Zhong nan da xue xue bao. Yi xue ban = Journal of Central South University. Medical sciences · 2026
[A prediction model for early neurological improvement after intravenous thrombolysis in patients with acute ischemic stroke].
Аннотация на английскомСтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
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.
Xie Dujie, Long Panyao, Hu Shuntong, Huang Juan, Yuan Yi, Zhu Anding
Аннотация
OBJECTIVES: Early neurological improvement (ENI) is an important prognostic indicator in patients with acute ischemic stroke (AIS) receiving intravenous thrombolytic therapy. This study aims to develop and validate a machine learning-based prediction model for ENI, enabling early and accurate estimation of the probability of ENI after intravenous thrombolysis in AIS patients and providing support for clinical decision-making.
METHODS: Clinical data from 305 AIS patients who underwent intravenous thrombolytic therapy were retrospectively collected and analyzed. The performance of 5 machine learning algorithms, including Logistic regression, least absolute shrinkage and selection operator (LASSO) regression, support vector machine (SVM), extreme gradient boosting (XGBoost), and random forest, was compared to identify the optimal predictive model. The best-performing algorithm was then used to select key predictors associated with ENI from candidate variables and to construct a visualized nomogram prediction model. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration curves, the Hosmer-Lemeshow goodness-of-fit test, and decision curve analysis (DCA) to assess predictive accuracy and clinical utility.
RESULTS: Among the 5 algorithms, the LASSO regression model demonstrated the best overall performance, with an area under the curve (AUC) of 0.843 (95% CI 0.760 to 0.926) in the testing set. The model identified nine key predictors of ENI: sex, baseline National Institutes of Health Stroke Scale (NIHSS) score at admission, admission-to-thrombolysis time, white blood cell count, lymphocyte count, D-dimer level, body mass index (BMI), thrombus location, and onset-to-treatment time. The nomogram constructed based on these predictors showed good calibration (Hosmer-Lemeshow test, P>0.05). DCA demonstrated that the nomogram provided significant net clinical benefit across a wide range of threshold probabilities.
CONCLUSIONS: The nomogram model based on LASSO regression exhibited good predictive performance for ENI following intravenous thrombolysis in patients with AIS. It may serve as a useful tool for individualized clinical decision-making.
METHODS: Clinical data from 305 AIS patients who underwent intravenous thrombolytic therapy were retrospectively collected and analyzed. The performance of 5 machine learning algorithms, including Logistic regression, least absolute shrinkage and selection operator (LASSO) regression, support vector machine (SVM), extreme gradient boosting (XGBoost), and random forest, was compared to identify the optimal predictive model. The best-performing algorithm was then used to select key predictors associated with ENI from candidate variables and to construct a visualized nomogram prediction model. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration curves, the Hosmer-Lemeshow goodness-of-fit test, and decision curve analysis (DCA) to assess predictive accuracy and clinical utility.
RESULTS: Among the 5 algorithms, the LASSO regression model demonstrated the best overall performance, with an area under the curve (AUC) of 0.843 (95% CI 0.760 to 0.926) in the testing set. The model identified nine key predictors of ENI: sex, baseline National Institutes of Health Stroke Scale (NIHSS) score at admission, admission-to-thrombolysis time, white blood cell count, lymphocyte count, D-dimer level, body mass index (BMI), thrombus location, and onset-to-treatment time. The nomogram constructed based on these predictors showed good calibration (Hosmer-Lemeshow test, P>0.05). DCA demonstrated that the nomogram provided significant net clinical benefit across a wide range of threshold probabilities.
CONCLUSIONS: The nomogram model based on LASSO regression exhibited good predictive performance for ENI following intravenous thrombolysis in patients with AIS. It may serve as a useful tool for individualized clinical decision-making.