Interpretable machine learning for predicting one-year prognosis in acute ischemic stroke.
- 1Department of Cardiovascular Medicine, Shuyang Hospital Of Traditional Chinese Medicine Medical Group, ShuYang, JiangSu Province, 223600, China.
- 2Neurology, Air Force Medical Center, Chinese People's Liberation Army, Beijing, 100142, China.
- 3Neurology, Air Force Medical Center, Chinese People's Liberation Army, Beijing, 100142, China. [email protected].
Abstract
Background
Ischemic stroke is the most prevalent type of stroke worldwide, accounting for approximately 85% of all stroke cases and resulting in the deaths of about 6.4 million people annually. Among stroke survivors, more than 60% experience varying degrees of functional impairment within three months following the stroke. Therefore, early identification and prediction of the risk of adverse outcomes after stroke are crucial. This study seeks to create an intuitive and clinically relevant machine learning model to predict the risk of adverse prognostic outcomes within one year in patients suffering from acute cerebral infarction.Methods
A retrospective cohort study was performed using medical data from 888 patients at the Air Force Specialty Medical Center of the People's Liberation Army of China to construct the model and evaluate its performance. Following screening, 771 patients were included and allocated into training and validation datasets in a 7:3 ratio. Patients were classified into poor and favorable prognostic groups based on the modified Rankin Scale (mRS) scores. The SHAP analysis method was employed to scrutinize the marginal effects of each feature on model outputs, delivering a nuanced analysis of the model's structure from a global and local perspective. Furthermore, the LIME interpretation technique was utilized for an exhaustive dissection of the model's local attributes.Results
In this study, the Recursive Feature Elimination (RFE) algorithm was employed to identify 14 key variables, including D-dimer, HDL, and PNI, for constructing 11 machine learning models. Comparative analysis revealed that the Extreme Gradient Boosting model demonstrated optimal predictive performance, with its AUC value reaching 0.766 and accuracy as high as 0.835. Utilizing SHAP analysis, the study ranked the global importance of the 14 key feature variables, including D-Dimer. Through LIME analysis, the respective weights of different feature ranges within the predictive model were uncovered.Conclusion
The interpretable machine learning predictive model developed in this study exhibited commendable accuracy in predicting adverse outcomes within one year for patients with acute cerebral infarction. In comparison to previous models, the integration of SHAP and LIME analyses significantly enhanced the model's interpretability, thereby further bolstering the clinical decision-making process.
Related
- Interpretable machine learning for predicting intraoperative oxygenation impairment during one-lung ventilation in thoracic surgery: a retrospective cohort study
- Predicting delirium in critically Ill patients with cancer using interpretable machine learning
- Development and validation of an interpretable machine learning model for predicting in-hospital mortality among critically ill patients with liver cirrhosis
- A machine learning model for predicting ischemic and bleeding risk after percutaneous coronary intervention: Development and external validation
- Interpretable machine learning analysis of immune-inflammatory biomarkers for predicting no-reflow in patients with acute myocardial infarction after percutaneous coronary intervention.
BibTeX
@article{zhu2026interpretable,
title = {{Interpretable machine learning for predicting one-year prognosis in acute ischemic stroke.}},
author = {Xing-Yu Zhu and Tian-Tian Jiang and Yan-Wei Yin},
journal = {BMC neurology},
year = {2026},
month = jul,
doi = {10.1186/s12883-026-05086-y},
url = {https://europepmc.org/article/MED/42907750},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Interpretable machine learning for predicting one-year prognosis in acute ischemic stroke.
AU - Xing-Yu Zhu
AU - Tian-Tian Jiang
AU - Yan-Wei Yin
PY - 2026
DA - 2026/07/01
JO - BMC neurology
DO - 10.1186/s12883-026-05086-y
UR - https://europepmc.org/article/MED/42907750
AB - Background Ischemic stroke is the most prevalent type of stroke worldwide, accounting for approximately 85% of all stroke cases and resulting in the deaths of about 6.4 million people annually. Among stroke survivors, more than 60% experience varying degrees of functional impairment within three months following the stroke. Therefore, early identification and prediction of the risk of adverse outcomes after stroke are crucial. This study seeks to create an intuitive and clinically relevant machine learning model to predict the risk of adverse prognostic outcomes within one year in patients suffering from acute cerebral infarction.Methods A retrospective cohort study was performed using medical data from 888 patients at the Air Force Specialty Medical Center of the People's Liberation Army of China to construct the model and evaluate its performance. Following screening, 771 patients were included and allocated into training and validation datasets in a 7:3 ratio. Patients were classified into poor and favorable prognostic groups based on the modified Rankin Scale (mRS) scores. The SHAP analysis method was employed to scrutinize the marginal effects of each feature on model outputs, delivering a nuanced analysis of the model's structure from a global and local perspective. Furthermore, the LIME interpretation technique was utilized for an exhaustive dissection of the model's local attributes.Results In this study, the Recursive Feature Elimination (RFE) algorithm was employed to identify 14 key variables, including D-dimer, HDL, and PNI, for constructing 11 machine learning models. Comparative analysis revealed that the Extreme Gradient Boosting model demonstrated optimal predictive performance, with its AUC value reaching 0.766 and accuracy as high as 0.835. Utilizing SHAP analysis, the study ranked the global importance of the 14 key feature variables, including D-Dimer. Through LIME analysis, the respective weights of different feature ranges within the predictive model were uncovered.Conclusion The interpretable machine learning predictive model developed in this study exhibited commendable accuracy in predicting adverse outcomes within one year for patients with acute cerebral infarction. In comparison to previous models, the integration of SHAP and LIME analyses significantly enhanced the model's interpretability, thereby further bolstering the clinical decision-making process.
SN - 1471-2377
ER -