Establishing Classifiers With Clinical Laboratory Indicators to Distinguish COVID-19 From Community-Acquired Pneumonia: Retrospective Cohort Study.

BACKGROUND: The initial symptoms of patients with COVID-19 are very much like those of patients with community-acquired pneumonia (CAP); it is difficult to distinguish COVID-19 from CAP with clinical symptoms and imaging examination. OBJECTIVE: The objective of our study was to construct an effective model for the early identification of COVID-19 that would also distinguish it 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 (ie, CLI combinations) were utilized to establish COVID-19 versus CAP classifiers with machine learning algorithms, including random forest classifier (RFC), logistic regression classifier, and gradient boosting classifier (GBC). The performance of the classifiers was assessed by calculating the area under the receiver operating characteristic curve (AUROC) and recall rate in COVID-19 prediction using the test data set. RESULTS: The classifiers that were constructed with three algorithms from 43 CLI combinations showed high performance (recall rate >0.9 and AUROC >0.85) in COVID-19 prediction for the test data set. Among the high-performance classifiers, several CLIs showed a high usage rate; these included procalcitonin (PCT), mean corpuscular hemoglobin concentration (MCHC), uric acid, albumin, albumin to globulin ratio (AGR), neutrophil count, red blood cell (RBC) count, monocyte count, basophil count, and white blood cell (WBC) count. They also had high feature importance except for basophil count. The feature combination (FC) of PCT, AGR, uric acid, WBC count, neutrophil count, basophil count, RBC count, and MCHC was the representative one among the nine FCs used to construct the classifiers with an AUROC equal to 1.0 when using the RFC or GBC algorithms. Replacing any CLI in these FCs would lead to a significant reduction in the performance of the classifiers that were built with them. CONCLUSIONS: The classifiers constructed with only a few specific CLIs could efficiently distinguish COVID-19 from CAP, which could help clinicians perform early isolation and centralized management of COVID-19 patients.

Comparative Performance of Four Nucleic Acid Amplification Tests for SARS-CoV-2 Virus.

BACKGROUND: COVID-19 is caused by the Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2), which was discovered in 2019 and spread around the world in a short time. SARS-CoV-2 nucleic acid amplification tests (NAATs) have been rapidly developed and quickly applied to clinical testing of COVID-19. Aim of this study was to evaluate the performance of four NAAT assays. METHODS: Limit of detection (LOD), precision, accuracy, analytical specificity and analytical interference studies on four NAATs (Daan, Sansure, Hybribio, and Bioperfectus) were performed according to Clinical Laboratory Standards Institute protocols and guidelines. The four NAATs were compared using 46 clinical samples. RESULTS: The LOD of the N gene for Daan, Sansure, and Hybribio was 500 copies/mL, and that for Bioperfectus was 1,000 copies/mL. The LOD of the ORF1ab gene for Daan, Bioperfectus, and Hybribio was 3,000 copies/mL, and that for Sansure was 2,000 copies/mL. A good precision was shown at the concentration above 20% of the LOD for all four NAATs, with all individual coefficients of variation below 3.6%. Satisfactory results were also observed in the accuracy, analytical specificity, and analytical interference tests. The results of the comparison test showed that Daan, Sansure, and Hybribio NAATs could detect the samples with a specificity of 100% (30/30) and a sensitivity of 100% (16/16), whereas Bioperfectus NAAT detected the samples with a specificity of 100% (30/30) and a sensitivity of 81.25% (13/16). However, no significant difference in sensitivity was found between Bioperfectus NAAT and the three other NAATs (p > 0.05). CONCLUSIONS: The four SARS-CoV-2 NAATs showed comparable performance, with the LOD of the N gene lower than the LOD of the ORF1ab gene.