In Journal of medical Internet research ; h5-index 88.0
BACKGROUND : The initial symptoms of the patients with COVID-19 are very much alike with those of the patients with community-acquired pneumonia (CAP), and it is difficult to distinguish COVID-19 from CAP by clinical symptoms and imaging examination.
OBJECTIVE : The objective of our study was to construct an effective model for the early identification of COVID-19 from CAP.
METHODS : The clinical laboratory indicators (CLIs) of 61 COVID-19 patients and 60 CAP patients were analyzed retrospectively. Random combinations of various CLIs (CLI_combinations) were utilized to establish COVID19_vs_CAP classifiers with machine learning algorithms including Random Forest Classifier (RFC), Logistic Regression (LR) and Gradient Boosting Classifier (GBC). The performance of the classifiers was assessed using the area under the receiver operating characteristic curve (AUC) and recall rate in COVID-19 prediction with the test data.
RESULTS : The classifiers constructed with three algorithms from 43 CLI_combinations showed high performance (recall rate > 0.9 and AUC > 0.85) in COVID-19 prediction for the test_set. In the high-performance classifiers, the CLIs including procalcitonin (PCT), mean corpuscular hemoglobin concentration (MCHC), urine acid (UA), albumin, ratio of albumin to globulin (AGR), neutrophil count (NEUTC), red blood cell count (RBC), monocyte count, basophil count (BASOC) and white blood count (WBC) showed a high usage rate. they also had high feature importance except BASOC. The feature combination (FC) of [PCT, AGR, UA, WBC, NEUTC, BASOC, RBC, MCHC] was the representative one among the nine FCs used to constructed the classifiers with an AUC equal to 1.0 by using RFC or GBC. Replacing any CLI in these FCs would lead to a significant reduction in the performance of the classifiers built with them.
CONCLUSIONS : The classifiers constructed with only a few specific CLIs could efficiently distinguish COVID-19 from CAP, which would help clinicians perform the early isolation and the centralized management of COVID-19 patients.
Dai Wanfa, Ke Pei-Feng, Li Zhen-Zhen, Zhuang Qi-Zhen, Huang Wei, Wang Yi, Xiong Yujuan, Huang Xian-Zhang