Quantitative Computed Tomography Parameters in Coronavirus Disease 2019 Patients and Prediction of Respiratory Outcomes Using a Decision Tree
Jieun Kang, Jiyeon Kang, Woo Jung Seo, So Hee Park, Hyung Koo Kang, Hye Kyeong Park, Je Eun Song, Yee Gyung Kwak, Jeonghyun Chang, Sollip Kim, Ki Hwan Kim, Junseok Park, Won Joo Choe, Sung-Soon Lee and Hyeon-Kyoung Koo
This study aimed to describe quantitative CT parameters in COVID-19 patients based on disease severity and build decision trees for predicting respiratory outcomes using these parameters. Patients were classified into four categories based on disease severity. High attenuation area (HAA) was defined and showed an increase with severity. Whole-lung images were analyzed using commercial software Aview® system by Coreline Soft Inc. Decision tree models were built using clinical variables and initial laboratory values, with and without quantitative CT parameters. Results showed that HAA had a moderate correlation with lactate dehydrogenases (LDH) and C-reactive protein (CRP). The decision tree model including quantitative CT parameters showed greater accuracy in predicting respiratory failure. In conclusion, using quantitative CT parameters along with clinical characteristics, PCR Ct value, and blood biomarkers can provide higher accuracy in predicting respiratory failure.