A novel survival algorithm in COVID-19 intensive care patients: the classification and regression tree (CRT) method

Background/aim: The present study aimed to create a decision tree for the identification of clinical, laboratory and radio- logical data of individuals with COVID-19 diagnosis or suspicion of Covid-19 in the Intensive Care Units of a Training and Research Hospital of the Ministry of Health on the European side of the city of Istanbul. Materials and methods: The present study, which had a retrospective and sectional design, covered all the 97 patients treated with Covid-19 diagnosis or suspicion of COVID-19 in the intensive care unit between 12 March and 30 April 2020. In all cases who had symptoms admitted to the COVID-19 clinic, nasal swab samples were taken and thoracic CT was per- formed when considered necessary by the physician, radiological findings were interpreted, clinical and laboratory data were included to create the decision tree. Results: A total of 61 (21 women, 40 men) of the cases included in the study died, and 36 were discharged with a cure from the intensive care process. By using the decision tree algorithm created in this study, dead cases will be predicted at a rate of 95%, and those who survive will be predicted at a rate of 81%. The overall accuracy rate of the model was found at 90%. Conclusions: There were no differences in terms of gender between dead and live patients. Those who died were older, had lower MON, MPV, and had higher D-Dimer values than those who survived. Keywords: Survival algorithm; COVID-19 intensive care patients; CRT method.