayDhir


COVID-19 pandemic affects the world disastrously and also had a major effect on the world economy. We aimed to create the prediction model of in-hospital mortality using machine learning methods for patients with coronavirus disease 2019 (COVID-19) based on Chronic disease, age, smoking, and gender. The model was applied to the reliable data published by the government of Mexico and the dataset was collected by Mexican health authorities. The important variables used in this model are age, hypertension, gender, COPD, smoking, intubated, diabetes, asthma, pneumonia, and cardiovascular disease. Furthermore, we calculated Accuracy using data from January 1, 2020, to April 26, 2022. Only those patients who had full information were included in this study. Of the 43,110 patients admitted for COVID-19, 3864 (8.91 %) died during their stay. Linear Regression, Decision Tree, Naive Bayes, and K-Nearest Neighbour have been used to build the model. The Model provided an excellent result with an accuracy of 89.34 %. The model can be useful in estimating the in-hospital mortality of COVID-19 patients and minimizing the deaths due to COVID-19.


COVID-19, Prediction Model, Hybrid Model, Machine Learning

Full Text