Dataset Information

Development and validation of a risk factor-based system to predict short-term survival in adult hospitalized patients with COVID-19: a multicenter, retrospective, cohort study.

ABSTRACT:

Background

Coronavirus disease 2019 (COVID-19) has become a public health emergency of global concern. We aimed to explore the risk factors of 14-day and 28-day mortality and develop a model for predicting 14-day and 28-day survival probability among adult hospitalized patients with COVID-19.

Methods

In this multicenter, retrospective, cohort study, we examined 828 hospitalized patients with confirmed COVID-19 hospitalized in Wuhan Union Hospital and Central Hospital of Wuhan between January 12 and February 9, 2020. Among the 828 patients, 516 and 186 consecutive patients admitted in Wuhan Union Hospital were enrolled in the training cohort and the validation cohort, respectively. A total of 126 patients hospitalized in Central Hospital of Wuhan were enrolled in a second external validation cohort. Demographic, clinical, radiographic, and laboratory measures; treatment; proximate causes of death; and 14-day and 28-day mortality are described. Patients' data were collected by reviewing the medical records, and their 14-day and 28-day outcomes were followed up.

Results

Of the 828 patients, 146 deaths were recorded until May 18, 2020. In the training set, multivariate Cox regression indicated that older age, lactate dehydrogenase level over 360 U/L, neutrophil-to-lymphocyte ratio higher than 8.0, and direct bilirubin higher than 5.0 μmol/L were independent predictors of 28-day mortality. Nomogram scoring systems for predicting the 14-day and 28-day survival probability of patients with COVID-19 were developed and exhibited strong discrimination and calibration power in the two external validation cohorts (C-index, 0.878 and 0.839).

Conclusion

Older age, high lactate dehydrogenase level, evaluated neutrophil-to-lymphocyte ratio, and high direct bilirubin level were independent predictors of 28-day mortality in adult hospitalized patients with confirmed COVID-19. The nomogram system based on the four factors revealed good discrimination and calibration, suggesting good clinical utility.

SUBMITTER: Zhang S

PROVIDER: S-EPMC7364297 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundThe current COVID-19 pandemic is unprecedented; under resource-constrained settings, predictive algorithms can help to stratify disease severity, alerting physicians of high-risk patients; however, there are only few risk scores derived from a substantially large electronic health record (EHR) data set, using simplified predictors as input.ObjectiveThe objectives of this study were to develop and validate simplified machine learning algorithms that predict COVID-19 adverse outcomes; to evaluate the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and calibration of the algorithms; and to derive clinically meaningful thresholds.MethodsWe performed machine learning model development and validation via a cohort study using multicenter, patient-level, longitudinal EHRs from the Optum COVID-19 database that provides anonymized, longitudinal EHR from across the United States. The models were developed based on clinical characteristics to predict 28-day in-hospital mortality, intensive care unit (ICU) admission, respiratory failure, and mechanical ventilator usages at inpatient setting. Data from patients who were admitted from February 1, 2020, to September 7, 2020, were randomly sampled into development, validation, and test data sets; data collected from September 7, 2020, to November 15, 2020, were reserved as the postdevelopment prospective test data set.ResultsOf the 3.7 million patients in the analysis, 585,867 patients were diagnosed or tested positive for SARS-CoV-2, and 50,703 adult patients were hospitalized with COVID-19 between February 1 and November 15, 2020. Among the study cohort (n=50,703), there were 6204 deaths, 9564 ICU admissions, 6478 mechanically ventilated or EMCO patients, and 25,169 patients developed acute respiratory distress syndrome or respiratory failure within 28 days since hospital admission. The algorithms demonstrated high accuracy (AUC 0.89, 95% CI 0.89-0.89 on the test data set [n=10,752]), consistent prediction through the second wave of the pandemic from September to November (AUC 0.85, 95% CI 0.85-0.86) on the postdevelopment prospective test data set [n=14,863], great clinical relevance, and utility. Besides, a comprehensive set of 386 input covariates from baseline or at admission were included in the analysis; the end-to-end pipeline automates feature selection and model development. The parsimonious model with only 10 input predictors produced comparably accurate predictions; these 10 predictors (age, blood urea nitrogen, SpO2, systolic and diastolic blood pressures, respiration rate, pulse, temperature, albumin, and major cognitive disorder excluding stroke) are commonly measured and concordant with recognized risk factors for COVID-19.ConclusionsThe systematic approach and rigorous validation demonstrate consistent model performance to predict even beyond the period of data collection, with satisfactory discriminatory power and great clinical utility. Overall, the study offers an accurate, validated, and reliable prediction model based on only 10 clinical features as a prognostic tool to stratifying patients with COVID-19 into intermediate-, high-, and very high-risk groups. This simple predictive tool is shared with a wider health care community, to enable service as an early warning system to alert physicians of possible high-risk patients, or as a resource triaging tool to optimize health care resources.

Project description:AbstractAs severe acute respiratory syndrome coronavirus 2 continues to spread, easy-to-use risk models that predict hospital mortality can assist in clinical decision making and triage. We aimed to develop a risk score model for in-hospital mortality in patients hospitalized with 2019 novel coronavirus (COVID-19) that was robust across hospitals and used clinical factors that are readily available and measured standardly across hospitals.In this retrospective observational study, we developed a risk score model using data collected by trained abstractors for patients in 20 diverse hospitals across the state of Michigan (Mi-COVID19) who were discharged between March 5, 2020 and August 14, 2020. Patients who tested positive for severe acute respiratory syndrome coronavirus 2 during hospitalization or were discharged with an ICD-10 code for COVID-19 (U07.1) were included. We employed an iterative forward selection approach to consider the inclusion of 145 potential risk factors available at hospital presentation. Model performance was externally validated with patients from 19 hospitals in the Mi-COVID19 registry not used in model development. We shared the model in an easy-to-use online application that allows the user to predict in-hospital mortality risk for a patient if they have any subset of the variables in the final model.Two thousand one hundred and ninety-three patients in the Mi-COVID19 registry met our inclusion criteria. The derivation and validation sets ultimately included 1690 and 398 patients, respectively, with mortality rates of 19.6% and 18.6%, respectively. The average age of participants in the study after exclusions was 64 years old, and the participants were 48% female, 49% Black, and 87% non-Hispanic. Our final model includes the patient's age, first recorded respiratory rate, first recorded pulse oximetry, highest creatinine level on day of presentation, and hospital's COVID-19 mortality rate. No other factors showed sufficient incremental model improvement to warrant inclusion. The area under the receiver operating characteristics curve for the derivation and validation sets were .796 (95% confidence interval, .767-.826) and .829 (95% confidence interval, .782-.876) respectively.We conclude that the risk of in-hospital mortality in COVID-19 patients can be reliably estimated using a few factors, which are standardly measured and available to physicians very early in a hospital encounter.

Project description:BackgroundPatients diagnosed with small cell lung cancer (SCLC) typically experience a poor prognosis, and it is essential to predict overall survival (OS) and stratify patients based on distinct prognostic risks.MethodsTotally 2309 SCLC patients from the hospitals in 15 cities of Shandong from 2010 - 2014 were included in this multicenter, population-based retrospective study. The data of SCLC patients during 2010-2013 and in 2014 SCLC were used for model development and validation, respectively. OS served as the primary outcome. Univariate and multivariate Cox regression were applied to identify the independent prognostic factors of SCLC, and a prognostic model was developed based on these factors. The discrimination and calibration of this model were assessed by the time-dependent C-index, time-dependent receiver operator characteristic curves (ROC), and calibration curves. Additionally, Decision Curve Analysis (DCA) curves, Net Reclassification Improvement (NRI), and Integrated Discriminant Improvement (IDI) were used to assess the enhanced clinical utility and predictive accuracy of the model compared to TNM staging systems.ResultsMultivariate analysis showed that region (Southern/Eastern, hazard ratio [HR] = 1.305 [1.046 - 1.629]; Western/Eastern, HR = 0.727 [0.617 - 0.856]; Northern/Eastern, HR = 0.927 [0.800 - 1.074]), sex (female/male, HR = 0.838 [0.737 - 0.952]), age (46-60/≤45, HR = 1.401 [1.104 - 1.778]; 61-75/≤45, HR = 1.500 [1.182 - 1.902]; >75/≤45, HR = 1.869 [1.382 - 2.523]), TNM stage (II/I, HR = 1.119[0.800 - 1.565]; III/I, HR = 1.478 [1.100 - 1.985]; IV/I, HR = 1.986 [1.477 - 2.670], surgery (yes/no, HR = 0.677 [0.521 - 0.881]), chemotherapy (yes/no, HR = 0.708 [0.616 - 0.813]), and radiotherapy (yes/no, HR = 0.802 [0.702 - 0.917]) were independent prognostic factors of SCLC patients and were included in the nomogram. The time-dependent AUCs of this model in the training set were 0.699, 0.683, and 0.683 for predicting 1-, 3-, and 5-year OS, and 0.698, 0.698, and 0.639 in the validation set, respectively. The predicted calibration curves aligned with the ideal curves, and the DCA curves, the IDI, and the NRI collectively demonstrated that the prognostic model had a superior net benefit than the TNM staging system.ConclusionThe nomogram using SCLC patients in Shandong surpassed the TNM staging system in survival prediction accuracy and enabled the stratification of patients with distinct prognostic risks based on nomogram scores.

Project description:ObjectiveTo develop and validate a scoring system to predict mortality among hospitalized patients with COVID-19.MethodsRetrospective cohort study. We analyzed 5,062 analyzed hospitalized patients with COVID-19 treated at two hospitals; one each in Quito and Guayaquil, from February to July 2020. We assessed predictors of mortality using survival analyses and Cox models. We randomly divided the database into two sets: (i) the derivation cohort (n = 2497) to identify predictors of mortality, and (ii) the validation cohort (n = 2565) to test the discriminative ability of a scoring system. After multivariate analyses, we used the final model's β-coefficients to build the score. Statistical analyses involved the development of a Cox proportional hazards regression model, assessment of goodness of fit, discrimination, and calibration.ResultsThere was a higher mortality risk for these factors: male sex [(hazard ratio (HR) = 1.32, 95% confidence interval (95% CI): 1.03-1.69], per each increase in a quartile of ages (HR = 1.44, 95% CI: 1.24-1.67) considering the younger group (17-44 years old) as the reference, presence of hypoxemia (HR = 1.40, 95% CI: 1.01-1.95), hypoglycemia and hospital hyperglycemia (HR = 1.99, 95% CI: 1.01-3.91, and HR = 1.27, 95% CI: 0.99-1.62, respectively) when compared with normoglycemia, an AST-ALT ratio >1 (HR = 1.55, 95% CI: 1.25-1.92), C-reactive protein level (CRP) of >10 mg/dL (HR = 1.49, 95% CI: 1.07-2.08), arterial pH <7.35 (HR = 1.39, 95% CI: 1.08-1.80) when compared with normal pH (7.35-7.45), and a white blood cell count >10 × 103 per μL (HR = 1.76, 95% CI: 1.35-2.29). We found a strong discriminative ability in the proposed score in the validation cohort [AUC of 0.876 (95% CI: 0.822-0.930)], moreover, a cutoff score ≥39 points demonstrates superior performance with a sensitivity of 93.10%, a specificity of 70.28%, and a correct classification rate of 72.66%. The LR+ (3.1328) and LR- (0.0981) values further support its efficacy in identifying high-risk patients.ConclusionMale sex, increasing age, hypoxemia, hypoglycemia or hospital hyperglycemia, AST-ALT ratio >1, elevated CRP, altered arterial pH, and leucocytosis were factors significantly associated with higher mortality in hospitalized patients with COVID-19. A statistically significant Cox regression model with strong discriminatory power and good calibration was developed to predict mortality in hospitalized patients with COVID-19, highlighting its potential clinical utility.

Project description:Background: Studies exploring the predictive performance of major risk factors associated with future stroke events are insufficient, and a useful tool to predict individual risk is not available. Therefore, personalized advice for preventing future stroke in patients with moyamoya disease (MMD) cannot provide evidence-based recommendations. The aim of this study was to develop a novel nomogram with reliable validity to predict the individual risk of future stroke for adult MMD patients. Methods: This study included 450 patients from seven medical centers between January 2013 and December 2018. Follow-ups were performed via clinical visits and/or telephone interviews from initial discharge to December 2019. The cohort was randomly assigned to a training set (2/3, n = 300) for nomogram development and a test set (1/3, n = 150) for external validation. The Kaplan-Meier analyses and receiver operating characteristic (ROC) curves were applied to assess the clinical benefits of this nomogram. Results: Diabetes mellitus, a family history of MMD, a past history of stroke or transient ischemic attack, clinical manifestation, and treatment were identified as major risk factors via the least absolute shrinkage and selection operator (LASSO) method. A nomogram including these predictors was established via a multivariate Cox regression model, which displayed excellent discrimination [Harrell's concordance index (C-index), 0.85; 95% confidence interval (CI): 0.75-0.96] and calibration. In the external validation, the nomogram was found to have good discrimination (C-index, 0.81; 95% CI: 0.68-0.94) and calibration. In the subgroup analysis, this predictive nomogram also showed great performance in both ischemic-type (C-index, 0.90; 95% CI: 0.77-1.00) and hemorrhagic-type MMD (C-index, 0.72; 95% CI: 0.61-0.83). Furthermore, the nomogram was shown to have potential in clinical practice through Kaplan-Meier analyses and ROC curves. Conclusions: We developed a novel nomogram incorporating several clinical characteristics with relatively good accuracy, which may have considerable potential for evaluating individual future stroke risk and providing useful management recommendations for adult patients with MMD in clinical practice.