Using machine learning in prediction of ICU admission, mortality, and length of stay in the early stage of admission of COVID-19 patients

Predicting the negative conversion time of nonsevere COVID‐19 patients using machine learning methods

“…Previous studies have also constructed models for predicting the negative conversion time of COVID‐19 patients, but these models only considered several clinical features and did not take into account any laboratory tests, especially the vaccination status 20 . In addition, some machine learning models artificially classified the negative conversion time into short‐term (up to 7 days) and long‐term (more than 7 days) and then used binary classification to predict the simplified negative conversion time 22,23 . However, our model can predict patients' actual negative conversion time, which is more instructive for clinicians.…”

“…20 In addition, some machine learning models artificially classified the negative conversion time into short-term (up to 7 days) and long-term (more than 7 days) and then used binary classification to predict the simplified negative conversion time. 22,23 However, our model can predict patients' actual negative conversion time, which is more instructive for clinicians.…”

“…There is a large amount of literature on machine learning in COVID‐19, but it is relatively little machine learning related to the negative conversion time of non‐severe COVID‐19 patients. Saadatmand et al 22 developed an integrated framework to predict the possibility of prolonged negative conversion time in COVID‐19 patients by applying and comparing several classical ML algorithms. The results showed that the integrated model was robust and more accurate and performed slightly better than the basic model.…”

“…There is a large amount of literature on machine learning in COVID-19, but it is relatively little machine learning related to the negative conversion time of non-severe COVID-19 patients. Saadatmand et al 22 developed an integrated framework to predict the possibility of prolonged…”

Evaluation of stacked ensemble model performance to predict clinical outcomes: A COVID-19 study

“…Stacked ensembles have proven to generally be more accurate prediction models than any one base learner alone in clinical contexts [12] , [13] , [14] . In particular, a large number of studies have used stacked ensembles to study COVID-19 data, with many of them focusing on mortality (e.g., [15] , [16] , [17] , [18] , [19] , [20] , [21] ) and a few assessing cardiac events [22] , [23] . In spite of this progress, it remains unclear how to define the best model combinations for strong performance when using stacked generalization.…”