Machine Learning-based Model for Prediction of Clinical Deterioration in Hospitalized Patients by COVID-19. (preprint)

Background: Despite the publication of great number of tools to aid decisions in COVID-19 patients, there is a lack of good instruments to predict clinical deterioration. Methods COVID19-Osakidetza is a prospective cohort study recruiting COVID-19 patients. We collected information from baseline to discharge on: sociodemographic characteristics, comorbidities and associated medications, vital signs, treatment received and lab test results. Outcome was need for intensive ventilatory support (with at least standard high-flow oxygen face mask with a reservoir bag for at least 6 hours and need for more intensive therapy afterwards or Optiflow™ high-flow nasal cannula or noninvasive or invasive mechanical ventilation) and/or admission to a critical care unit and/or death during hospitalization. We developed a Catboost model summarizing the findings using Shapley Additive Explanations. Performance of the model was assessed using area under the receiver operating characteristic and prediction recall curves (AUROC and AUPRC respectively) and calibrated using the Hosmer-Lemeshow test. Results Overall, 1568 patients were included in the derivation cohort and 956 in the (external) validation cohort. The percentages of patients who reached the composite endpoint were 23.3% vs 20% respectively. The strongest predictors of clinical deterioration were arterial blood oxygen pressure, followed by age, levels of several markers of inflammation (procalcitonin, LDH, CRP) and alterations in blood count and coagulation. Some medications, namely, ATC AO2 (antiacids) and N05 (neuroleptics) were also among the group of main predictors, together with C03 (diuretics). In the validation set, the CatBoost AUROC was 0.79, AUPRC 0.21 and Hosmer-Lemeshow test statistic 0.36. Conclusions We present a machine learning-based prediction model with excellent performance properties to implement in EHRs. Our main goal was to predict progression to a score of 5 or higher on the WHO Clinical Progression Scale before patients required mechanical ventilation. Future steps are to externally validate the model in other settings and in a cohort from a different period and to apply the algorithm in clinical practice.

COVID-19 IN YOUNG AND MIDDLE-AGED ADULTS. PREDICTORS OF POOR OUTCOME AND CLINICAL DIFFERENCES. (preprint)

ABSTRACT Young and middle-aged adults are the largest group of patients infected with SARS-CoV-2 and some of them develop severe disease. Objective: To investigate clinical manifestations in adults aged 18-65 years hospitalized for COVID-19 and identify predictors of poor outcome. Secondary objectives: to explore potential differences compared to the disease in elderly patients and the suitability of the commonly used community-acquired pneumonia prognostic scales in younger populations. Methods: Multicenter prospective registry of consecutive patients hospitalized for COVID-19 pneumonia aged 18-65 years between March and May 2020. We considered a composite outcome of “poor outcome” including intensive care unit admission and/or use of noninvasive ventilation, continuous positive airway pressure or high flow nasal cannula oxygen therapies and/or death. Results: We identified 513 patients <65 years of age, from a cohort of 993 patients. 102 had poor outcomes (19.8%) and 3.9% died. 78% and 55% of patients with poor outcomes were classified as low risk based on CURB and PSI scores respectively. A multivariate Cox regression model identified six independent factors associated with poor outcome: heart disease, chest pain, anosmia, low oxygen saturation, high LDH and lymphocyte count <800/mL. Conclusions: COVID-19 in younger patients carries significant morbidity and differs in some respects from this disease the elderly. Baseline heart disease is a relevant risk factor, while anosmia and pleuritic pain are more common and protective. Hypoxemia, LDH and lymphocyte count are predictors of poor outcome. We consider that CURB and PSI scores are not suitable criteria for deciding admission in this population.