Development of an Early Warning Model for Predicting the Death Risk of Coronavirus Disease 2019 Based on Data Immediately Available on Admission

Abstract

Introduction: COVID-19 has overloaded worldwide medical facilities, leaving some potentially high-risk patients trapped in outpatient clinics without sufficient treatment. However, there is still a lack of a simple and effective tool to identify these patients early.Methods: A retrospective cohort study was conducted to develop an early warning model for predicting the death risk of COVID-19. Seventy-five percent of the cases were used to construct the prediction model, and the remaining 25% were used to verify the prediction model based on data immediately available on admission.Results: From March 1, 2020, to April 16, 2020, a total of 4,711 COVID-19 patients were included in our study. The average age was 63.37 ± 16.70 years, of which 1,148 (24.37%) died. Finally, age, SpO2, body temperature (T), and mean arterial pressure (MAP) were selected for constructing the model by univariate analysis, multivariate analysis, and a review of the literature. We used five common methods for constructing the model and finally found that the full model had the best specificity and higher accuracy. The area under the ROC curve (AUC), specificity, sensitivity, and accuracy of full model in train cohort were, respectively, 0.798 (0.779, 0.816), 0.804, 0.656, and 0.768, and in the validation cohort were, respectively, 0.783 (0.751, 0.815), 0.800, 0.616, and 0.755. Visualization tools of the prediction model included a nomogram and an online dynamic nomogram (https://wanghai.shinyapps.io/dynnomapp/).Conclusion: We developed a prediction model that might aid in the early identification of COVID-19 patients with a high probability of mortality on admission. However, further research is required to determine whether this tool can be applied for outpatient or home-based COVID-19 patients.

Predicting In-Hospital Mortality in Severe COVID-19: A Systematic Review and External Validation of Clinical Prediction Rules

“…Fifty-five studies aimed to exclusively predict in-hospital mortality [ 2 , 11 , 14 , 15 , 16 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 29 , 30 , 31 , 32 , 34 , 35 , 36 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 47 , 50 , 51 , 52 , 54 , 56 , 57 , 58 , 59 , 60 , 61 , 62 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 , 72 , 73 , 74 , 75 , 76 , 77 , 79 ], while thirteen reported on combined outcome...…”

“…Thirty-four nomograms were derived and validated (in different patients from the same institution) in the same study; random training test splits [ 14 , 17 , 18 , 19 , 23 , 24 , 30 , 32 , 33 , 41 , 45 , 50 , 51 , 55 , 59 , 60 , 61 , 62 , 63 , 65 , 66 , 67 , 71 , 75 , 76 , 77 ] and temporal splits [ 15 , 43 , 44 , 46 , 53 , 70 ] were performed in fourteen and five studies, respectively. One study performed validation by leave-one-hospital-out cross validation [ 72 ].…”

“…Overall, 67 models identified predictors for risk of COVID-19-related mortality in patients admitted to hospitals, and a further 3 also included information from the general population and/or out-patients [ 19 , 23 , 49 , 71 , 77 ]. The vast majority of these studies used multivariable logistic regression models to identify predictors [ 2 , 12 , 13 , 14 , 16 , 17 , 18 , 20 , 21 , 22 , 24 , 25 , 26 , 27 , 30 , 31 , 32 , 33 , 34 , 35 , 37 , 38 , 39 , 41 , 43 , 45 , 46 , 47 , 48 , 49 , 51 , 52 , 53 , 54 , 56 , 57 , 58 , 59 , 62 , 63 , 64 , 65 , 66 ,…”

Predictors of Mortality in Hospitalized COVID-19 Patients Complicated With Hypotension and Hypoxemia: A Retrospective Cohort Study

“…The four variables were used to construct the prognosis prediction model for these patients, and we discovered that it had a high predictive value, the AUC was higher than 0.9, and high sensitivity and specificity. Numerous studies had shown that age was an independent risk factor for a poor outcome with COVID-19 (14)(15)(16)(17). The following are possible explanations: chronic illnesses such as hypertension, diabetes, and coronary heart disease become increasingly prevalent as people become older (18); the elderly's baseline level of proinflammatory cytokines in tissues and circulation increases with age, and the body's immune response to pathogenic threats or tissue damage is also delayed (19); the angiotensin-converting enzyme 2 (ACE-2) receptor is required for the COVID-19 virus to enter cells (20).…”

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

“…In the early phase of the COVID-19 pandemic, meta-analysis studies documented that dyspnea, anorexia, dizziness, and fatigue were significantly associated with the critical outcome [ 3 ]. Likewise, oxyhemoglobin saturation by pulse oximetry (SpO 2 ), body temperature, and mean arterial pressure on admission can also predict COVID-19 patients with a high probability of mortality [ 4 ]. The COVID-19 timeline was described as the median duration from illness onset to dyspnea of 8.0 days (interquartile range, 5.0–13), whereas from onset of symptoms to first hospital admission was 7.0 days (4.0–8.0) [ 5 , 6 ].…”