Machine learning-based models to predict 90-day non-excellent functional outcomes among patients with mild acute ischemic stroke after intravenous thrombolysis
- 1Tianjin Medical University
- 2Tianjin University
- 3Tianjin Fourth Central Hospital Affiliated to Tianjin Medical University
Abstract
Background: Despite intravenous thrombolysis, a substantial proportion of patients with mild acute ischemic stroke fail to achieve an excellent functional outcome. Prediction models specifically developed for these patients remain limited. We aimed to construct and evaluate a machine learning model for identifying 90-day non-excellent functional outcomes.
Methods: We retrospectively collected data from patients with mild acute ischemic stroke treated with intravenous thrombolysis at Tianjin Fourth Central Hospital between January 2024 and June 2025. Demographic, clinical, laboratory, and neuroimaging variables were extracted from electronic medical records. LASSO regression was applied for feature selection, followed by the development of seven machine learning models. Model performance was assessed using discrimination, calibration, clinical utility, and classification metrics. We conducted SHAP analysis to elucidate the relative importance and direction of association of individual predictors with model predictions.
Results: A total of 507 patients with mild acute ischemic stroke undergoing intravenous thrombolysis were included, of whom 136 (26.8%) experienced a non-excellent functional outcome at 90 days. LASSO regression identified six predictors, including age, baseline National Institutes of Health Stroke Scale score, platelet count, monocyte count, blood glucose level, and neutrophil-to-lymphocyte ratio. In the validation cohort, XGBoost achieved the highest numerical AUC of 0.753 (95% CI, 0.660–0.840) and demonstrated adequate calibration and clinical usefulness.
Conclusion: A machine learning model was developed and internally validated to predict 90-day non-excellent functional outcomes in patients with mild acute ischemic stroke after intravenous thrombolysis. The XGBoost model showed promising predictive performance and potential utility for early risk stratification.
Related
- Association of the remnant cholesterol inflammation index with long-term outcomes among patients with acute ischemic stroke treated with intravenous thrombolysis
- Real-world implementation and outcomes of extended-window intravenous thrombolysis in Catalonia, 2016-2024: A population-based study using the CICAT registry.
- Arthroscopic Anterior Cruciate Ligament Repair With Suture Augmentation Provides Good to Excellent Midterm Functional Outcomes Despite Clinically Relevant Revision Rates.
- Extending the Treatment Window for Intravenous Thrombolysis in Acute Ischemic Stroke
- Success rate and determinants of intravenous thrombolysis in acute ischemic stroke from the Malaysia National Stroke Registry
BibTeX
@article{wang2026machine,
title = {{Machine learning-based models to predict 90-day non-excellent functional outcomes among patients with mild acute ischemic stroke after intravenous thrombolysis}},
author = {Yichen Wang and Xinyu Qiu and Yi Wang and Lijun Wang},
journal = {Frontiers in Neurology},
year = {2026},
month = oct,
doi = {10.3389/fneur.2026.1960403},
url = {https://www.frontiersin.org/articles/10.3389/fneur.2026.1960403/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Machine learning-based models to predict 90-day non-excellent functional outcomes among patients with mild acute ischemic stroke after intravenous thrombolysis
AU - Yichen Wang
AU - Xinyu Qiu
AU - Yi Wang
AU - Lijun Wang
PY - 2026
DA - 2026/10/19
JO - Frontiers in Neurology
DO - 10.3389/fneur.2026.1960403
UR - https://www.frontiersin.org/articles/10.3389/fneur.2026.1960403/full
AB - Background: Despite intravenous thrombolysis, a substantial proportion of patients with mild acute ischemic stroke fail to achieve an excellent functional outcome. Prediction models specifically developed for these patients remain limited. We aimed to construct and evaluate a machine learning model for identifying 90-day non-excellent functional outcomes. Methods: We retrospectively collected data from patients with mild acute ischemic stroke treated with intravenous thrombolysis at Tianjin Fourth Central Hospital between January 2024 and June 2025. Demographic, clinical, laboratory, and neuroimaging variables were extracted from electronic medical records. LASSO regression was applied for feature selection, followed by the development of seven machine learning models. Model performance was assessed using discrimination, calibration, clinical utility, and classification metrics. We conducted SHAP analysis to elucidate the relative importance and direction of association of individual predictors with model predictions. Results: A total of 507 patients with mild acute ischemic stroke undergoing intravenous thrombolysis were included, of whom 136 (26.8%) experienced a non-excellent functional outcome at 90 days. LASSO regression identified six predictors, including age, baseline National Institutes of Health Stroke Scale score, platelet count, monocyte count, blood glucose level, and neutrophil-to-lymphocyte ratio. In the validation cohort, XGBoost achieved the highest numerical AUC of 0.753 (95% CI, 0.660–0.840) and demonstrated adequate calibration and clinical usefulness. Conclusion: A machine learning model was developed and internally validated to predict 90-day non-excellent functional outcomes in patients with mild acute ischemic stroke after intravenous thrombolysis. The XGBoost model showed promising predictive performance and potential utility for early risk stratification.
SN - 1664-2295
ER -