ABSTRACT
From late November 2019 until today, the Coronavirus (COVID19) has been circulating worldwide on a broad scale. The World Health Organization agrees that this is the world's most serious outbreak in the last twenty years. Algeria is no exception;although the relatively early precautions taken by the Algerian government, especially the national lockdown, the spread of Coronavirus has attained all cities. This study aims at clarifying how COVID-19 has spread in Algeria so fast in a short time and perform an intelligent system to predict confirmed, deaths, recovered, and active cases. This paper presents firstly a comprehensive analytics study on the spread of the pandemic to understand the COVID19 evolution in Algeria. Secondly, a predictive model based on a Long Short Term Memory Network is proposed and studied to estimate the future number of confirmed, deaths, recovered, and Active cases. © 2022 IEEE.
ABSTRACT
The COVID-19 pandemic has become a great challenge for healthcare systems due to the urgent need for ICUs that exceeded their capacity. Determining critical patients that require ICU transfer early will be valuable in optimising ICU resources and triage the patients. We propose a ML-based approach to predict ICU requirement within COVID-19 patients based on clinical data. A Mexican dataset of 7078737 cases and 38 attributes was considered in this paper. We trained four models MLP, DT, RF, and GB, on 70% of the data with five fold cross-validation and tested using the remaining 30%. Classification accuracies obtained were 97.72%, 97.14%, 99.06%, and 99.28%, respectively. Feature importance analysis based on GB model showed that age, hypertension, diabetes, obesity, pneumonia, days between symptoms onset and hospitalisation, location of the care unit, and private and public insurance are the main important factors. The latter factors highlight the importance of rapid and good quality care. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.