Predictive Modeling of Morbidity and Mortality in Patients Hospitalized With COVID-19 and its Clinical Implications: Algorithm Development and Interpretation

Abstract

Background The COVID-19 pandemic began in early 2021 and placed significant strains on health care systems worldwide. There remains a compelling need to analyze factors that are predictive for patients at elevated risk of morbidity and mortality. Objective The goal of this retrospective study of patients who tested positive with COVID-19 and were treated at NYU (New York University) Langone Health was to identify clinical markers predictive of disease severity in order to assist in clinical decision triage and to provide additional biological insights into disease progression. Methods The clinical activity of 3740 patients at NYU Langone Hospital was obtained between January and August 2020; patient data were deidentified. Models were trained on clinical data during different parts of their hospital stay to predict three clinical outcomes: deceased, ventilated, or admitted to the intensive care unit (ICU). Results The XGBoost (eXtreme Gradient Boosting) model that was trained on clinical data from the final 24 hours excelled at predicting mortality (area under the curve [AUC]=0.92; specificity=86%; and sensitivity=85%). Respiration rate was the most important feature, followed by SpO2 (peripheral oxygen saturation) and being aged 75 years and over. Performance of this model to predict the deceased outcome extended 5 days prior, with AUC=0.81, specificity=70%, and sensitivity=75%. When only using clinical data from the first 24 hours, AUCs of 0.79, 0.80, and 0.77 were obtained for deceased, ventilated, or ICU-admitted outcomes, respectively. Although respiration rate and SpO2 levels offered the highest feature importance, other canonical markers, including diabetic history, age, and temperature, offered minimal gain. When lab values were incorporated, prediction of mortality benefited the most from blood urea nitrogen and lactate dehydrogenase (LDH). Features that were predictive of morbidity included LDH, calcium, glucose, and C-reactive protein. Conclusions Together, this work summarizes efforts to systematically examine the importance of a wide range of features across different endpoint outcomes and at different hospitalization time points.

Identifying Immunological and Clinical Predictors of COVID-19 Severity and Sequelae by Mathematical Modeling

“…Interestingly, stochastic modeling was previously used to model the human immune response to the yellow fever vaccine ( 9 ). Since COVID-19 is linked to immune response, modeling of the SARS-CoV-2 infection have been extensively published on different aspects of the disease, including the immune system using multiple ODEs to model immune cells, antibodies and cytokines ( 10 – 13 ), and on the clinical and radiological data ( 14 – 16 ). A few models on cytokine release syndrome in other diseases were also created ( 17 – 19 ).…”

A Comparison of XGBoost, Random Forest, and Nomograph for the Prediction of Disease Severity in Patients With COVID-19 Pneumonia: Implications of Cytokine and Immune Cell Profile

“…SHAP values are a game-theoretic approach to model interpretability that provide explanations of global model structure based on combinations of local explanations for each prediction ( Vaid et al., 2021 ). XGBoost has been used to predict respiratory failure within 48 h, morbidity and mortality in patients hospitalized with COVID-19 ( Pan et al., 2020 ; Bolourani et al., 2021 ; Wang et al., 2021 ). AlJame et al.…”

A Machine Learning Model for Predicting Hospitalization in Patients with Respiratory Symptoms during the COVID-19 Pandemic

“…Importantly, machine learning algorithms may also predict the early onset of acute distress respiratory syndrome in critically ill adults with COVID-19 when oxygen saturation, respiratory rate, and blood pressure were evaluated accordingly to age and sex [ 23 ]. XGBoost models may also predict COVID-19 progression and mortality when trained with data from the last 24 h. Therefore, respiratory rate, SpO 2 , age greater than 75 years, and laboratory parameters (lactate dehydrogenase, calcium, glucose, and C-reactive protein) were important for risk-stratifying patients with COVID-19 during the first wave, from January to August 2000 [ 24 ], which represent the same period when our study was conducted.…”