Predicting Hospital Utilization and Inpatient Mortality of Patients Tested for COVID-19

Abstract

Using structured elements from Electronic Health Records (EHR), we seek to: i) build predictive models to stratify patients tested for COVID-19 by their likelihood for hospitalization, ICU admission, mechanical ventilation and inpatient mortality, and ii) identify the most important EHR-based features driving the predictions. We leveraged EHR data from the Duke University Health System tested for COVID-19 or hospitalized between March 11, 2020 and August 24, 2020, to build models to predict hospital admissions within 4 weeks. Models were also created for ICU admissions, need for mechanical ventilation and mortality following admission. Models were developed on a cohort of 86,355 patients with 112,392 outpatient COVID-19 tests or any-cause hospital admissions between March 11, 2020 and June 4, 2020. The four models considered resulted in AUROC=0.838 (CI: 0.832-0.844) and AP=0.272 (CI: 0.260-0.287) for hospital admissions, AUROC=0.847 (CI: 0.839-855) and AP=0.585 (CI: 0.565-0.603) for ICU admissions, AUROC=0.858 (CI: 0.846-0.871) and AP=0.434 (CI: 0.403-0.467) for mechanical ventilation, and AUROC=0.0.856 (CI: 0.842-0.872) and AP=0.243 (CI: 0.205-0.282) for inpatient mortality. Patient history abstracted from the EHR has the potential for being used to stratify patients tested for COVID-19 in terms of utilization and mortality. The dominant EHR features for hospital admissions and inpatient outcomes are different. For the former, age, social indicators and previous utilization are the most important predictive features. For the latter, age and physiological summaries (pulse and blood pressure) are the main drivers.

The impact of super-spreader cities, highways, and intensive care availability in the early stages of the COVID-19 epidemic in Brazil

“…For instance, Mu 17 discussed how constraints on inter-city travel (reaching a 70% reduction in people flow) in China slowed the spread of COVID-19 cases throughout the country. Furthermore, as we did in the present work, Davis et al 16 employed a complex network model based on human mobility to inspect the domestic seeding of COVID-19 cases within the USA. Their analysis revealed that, even though international travel was a key driver to the initial disease spread in certain metropolitan areas, many states were infected by domestic travel flows.…”

Natural products provide a new perspective for anti-complement treatment of severe COVID-19: a review

“…Severe COVID-19 patients have higher serum complement protein C5a level than mild patients and healthy people. The CoVs’ nuclear proteins bind to mannan-binding lectin serine protease 2 (MASP-2), a key protein of the LP activation, resulting and aggravating inflammatory lung injury [ 79 , 80 ]. In addition, C5b-9, C4d and MASP-2 deposits were found in the microvasculature of lung and skin biopsy in severe COVID-19 patients, consistent with activation of the AP and LP of complement [ 81 ].…”

“…Indeed, elevated plasma C5a levels in COVID-19 patients are consistent with the clear role of C5a in promoting lung sequestration of leukocytes and pulmonary dysfunction, that reflects the severity of the disease. It also indicates that sC5b-9 has similar effects, which can cause leukocyte migration across the epithelium and vascular leakage [ 80 , 106 ].…”

Deep Forest Model for Diagnosing COVID-19 From Routine Blood Tests

“…Connor et al 47 proposed models to predict hospitalization within 4 weeks of an outpatient COVID-19 test, ICU admission, mechanical ventilation and inpatient mortality by leveraging EHR data from the Duke University Health. For each type of models, three classifiers were considered including logistic regression, XGBoost and LGBM.…”