DOI 10.3389/fneur.2026.1754883
Risk factors for lower limb deep vein thrombosis in patients with intracerebral hemorrhage: a retrospective study using LASSO regression to develop a nomogram.
Аннотация
OBJECTIVE
To explore the influencing factors of clinically suspected lower limb deep vein thrombosis (DVT) in patients with cerebral hemorrhage and establish a nomogram clinical prediction model based on Lasso regression.
METHODS
A total of 297 patients with cerebral hemorrhage treated in our hospital from January 2023 to July 2025 were retrospectively included. They were randomly divided into the training group (n = 208) and the validation group (n = 89) in a ratio of 7:3. The training group was separated into the non DVT group (n = 156) and the DVT group (n = 52) based on the occurrence of lower limb DVT during hospitalization. Lasso regression analysis and multivariate logistic regression analysis were applied to screen the influencing factors of clinically suspected lower extremity DVT in patients with intracerebral hemorrhage. The nomogram was created based on the results of regression analysis. Calibration curves, receiver operating characteristic (ROC) curves, and clinical decision curve analysis (DCA) curves were plotted to evaluate the calibration, discrimination, and clinical utility of the nomogram model.
RESULTS
There was no statistical difference in baseline data between the training group and the validation group (p > 0.05). The results of Lasso and logistic regression analyses showed that Age (OR: 1.206), albumin (OR: 0.747), D-dimer (OR: 1.992), and the TyG index (OR: 2.061) were influencing factors of clinically suspected lower limb DVT in patients with cerebral hemorrhage (p < 0.05). The calibration curves of the training group and the validation group showed that the Hosmer-Lemeshow χ2 statistic was 6.482 and 7.935, respectively, with p = 0.627 and 0.492 > 0.05, indicating that the model had good calibration. ROC curve showed that the AUC was 0.891 (95%CI: 0.845 ~ 0.937) and 0.848 (95%CI: 0.791 ~ 0.905), and the model had good discrimination. In addition, DCA curve showed that the model provided favorable net clinical benefits within the high-risk thresholds of 0.07-0.89 and 0.09-0.69.
CONCLUSION
The nomogram prediction model constructed based on the influencing factors of this study has a certain predictive performance and can assist clinicians in assessing the risk of occurrence of clinically suspected lower limb DVT in patients with cerebral hemorrhage, but it should be considered preliminary before external validation is completed.
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.