ABSTRACT
The COVID-19 pandemic is continuously evolving with drastically changing epidemiological situations which are approached with different decisions: from the reduction of fatalities to even the selection of patients with the highest probability of survival in critical clinical situations. Motivated by this, a battery of mortality prediction models with different performances has been developed to assist physicians and hospital managers. Logistic regression, one of the most popular classifiers within the clinical field, has been chosen as the basis for the generation of our models. Whilst a standard logistic regression only learns a single model focusing on improving accuracy, we propose to extend the possibilities of logistic regression by focusing on sensitivity and specificity. Hence, the log-likelihood function, used to calculate the coefficients in the logistic model, is split into two objective functions: one representing the survivors and the other for the deceased class. A multi-objective optimization process is undertaken on both functions in order to find the Pareto set, composed of models not improved by another model in both objective functions simultaneously. The individual optimization of either sensitivity (deceased patients) or specificity (survivors) criteria may be conflicting objectives because the improvement of one can imply the worsening of the other. Nonetheless, this conflict guarantees the output of a battery of diverse prediction models. Furthermore, a specific methodology for the evaluation of the Pareto models is proposed. As a result, a battery of COVID-19 mortality prediction models is obtained to assist physicians in decision-making for specific epidemiological situations. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
INTRODUCTION: There is controversy regarding the best predictors of clinical deterioration in COVID-19. OBJECTIVE: This work aims to identify predictors of risk factors for deterioration in patients hospitalized due to COVID-19. METHODS DESIGN: Nested case-control study within a cohort. SETTING: 13 acute care centers of the Osakidetza-Basque Health Service. PARTICIPANTS: patients hospitalized for COVID-19 with clinical deterioration-defined as onset of severe ARDS, ICU admission, or death-were considered cases. Two controls were matched to each case based on age. Sociodemographic data; comorbidities; baseline treatment; symptoms; date of onset; previous consultations; and clinical, analytical, and radiological variables were collected. An explanatory model of clinical deterioration was created by means of conditional logistic regression. RESULTS: A total of 99 cases and 198 controls were included. According to the logistic regression analysis, the independent variables associated with clinical deterioration were: emergency department O2 saturation ≤90% (OR 16.6; 95%CI 4-68), pathological chest X-ray (OR 5.6; 95%CI 1.7-18.4), CRP > 100 mg/dL (OR 3.62; 95%CI 1.62-8), thrombocytopenia with <150,000 platelets (OR 4; 95%CI 1.84-8.6); and a medical history of acute myocardial infarction (OR 15.7; 95%CI, 3.29-75.09), COPD (OR 3.05; 95%CI 1.43-6.5), or HT (OR 2.21; 95%CI 1.11-4.4). The model's AUC was 0.86. On the univariate analysis, female sex and presence of dry cough and sore throat were associated with better clinical progress, but were not found to be significant on the multivariate analysis. CONCLUSION: The variables identified could be useful in clinical practice for the detection of patients at high risk of poor outcomes.
Subject(s)
COVID-19 , Clinical Deterioration , Case-Control Studies , Female , Humans , Risk Factors , SARS-CoV-2ABSTRACT
INTRODUCTION: There is controversy regarding the best predictors of clinical deterioration in COVID-19. OBJECTIVE: This work aims to identify predictors of risk factors for deterioration in patients hospitalized due to COVID-19. METHODS DESIGN: Nested case-control study within a cohort. Setting: 13 acute care centers of the Osakidetza-Basque Health Service. Participants: Patients hospitalized for COVID-19 with clinical deterioration-defined as onset of severe ARDS, ICU admission, or death-were considered cases. Two controls were matched to each case based on age. Sociodemographic data; comorbidities; baseline treatment; symptoms; date of onset; previous consultations; and clinical, analytical, and radiological variables were collected. An explanatory model of clinical deterioration was created by means of conditional logistic regression. RESULTS: A total of 99 cases and 198 controls were included. According to the logistic regression analysis, the independent variables associated with clinical deterioration were: emergency department O2 saturation ≤90% (OR 16.6; 95%CI 4-68), pathological chest X-ray (OR 5.6; 95%CI 1.7-18.4), CRP >100 mg/dL (OR 3.62; 95%CI 1.62-8), thrombocytopenia with < 150,000 platelets (OR 4; 95%CI 1.84-8.6); and a medical history of acute myocardial infarction (OR 15.7; 95%CI, 3.29-75.09), COPD (OR 3.05; 95%CI 1.43-6.5), or HT (OR 2.21; 95%CI 1.11-4.4). The model's AUC was 0.86. On the univariate analysis, female sex and presence of dry cough and sore throat were associated with better clinical progress, but were not found to be significant on the multivariate analysis. CONCLUSION: The variables identified could be useful in clinical practice for the detection of patients at high risk of poor outcomes.