Comparing of Machine Learning Algorithms for Predicting ICU admission in COVID-19 hospitalized patients

The world hospital systems are presently facing many unprecedented challenges from coronavirus disease 2019 (COVID-19). Prediction the deteriorating or critical cases can help triage patients and assist in effective medical resource allocation.

To develop and validate Machine Learning (ML) models based clinical characteristics at hospital admission to assessment the future critical condition that needs Intensive Care Unit (ICU) hospitalization.

Using a single-center registry, we studied the records of 1225 confirmed COVID-19 hospitalized patients from Mostafa Khomeini hospital, focal point center for COVID-19 care and treatment in Ilam city, West of Iran. We applied 13 ML techniques from six different groups to predict ICU admission. To evaluate the performances of models the metrics derived from the confusion matrix were calculated.    

In this retrospective study, the median age was 50.9 years and 664 (54.20%) were male. The experimental results indicate that Meta algorithms have the best performance in ICU admission risk prediction with accuracy of 90.37%, sensitivity of 90.35%, precision of 88.25% , F-measure of 88.35% and ROC of 91%.

ML algorithms are useful predictive tools for real-time and accurate ICU risk prediction in patients with COVID-19 at hospital admission. This model enables, and potentially facilitates more responsive health systems that are beneficial to high risk COVID-19 patients.