ABSTRACT
BACKGROUND: The WHO ordinal severity scale has been used to predict mortality and guide trials in COVID-19. However, it has its limitations. OBJECTIVE: The present study aims to compare three classificatory and predictive models: the WHO ordinal severity scale, the model based on inflammation grades, and the hybrid model. DESIGN: Retrospective cohort study with patient data collected and followed up from March 1, 2020, to May 1, 2021, from the nationwide SEMI-COVID-19 Registry. The primary study outcome was in-hospital mortality. As this was a hospital-based study, the patients included corresponded to categories 3 to 7 of the WHO ordinal scale. Categories 6 and 7 were grouped in the same category. KEY RESULTS: A total of 17,225 patients were included in the study. Patients classified as high risk in each of the WHO categories according to the degree of inflammation were as follows: 63.8% vs. 79.9% vs. 90.2% vs. 95.1% (p<0.001). In-hospital mortality for WHO ordinal scale categories 3 to 6/7 was as follows: 0.8% vs. 24.3% vs. 45.3% vs. 34% (p<0.001). In-hospital mortality for the combined categories of ordinal scale 3a to 5b was as follows: 0.4% vs. 1.1% vs. 11.2% vs. 27.5% vs. 35.5% vs. 41.1% (p<0.001). The predictive regression model for in-hospital mortality with our proposed combined ordinal scale reached an AUC=0.871, superior to the two models separately. CONCLUSIONS: The present study proposes a new severity grading scale for COVID-19 hospitalized patients. In our opinion, it is the most informative, representative, and predictive scale in COVID-19 patients to date.
Subject(s)
COVID-19 , COVID-19/diagnosis , Humans , Inflammation/diagnosis , Retrospective Studies , SARS-CoV-2 , Treatment Outcome , World Health OrganizationABSTRACT
BACKGROUND: Efficient and early triage of hospitalized Covid-19 patients to detect those with higher risk of severe disease is essential for appropriate case management. METHODS: We trained, validated, and externally tested a machine-learning model to early identify patients who will die or require mechanical ventilation during hospitalization from clinical and laboratory features obtained at admission. A development cohort with 918 Covid-19 patients was used for training and internal validation, and 352 patients from another hospital were used for external testing. Performance of the model was evaluated by calculating the area under the receiver-operating-characteristic curve (AUC), sensitivity and specificity. RESULTS: A total of 363 of 918 (39.5%) and 128 of 352 (36.4%) Covid-19 patients from the development and external testing cohort, respectively, required mechanical ventilation or died during hospitalization. In the development cohort, the model obtained an AUC of 0.85 (95% confidence interval [CI], 0.82 to 0.87) for predicting severity of disease progression. Variables ranked according to their contribution to the model were the peripheral blood oxygen saturation (SpO2)/fraction of inspired oxygen (FiO2) ratio, age, estimated glomerular filtration rate, procalcitonin, C-reactive protein, updated Charlson comorbidity index and lymphocytes. In the external testing cohort, the model performed an AUC of 0.83 (95% CI, 0.81 to 0.85). This model is deployed in an open source calculator, in which Covid-19 patients at admission are individually stratified as being at high or non-high risk for severe disease progression. CONCLUSIONS: This machine-learning model, applied at hospital admission, predicts risk of severe disease progression in Covid-19 patients.
Subject(s)
COVID-19/classification , Machine Learning , Adult , Aged , Area Under Curve , COVID-19/diagnosis , COVID-19/epidemiology , COVID-19/therapy , Cohort Studies , Female , Forecasting , Hospitalization/statistics & numerical data , Humans , Male , Middle Aged , Models, Statistical , ROC Curve , Respiration, Artificial , Retrospective Studies , Risk Assessment , SARS-CoV-2/isolation & purification , Severity of Illness Index , Spain/epidemiology , Triage/methodsABSTRACT
BACKGROUND: The evidence for the efficacy of glucocorticoids combined with tocilizumab (TCZ) in COVID-19 comes from observational studies or subgroup analysis. Our aim was to compare outcomes between hospitalized COVID-19 patients who received high-dose corticosteroid pulse therapy and TCZ and those who received TCZ. METHODS: A retrospective single-center study was performed on consecutive hospitalized patients with severe COVID-19 between 1 March and 23 April 2020. Patients treated with either TCZ (400-600 mg, one to two doses) and methylprednisolone pulses (MPD-TCZ group) or TCZ alone were analyzed for the occurrence of a combined endpoint of death and need for invasive mechanical ventilation during admission. The independence of both treatment groups was tested using machine learning classifiers, and relevant variables that were potentially different between the groups were measured through a mean decrease accuracy algorithm. RESULTS: An earlier date of admission was significantly associated with worse outcomes regardless of treatment type. Twenty patients died (27.0%) in the TCZ group, and 33 (44.6%) died or required intubation (n = 74), whereas in the MPD-TCZ group, 15 (11.0%) patients died and 29 (21.3%) patients reached the combined endpoint (n = 136; p = 0.006 and p < 0.001, respectively). Machine learning methodology using a random forest classifier confirmed significant differences between the treatment groups. CONCLUSIONS: MPD and TCZ improved outcomes (death and invasive mechanical ventilation) among hospitalized COVID-19 patients, but confounding variables such as the date of admission during the COVID-19 pandemic should be considered in observational studies.