RESUMO
BACKGROUND: To develop machine learning classifiers at admission for predicting which patients with coronavirus disease 2019 (COVID-19) who will progress to critical illness. METHODS: A total of 158 patients with laboratory-confirmed COVID-19 admitted to three designated hospitals between December 31, 2019 and March 31, 2020 were retrospectively collected. 27 clinical and laboratory variables of COVID-19 patients were collected from the medical records. A total of 201 quantitative CT features of COVID-19 pneumonia were extracted by using an artificial intelligence software. The critically ill cases were defined according to the COVID-19 guidelines. The least absolute shrinkage and selection operator (LASSO) logistic regression was used to select the predictors of critical illness from clinical and radiological features, respectively. Accordingly, we developed clinical and radiological models using the following machine learning classifiers, including naive bayes (NB), linear regression (LR), random forest (RF), extreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), K-nearest neighbor (KNN), kernel support vector machine (k-SVM), and back propagation neural networks (BPNN). The combined model incorporating the selected clinical and radiological factors was also developed using the eight above-mentioned classifiers. The predictive efficiency of the models is validated using a 5-fold cross-validation method. The performance of the models was compared by the area under the receiver operating characteristic curve (AUC). RESULTS: The mean age of all patients was 58.9±13.9 years and 89 (56.3%) were males. 35 (22.2%) patients deteriorated to critical illness. After LASSO analysis, four clinical features including lymphocyte percentage, lactic dehydrogenase, neutrophil count, and D-dimer and four quantitative CT features were selected. The XGBoost-based clinical model yielded the highest AUC of 0.960 [95% confidence interval (CI): 0.913-1.000)]. The XGBoost-based radiological model achieved an AUC of 0.890 (95% CI: 0.757-1.000). However, the predictive efficacy of XGBoost-based combined model was very close to that of the XGBoost-based clinical model, with an AUC of 0.955 (95% CI: 0.906-1.000). CONCLUSIONS: A XGBoost-based based clinical model on admission might be used as an effective tool to identify patients at high risk of critical illness.
RESUMO
BACKGROUND: The pandemic due to the novel coronavirus disease 2019 (COVID-19) has resulted in an increasing number of patients need to be tested. We aimed to determine if the use of integrated laboratory data can discriminate COVID-19 patients from other pulmonary infection patients. METHODS: This retrospective cohort study was conducted at Kunming Third People's Hospital in China from January 20 to February 28, 2020. Medical records and laboratory data were extracted and combined for COVID-19 and other pulmonary infection patients on admission. A partial least square discriminant analysis (PLS-DA) model was constructed and calibrated to discriminate COVID-19 from other pulmonary infection patients. RESULTS: COVID-19 patients diagnosed and treated in Kunming were balanced in terms of sex and covered all age groups. Most of them were mild cases; only five were severe cases. The first two dimensions of the PLS-DA model could classify COVID-19 and other pulmonary infection patients with an accuracy of 96.6% (95.1% in the cross-validation model). Basophil count, the proportion of basophils, prothrombin time, prothrombin time activity, and international normalized ratio were the five most discriminant biomarkers. CONCLUSION: Integration of biomarkers can discriminate COVID-19 patients from other pulmonary infections on admission to hospital and thus may be a supplement to nucleic acid tests.