ABSTRACT
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.