ABSTRACT
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.
Subject(s)
COVID-19 , Diabetes MellitusABSTRACT
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.
Subject(s)
COVID-19 , Coronavirus InfectionsABSTRACT
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
Subject(s)
COVID-19 , Learning Disabilities , DeathABSTRACT
Chagas disease (CD) continues to be a major public health burden in Latina America. Information on the interplay between COVID-19 and CD is lacking. Our aim was to assess clinical characteristics and in-hospital outcomes of patients with CD and COVID-19, and to compare it to non-CD patients. Consecutive patients with confirmed COVID-19 were included from March to September 2020. Genetic matching for sex, age, hypertension, diabetes mellitus and hospital was performed in a 4:1 ratio. Of the 7,018 patients who had confirmed COVID-19, 31 patients with CD and 124 matched controls were included (median age 72 (64.-80) years-old, 44.5% were male). At baseline, heart failure (25.8% vs. 9.7%) and atrial fibrillation (29.0% vs. 5.6%) were more frequent in CD patients than in the controls (p
Subject(s)
Coinfection , Chagas Disease , Diabetes Mellitus , Hypertension , COVID-19ABSTRACT
Objective: Chagas disease (CD) continues to be a major public health burden in Latina America, where co-infection with SARS-CoV-2 can occur. However, information on the interplay between COVID-19 and Chagas disease is lacking. Our aim was to assess clinical characteristics and in-hospital outcomes of patients with CD and COVID-19, and to compare it to non-CD patients. Methods: Patients with COVID-19 diagnosis were selected from the Brazilian COVID-19 Registry, a prospective multicenter cohort, from March to September, 2020. CD diagnosis was based on hospital record at the time of admission. Study data were collected by trained hospital staff using Research Electronic Data Capture (REDCap) tools. Genetic matching for sex, age, hypertension, DM and hospital was performed in a 4:1 ratio. Results: Of the 7,018 patients who had confirmed infection with SARS-CoV-2 in the registry, 31 patients with CD and 124 matched controls were included. Overall, the median age was 72 (64.-80) years-old and 44.5% were male. At baseline, heart failure (25.8% vs. 9.7%) and atrial fibrillation (29.0% vs. 5.6%) were more frequent in CD patients than in the controls (p<0.05 for both). C-reactive protein levels were lower in CD patients compared with the controls (55.5 [35.7, 85.0] vs. 94.3 [50.7, 167.5] mg/dL). Seventy-two (46.5%) patients required admission to the intensive care unit. In-hospital management, outcomes and complications were similar between the groups. Conclusions: In this large Brazilian COVID-19 Registry, CD patients had a higher prevalence of atrial fibrillation and chronic heart failure compared with non-CD controls, with no differences in-hospital outcomes. The lower C-reactive protein levels in CD patients require further investigation.
Subject(s)
Coinfection , Heart Failure , Chagas Disease , Myotonic Dystrophy , Hypertension , COVID-19 , Atrial FibrillationABSTRACT
Objective: To develop and validate a rapid scoring system at hospital admission for predicting in-hospital mortality in patients hospitalized with coronavirus disease 19 (COVID-19), and to compare this score with other existing ones. Design: Cohort study Setting: The Brazilian COVID-19 Registry has been conducted in 36 Brazilian hospitals in 17 cities. Logistic regression analysis was performed to develop a prediction model for in-hospital mortality, based on the 3978 patients that were admitted between March-July, 2020. The model was then validated in the 1054 patients admitted during August-September, as well as in an external cohort of 474 Spanish patients. Participants: Consecutive symptomatic patients ([≥]18 years old) with laboratory confirmed COVID-19 admitted to participating hospitals. Patients who were transferred between hospitals and in whom admission data from the first hospital or the last hospital were not available were excluded, as well those who were admitted for other reasons and developed COVID-19 symptoms during their stay. Main outcome measures: In-hospital mortality Results: Median (25th-75th percentile) age of the model-derivation cohort was 60 (48-72) years, 53.8% were men, in-hospital mortality was 20.3%. The validation cohorts had similar age distribution and in-hospital mortality. From 20 potential predictors, seven significant variables were included in the in-hospital mortality risk score: age, blood urea nitrogen, number of comorbidities, C-reactive protein, SpO2/FiO2 ratio, platelet count and heart rate. The model had high discriminatory value (AUROC 0.844, 95% CI 0.829 to 0.859), which was confirmed in the Brazilian (0.859) and Spanish (0.899) validation cohorts. Our ABC2-SPH score showed good calibration in both Brazilian cohorts, but, in the Spanish cohort, mortality was somewhat underestimated in patients with very high (>25%) risk. The ABC2-SPH score is implemented in a freely available online risk calculator (https://abc2sph.com/). Conclusions: We designed and validated an easy-to-use rapid scoring system based on characteristics of COVID-19 patients commonly available at hospital presentation, for early stratification for in-hospital mortality risk of patients with COVID-19.