A super learner ensemble of 14 statistical learning models for predicting COVID-19 severity among patients with cardiovascular conditions

Abstract

Background Cardiovascular and other circulatory system diseases have been implicated in the severity of COVID-19 in adults. This study provides a super learner ensemble of models for predicting COVID-19 severity among these patients. Method The Cerner Real-World Database was used for this study. Data on adult patients (18 years or older) with cardiovascular and related circulatory diseases between 2017 and 2019 were retrieved and a total of 13 these conditions were identified. Among these patients, 33,042 admitted with positive diagnoses for COVID-19 between March 2020 and June 2020 (from 59 hospitals) were identified and selected for this study. A total of 14 statistical and machine learning models were developed and combined into a single more powerful super learning model for predicting COVID-19 severity on admission to the hospital. Result LASSO regression, a full extreme gradient boosting model with tree depth of 2, and a full logistic regression model were the most predictive with cross-validated AUROCs of 0.7964, 0.7961, and 0.7958 respectively. The resulting super learner ensemble model had a cross validated AUROC of 0.8006 (range: 0.7814, 0.8163). The unbiased AUROC of the super learner model on an independent test set was 0.8057 (95% CI: 0.7954, 0.8159). Conclusion Highly predictive models can be built to predict COVID-19 severity of patients with cardiovascular and other circulatory conditions. Super learning ensembles will improve individual and classical ensemble models significantly.

Association of Congenital and Acquired Cardiovascular Conditions With COVID-19 Severity Among Pediatric Patients in the US

“…2,3 In adults, preexisting cardiovascular conditions have been implicated in severe COVID-19 and are associated with increased morbidity and mortality. [4][5][6][7][8][9][10][11] An early meta-analysis of COVID-19 cases in China found an association between cardiovascular conditions and unfavorable clinical outcomes. 4,7,12 has been shown to be associated with development of cardiovascular conditions, including myocardial injury, arrhythmia, acute coronary syndrome, and venous thromboembolism.…”

Data-driven machine learning: A new approach to process and utilize biomedical data

“…It has also been observed that the severity of Covid-19 infection in adults has a direct and bidirectional relationship with the occurrence and severity of circulatory and cardiovascular diseases [88] . A study led by Ehwerhemuepha et al demonstrated the usage of ensemble models in the prediction of Covid-19 severity among patients having cardiovascular diseases, and maybe even for the general population as well [89] . However, the study was limited demographically due to the availability of only local data (namely, white patients), which may have effects on the predictive accuracy of the model on a general scale.…”

“…Patient data analyzed using these algorithms has shown efficient detection and diagnosis, better response to healthcare services, accompanied by the increase in clinical efficiency and resource reallocation (especially in the case of predictive algorithms) [15] , [16] . Very recently, combinations of ML-based algorithms with deep learning and ensemble systems have been successfully implemented in the diagnosis and detection of various traditional diseases like cancer and Alzheimer's disease [63] , [72] , [75] , [79] , [82] , [83] and even in the case of Covid-19 [50] , [86] , [89] , which has been ravaging the world. Some models have also been used to study pathogenesis and other aspects of cellular biology [36] .…”

Interval forecasts of weekly incident and cumulative COVID-19 mortality in the United States: A comparison of combining methods

“…This has encouraged the more recent applications of combining in infectious disease prediction [ 14 , 26 – 29 ], including online platforms that present visualisations of combined probabilistic forecasts of COVID-19 data from the U.S, reported by the Centers for Disease Control and Prevention (CDC), and from Europe, reported by the European Centre for Disease and Control (EDCD). Other examples or combined probabilistic forecasts are in vaccine trial planning [ 30 ] and diagnosing disease [ 31 ]. These examples have mainly focused on simple mean and median ‘ensembles’ and, in the case of prediction of COVID-19 data, published studies have primarily involved short periods of data, which rules out the consideration of more sophisticated methods, such as those weighted by historical accuracy.…”