key: cord-0842964-kp2pf2vj authors: Oh, Jee Youn title: Predictors of Worsening Oxygenation in COVID-19 date: 2021-03-10 journal: Tuberc Respir Dis (Seoul) DOI: 10.4046/trd.2021.0034 sha: fba7a63560fa5666b158b7d24dc6102a5dc3bdc7 doc_id: 842964 cord_uid: kp2pf2vj nan The spread of coronavirus disease 2019 (COVID-19) has resulted in a pandemic, leading to a sudden and substantial increase in the use of medical resources worldwide 1 . Although the key characteristic of COVID-19 is that most patients have a mild clinical course, some patients demonstrate rapid deterioration to respiratory failure 2 . Thus, it is important to triage and stratify the risk of COVID-19 patients in order to optimize the distribution of medical resources and prevent progression 3 . Worsening oxygenation is the key finding that forecasts severe cases 4 , but investigating biomarkers for worsening oxygenation is still an unmet medical need in COVID-19 patients. Hahm et al. 5 retrospectively evaluated the factors associated with worsening oxygenation in patients with non-severe COVID-19 pneumonia. Quantitative analysis of computed tomography (CT) using artificial intelligence (AI) tools as well as laboratory findings such as C-reactive protein (CRP), ferritin, lactic dehydrogenase (LDH), and lower lymphocyte counts were predictors of worsening oxygenation. Although this was a retrospective, single-center study involving a small number of patients with non-severe pneumonia, it synthetically analyzed the factors known to be associated with deterioration including comorbidities, pro-inflammatory cytokines, and CT findings using AI tools, and provided an automatic and objective estimation of the disease burden. Previous studies have reported that age and underlying diseases may be risk factors for COVID-19 patients requiring oxygenation, which is a well-known risk factor for other pneumonia 6 . Particularly for COVID-19, some patients progress to hypoxemia rapidly at approximately 1-2 weeks after onset, likely not due to the cytopathic activity of the virus, but due to the cytokine storm, as evidenced by increased proinflammatory cytokines 7 . Thus, inflammatory markers such as CRP, procalcitonin levels, neutrophil-lymphocyte ratio, and the rate of change of CRP have been reported to predict the progression of COVID-19 8 . Subsequently, more critical COVID-19 patients release procoagulant autoantibodies and markers associated with cytokine-mediated tissue damage and organ failure, and these are reported markers predicting severe COVID-19 or poor outcomes of COVID-19 9 . Elevated D-dimer levels, LDH, troponin I, and thrombocytopenia in patients with severe COVID-19 have also been reported, suggesting that a hypercoagulable state may contribute to the severity of illness and mortality 10 . In non-severe cases, chest CT is pivotal in predicting prognosis 11, 12 . Chest quantitative CT has a promising role in the early diagnosis of COVID-19 and provides new metrics for predicting clinical outcomes 13 . The binding of coronavirus spike protein to angiotensin-converting enzyme II receptor increases pulmonary capillary permeability and causes diffuse opacities in CT 14 . CT could reflect the early pathogenesis of COVID-19 inflammation, even though chest radiography could not detect the abnormalities 15 . In fact, CT severity score is associated with inflammatory levels, and CT severity score on admission is an independent risk factor for early deterioration 16 . Moreover, the rapid improvement of AI has enabled the automatic quantification of lesions and the prediction of outcomes more precisely. There have been thousands of reports on biomarkers for predicting outcomes of COVID-19 with various parameters, diverse clinical severities, and outcomes. In particular, many studies have dealt with mortality predictors for severe CO-VID-19 cases 4,10,17 . However, rather than predicting mortality for initially critical patients, Hahm et al. 5 investigated the scoring of non-severe patients on potential rapidly worsening oxygenation, which would be a more useful tool in regions where non-severe cases are more prevalent due to mass surveillance Responding to COVID-19: a once-in-a-century pandemic? Pathophysiology, transmission, diagnosis, and treatment of coronavirus disease 2019 (COVID-19): a review The toughest triage: allocating ventilators in a pandemic The association between mortality and the oxygen saturation and fraction of inhaled oxygen in patients requiring oxygen therapy due to COVID-19-associated pneumonia Factors associated with worsening oxygenation in patient with non-severe COVID-19 pneumonia Risk stratification of patients admitted to hospital with covid-19 using the ISARIC WHO Clinical Characterisation Protocol: development and validation of the 4C Mortality Score Is a "cytokine storm" relevant to COVID-19? Prediction models for diagnosis and prognosis of COVID-19 infection: systematic review and critical appraisal Thrombocytopathy and endotheliopathy: crucial contributors to COVID-19 thromboinflammation Risk factors for mortality in hospitalized patients with COVID-19: an overview in a Mexican population Integrating deep learning CT-scan model, biological and clinical variables to predict severity of CO-VID-19 patients Clinically applicable AI system for accurate diagnosis, quantitative measurements, and prognosis of COVID-19 pneumonia using computed tomography Deep learning-based triage and analysis of lesion burden for COVID-19: a retrospective study with external validation SARS-CoV-2 receptor and regulator of the renin-angiotensin system: celebrating the 20th Anniversary of the Discovery of ACE2 Imaging tests for the diagnosis of COVID-19. Cochrane Database Syst Rev Early prediction of disease progression in COVID-19 pneumonia patients with chest CT and clinical characteristics Predictors of in-hospital COVID-19 mortality: a comprehensive systematic review and meta-analysis exploring differences by age, sex and health conditions Quarantine facility for patients with COVID-19 with mild symptoms in Korea: experience from eighteen residential treatment centers