Abstract
Objectives: The emergence of SARS-CoV-2 variants of concern has led to significant phenotypical changes in transmissibility, virulence, and public health measures. Our study used clinical data to compare characteristics between a Delta variant wave and a pre-Delta variant wave of hospitalized patients.
Methods: This single-center retrospective study defined a wave as an increasing number of COVID-19 hospitalizations, which peaked and later decreased. Data from the United States Department of Health and Human Services were used to identify the waves’ primary variant. Wave 1 (August 8, 2020-April 1, 2021) was characterized by heterogeneous variants, whereas Wave 2 (June 26, 2021-October 18, 2021) was predominantly the Delta variant. Descriptive statistics, regression techniques, and machine learning approaches supported the comparisons between waves.
Results: From the cohort (N = 1318), Wave 2 patients (n = 665) were more likely to be younger, have fewer comorbidities, require more care in the intensive care unit, and show an inflammatory profile with higher C-reactive protein, lactate dehydrogenase, ferritin, fibrinogen, prothrombin time, activated thromboplastin time, and international normalized ratio compared with Wave 1 patients (n = 653). The gradient boosting model showed an area under the receiver operating characteristic curve of 0.854 (sensitivity 86.4%; specificity 61.5%; positive predictive value 73.8%; negative predictive value 78.3%).
Conclusion: Clinical and laboratory characteristics can be used to estimate the COVID-19 variant regardless of genomic testing availability. This finding has implications for variant-driven treatment protocols and further research.
Keywords: COVID-19; Delta variant; Genomics; Gradient boosting model; Machine learning; Variants of concern.
【저자키워드】 COVID-19, machine learning, delta variant, Genomics, variants of concern., Gradient boosting model, 【초록키워드】 intensive care, machine learning, Human, variant, SARS-CoV-2 variant, Comorbidities, intensive care unit, Delta, C-reactive protein, ferritin, hospitalized patients, delta variant, lactate dehydrogenase, Genomics, variants, Predictive value, Retrospective study, sensitivity, specificity, Cohort, Positive predictive value, Characteristics, Transmissibility, SARS-CoV-2 variants, clinical, comparison, International, hospitalizations, Research, Patient, Treatment protocol, Waves, laboratory characteristics, fibrinogen, United States, characteristic, virulence, genomic, Care, prothrombin, Lactate, Inflammatory, Negative predictive value, Prothrombin time, receiver operating characteristic, international normalized ratio, Wave, Clinical data, public health measures, Descriptive statistics, Comparisons, single-center, THROMBOPLASTIN, receiver, heterogeneous, machine, Department, machine learning approaches, service, implication, Gradient, defined, identify, the United State, peaked, supported, characterized, can be used, activated, were used, changes in, machine learning approach, normalized, phenotypical, 【제목키워드】 variant, Laboratory, clinical, profile, the SARS-CoV-2,