Mechanical Ventilation and Death During Pregnancy Complicated by COVID-19: A Prognostic Analysis from the Brazilian COVID-19 Registry Score (preprint)

Background: Assessing predictors of critical outcomes in COVID-19 may advise timely treatments and better prepare facilities to overcome extra adversities during pregnancy. However, many clinical parameters of existent scores are deeply modified by physiologic adaptations. Our aim was to assess the feasibility of a prognosis score developed for general hospitalized adults with COVID-19 in Brazil to predict clinical adverse outcomes in pregnant women upon hospital admission. Methods This is a multicenter retrospective substudy of the Brazilian COVID-19 Registry, a multicenter cohort analysis in Brazilian hospitals, which provided an accurate score to predict in-hospital death. The present analysis assessed the performance of this model, ABC 2 -SPH, based on data of 3978 patients, to assess poor clinical outcomes in data from 85 pregnant women admitted due to COVID-19 from March 1, 2020, to May 5, 2021, in 19 Brazilian hospitals. The primary outcomes were death and the composite mechanical ventilation or death, and secondary were pregnancy outcomes and severe/critical Covid-19. The overall discrimination of the model was presented as the area under the receiver operating characteristic curve (AUROC). Results Thirty-one (36.5%) pregnant women had critical or severe COVID-19. Most of them had no previous comorbidities (64.7%). The median gestational age was 31.0 (26.0, 36.2) weeks; 38 (44.7%) women gave birth during hospitalization by Covid-19, most of them by C-section (76.3%). The need for mechanical ventilation or death occurred in 14 (17.3%) pregnant women. Severe and critical COVID-19 in pregnant women was associated with diabetes, inflammatory markers, and abnormal vital signals observed at admission. The model was not able to identify adverse clinical outcomes. The AUROC of predicting severe/critical Covid-19 illness was 0.595 (95% CI: 0.424-0.754); AUROC of the inpatient death discrimination was 0.683 (95% CI: 0.293-0.945), as the AUROC of mechanical ventilation or death discrimination was 0.591 (95% CI: 0.434-0.75). Conclusions The model ABC 2 -SPH developed in Brazilian general patients was not able to identify adverse clinical outcomes in pregnant women with COVID-19. We warn against the use of general inpatients COVID-19 prognosis in pregnant women. A more useful model for clinical prognosis is necessary concerning the specificities of pregnancy affected by COVID-19.

Development and validation of the MMCD score to predict kidney replacement therapy in COVID-19 patients (preprint)

Background: Acute kidney injury (AKI) is frequently associated with COVID-19 and the need for kidney replacement therapy (KRT) is considered an indicator of disease severity. This study aimed to develop a prognostic score for predicting the need for KRT in hospitalized COVID-19 patients. Methods: This study is part of the multicentre cohort, the Brazilian COVID-19 Registry. A total of 5,212 adult COVID-19 patients were included between March/2020 and September/2020. We evaluated four categories of predictor variables: (1) demographic data; (2) comorbidities and conditions at admission; (3) laboratory exams within 24 h; and (4) the need for mechanical ventilation at any time during hospitalization. Variable selection was performed using generalized additive models (GAM) and least absolute shrinkage and selection operator (LASSO) regression was used for score derivation. The accuracy was assessed using the area under the receiver operating characteristic curve (AUCROC). Risk groups were proposed based on predicted probabilities: non-high (up to 14.9%), high (15.0 to 49.9%), and very high risk ([≥] 50.0%). Results: The median age of the model-derivation cohort was 59 (IQR 47-70) years, 54.5% were men, 34.3% required ICU admission, 20.9% evolved with AKI, 9.3% required KRT, and 15.1% died during hospitalization. The validation cohort had similar age, sex, ICU admission, AKI, required KRT distribution and in-hospital mortality. Thirty-two variables were tested and four important predictors of the need for KRT during hospitalization were identified using GAM: need for mechanical ventilation, male gender, higher creatinine at admission, and diabetes. The MMCD score had excellent discrimination in derivation (AUROC = 0.929; 95% CI 0.918-0.939) and validation (AUROC = 0.927; 95% CI 0.911-0.941) cohorts an good overall performance in both cohorts (Brier score: 0.057 and 0.056, respectively). The score is implemented in a freely available online risk calculator (https://www.mmcdscore.com/). Conclusion: The use of the MMCD score to predict the need for KRT may assist healthcare workers in identifying hospitalized COVID-19 patients who may require more intensive monitoring, and can be useful for resource allocation.

Effectiveness, Explainability and Reliability of Machine Meta-Learning Methods for Predicting Mortality in Patients with COVID-19: Results of the Brazilian COVID-19 Registry (preprint)

The majority prognostic scores proposed for early assessment of coronavirus disease 19 (COVID-19) patients are bounded by methodological flaws. Our group recently developed a new risk score - ABC 2 SPH - using traditional statistical methods (least absolute shrinkage and selection operator logistic regression - LASSO). In this article, we provide a thorough comparative study between modern machine learning (ML) methods and state-of-the-art statistical methods, represented by ABC 2 SPH, in the task of predicting in-hospital mortality in COVID-19 patients using data upon hospital admission. We overcome methodological and technological issues found in previous similar studies, while exploring a large sample (5,032 patients). Additionally, we take advantage of a large and diverse set of methods and investigate the effectiveness of applying meta-learning, more specifically Stacking, in order to combine the methods' strengths and overcome their limitations. In our experiments, our Stacking solutions improved over previous state-of-the-art by more than 26% in predicting death, achieving 87.1% of AUROC and MacroF1 of 73.9%. We also investigated issues related to the interpretability and reliability of the predictions produced by the most effective ML methods. Finally, we discuss the adequacy of AUROC as an evaluation metric for highly imbalanced and skewed datasets commonly found in health-related problems.

Frequency and burden of neurological manifestations in hospitalized patients with COVID-19: findings from a large Brazilian cohort (preprint)

Background: Scientific data regarding the prevalence of COVID-19 neurological manifestations and prognosis in Latin America countries is still lacking. Therefore, the study aims to understand neurological manifestations of SARS-CoV 2 infection in the Brazilian population and its association with patient outcomes, such as in-hospital mortality. Methods This study is part of the Brazilian COVID-19 Registry, a multicentric COVID-19 cohort, including data from 37 Brazilian hospitals. For the analysis, patients were grouped according to the presence of self-reported vs. clinically-diagnosed neurological manifestations and matched with patients without neurological manifestations by age, sex, number of comorbidities, hospital, and whether or not patients ha neurological underlying disease. Results From 7,232 hospitalized patients with COVID-19, 27.8% presented self-reported neurological manifestations, 9.9% were diagnosed with a clinically-defined neurological syndrome and 1.2% did not show any neurological symptoms. In patients with self-reported symptoms, the most common ones were headache (19.3%), ageusia (10.4%) and anosmia (7.4%). Meanwhile, in the group with clinically-defined neurological syndromes, acute encephalopathy was the most common diagnosis (10.5%), followed by coma (0.6%1) and seizures (0.4%). Men and younger patients were more likely to self-report neurological symptoms, while women and older patients were more likely to develop a neurological syndrome. Patients with clinically-defined neurological syndromes presented a higher prevalence of comorbidities, as well as lower oxygen saturation and blood pressure at hospital admission. In the paired analysis, it was observed that patients with clinically-defined neurological syndromes were more likely to require ICU admission (46.9 vs. 37.9%), mechanical ventilation (33.4 vs. 28.2%), to develop acute heart failure (5.1 vs. 3.0%, p=0.037) and to die (40.7 vs. 32.3%, p<0.001) when compared to controls. Conclusion Neurological manifestations are an important cause of morbidity in COVID-19 patients. More specifically, patients with clinically defined neurological syndromes presented a poorer prognosis for the disease when compared to matched controls.

Hypothyroidism does not lead to worse prognosis in COVID-19: findings from the Brazilian COVID-19 registry (preprint)

Background: It is not clear whether previous thyroid diseases influence the course and outcomes of COVID-19. The study aims to compare clinical characteristics and outcomes of COVID-19 patients with and without hypothyroidism. Methods: The study is a part of a multicentric cohort of patients with confirmed COVID-19 diagnosis, including data collected from 37 hospitals. Matching for age, sex, number of comorbidities and hospital was performed to select the patients without hypothyroidism for the paired analysis. Results: From 7,762 COVID-19 patients, 526 had previously diagnosed hypothyroidism (50%) and 526 were selected as matched controls. The median age was 70 (interquartile range 59.0-80.0) years-old and 68.3% were females. The prevalence of underlying comorbidities were similar between groups, except for coronary and chronic kidney diseases, that had a higher prevalence in the hypothyroidism group (9.7% vs. 5.7%, p=0.015 and 9.9% vs. 4.8%, p=0.001, respectively). At hospital presentation, patients with hypothyroidism had a lower frequency of respiratory rate > 24 breaths per minute (36.1% vs 42.0%; p=0.050) and need of mechanical ventilation (4.0% vs 7.4%; p=0.016). D-dimer levels were slightly lower in hypothyroid patients (2.3 times higher than the reference value vs 2.9 times higher; p=0.037). In-hospital management was similar between groups, but hospital length-of-stay (8 vs 9 days; p=0.029) and mechanical ventilation requirement (25.4% vs. 33.1%; p=0.006) were lower for patients with hypothyroidism. There was a trend of lower in-hospital mortality in patients with hypothyroidism (22.1% vs. 27.0%; p=0.062). Conclusion: In this large Brazilian COVID-19 Registry, patients with hypothyroidism had a lower requirement of mechanical ventilation, and showed a trend of lower in-hospital mortality. Therefore, hypothyroidism does not seem to be associated with a worse prognosis, and should not be considered among the comorbidities that indicate a risk factor for COVID-19 severity.

Effectiveness, Explainability and Reliability of Machine Meta-Learning Methods for Predicting Mortality in Patients with COVID-19: Results of the Brazilian COVID-19 Registry (preprint)

Objective: To provide a thorough comparative study among state ofthe art machine learning methods and statistical methods for determining in-hospital mortality in COVID 19 patients using data upon hospital admission; to study the reliability of the predictions of the most effective methods by correlating the probability of the outcome and the accuracy of the methods; to investigate how explainable are the predictions produced by the most effective methods. Materials and Methods: De-identified data were obtained from COVID 19 positive patients in 36 participating hospitals, from March 1 to September 30, 2020. Demographic, comorbidity, clinical presentation and laboratory data were used as training data to develop COVID 19 mortality prediction models. Multiple machine learning and traditional statistics models were trained on this prediction task using a folded cross validation procedure, from which we assessed performance and interpretability metrics. Results: The Stacking of machine learning models improved over the previous state of the art results by more than 26% in predicting the class of interest (death), achieving 87.1% of AUROC and macroF1 of 73.9%. We also show that some machine learning models can be very interpretable and reliable, yielding more accurate predictions while providing a good explanation for the why. Conclusion: The best results were obtained using the meta learning ensemble model Stacking. State of the art explainability techniques such as SHAP values can be used to draw useful insights into the patterns learned by machine-learning algorithms. Machine learning models can be more explainable than traditional statistics models while also yielding highly reliable predictions. Key words: COVID-19; prognosis; prediction model; machine learning