Are biological rhythms a predictive factor in the need for oxygen therapy in COVID-19 patients?

Given the extensive implementation of oxygen therapy in the management of COVID-19 patients, we aimed to identify the predictors for requiring oxygen therapy in individuals with COVID-19. We used the Artificial neural network models with the multilayer feed-forward and back-propagation algorithms. In model selection, different combinations of connections, the number of hidden layers, and the number of neurons in each hidden layer were evaluated. This study demonstrated that vital signs on admission (48.40%) and comorbidities (22.70%) are important factors in determining the need for oxygen therapy among the 18–64 age group. In older adult groups, biological rhythms (23.10%), comorbidities (25.20%), and clinical symptoms on admission (21.90%) can serve as indicators for the need for oxygen therapy. In adults’ groups, pay attention to the vital signs and comorbidities of the person is necessary. Meanwhile, for the Older Adults group, it is important to consider biological rhythms, comorbidities, and clinical symptoms.