A Nomogram for Predicting Venous Thromboembolism in Critically Ill Patients with Primary Intracerebral Hemorrhage

■ OBJECTIVE: To develop and validate a nomogram for predicting the risk of venous thromboembolism in critically ill patients with primary intracerebral hemorrhage. ■ METHODS: Patients double dagger 18 years old with primary intra-cerebral hemorrhage were screened within 24 hours of onset from January 2019 to April 2021. Univariate and multivariate logistic regression analyses were performed to screen out independent predictors that were signifi-cantly associated with venous thromboembolism. A nomogram was constructed based on the results of a multivariate regression analysis. Discrimination and cali-bration were used to evaluate performance of the nomo-gram. A decision curve analysis was used to assess its clinical utility. ■ RESULTS: This study enrolled 369 patients. The nomo-gram included 3 predictors from the regression analysis: D-dimer, National Institutes of Health Stroke Scale score, and Glasgow Coma Scale score on admission. The area under the receiver operating characteristic curve was 0.794, indicating good discrimination of the nomogram. The nomogram demonstrated calibration curves with slight deviation from the ideal predictions. Decision curve anal-ysis showed that the prediction nomogram was clinically useful. ■ CONCLUSIONS: This nomogram comprising D-dimer, National Institutes of Health Stroke Scale score and Glasgow Coma Scale score on admission can accurately predict the risk of venous thromboembolism in critically ill patients with intracerebral hemorrhage.

Automated summary

This study developed and validated a nomogram to predict the risk of venous thromboembolism in critically ill patients with primary intracerebral hemorrhage. The nomogram showed good discrimination and calibration, making it clinically useful in predicting the risk of venous thromboembolism.