Toward artificial intelligence (AI) applications in the determination of COVID-19 infection severity: considering AI as a disease control strategy in future pandemics

To guarantees patient survival and reduce the consumption of pharmaceutical and medical resources, an accurate diagnosis and assessment of COVID-19 severity are crucial. Since the outbreak of the pandemic, researchers have evaluated, identified, and predicted the severity of COVID-19 using a range of AI techniques. Due to the lack of a systematic review in the field of analysis of these studies, the present research rigorously reviewed all the pertinent literature.

Between December 1, 2019, and January 1, 2022, 762 articles were found by searching the PubMed, Scopus, Web of Science, and Scholar databases using the search method. 34 papers were chosen from this group as the research community's representatives using inclusion and exclusion criteria.

By looking at the machine learning approach used in this research, it can be seen that XGBoost and SVM algorithms were more prevalent and effective in identifying the severity of the condition, according to the results of the data analysis used in this study. A set of impressive features, including clinical, demographic, laboratory, and serology data, was used to calculate the severity of COVID-19 using ML algorithms. By calculating the performance metric, it can be concluded that the ML methods had high sensitivity and specificity in determining the severity of COVID-19.

Deep learning methods, as cutting-edge methods, have a significant tangible capacity for providing an accurate and efficient intelligent system for detecting and estimating the severity of COVID-19. It is recommended that in the future or other variants of COVID-19 epidemics, AI-based systems in conjunction with IoT, cloud storage, and 5G technologies be used to remove geographical problems in the rapid estimation of disease severity, immediate epidemic control before the pandemic, epidemic management, and lower treatment costs