Predicting critical state after COVID-19 diagnosis: Model development using a large US electronic health record dataset

As the COVID-19 pandemic is challenging healthcare systems worldwide, early identification of patients with a high risk of complication is crucial. We present a prognostic model predicting critical state within 28 days following COVID-19 diagnosis trained on data from US electronic health records (IBM Explorys), including demographics, comorbidities, symptoms, insurance types, and hospitalization. Out of 15816 COVID-19 patients, 2054 went into critical state or deceased. Random, stratified train-test splits were repeated 100 times and lead to a ROC AUC of 0.872 [0.868, 0.877] and a precision-recall AUC of 0.500 [0.488, 0.509] (median and interquartile range). The model was well-calibrated, showing minor tendency to overforecast probabilities above 0.5. The interpretability analysis confirmed evidence on major risk factors (e.g., older age, higher BMI, male gender, diabetes, and cardiovascular disease) in an efficient way compared to clinical studies, demonstrating the model validity. Such personalized predictions could enable fine-graded risk stratification for optimized care management.