Multimodal machine learning for early risk stratification of post-stroke cognitive impairment.
Authors
Affiliations (7)
Affiliations (7)
- Department of Neurology, The Affiliated Lianyungang Hospital of Xuzhou Medical University, Lianyungang, China.
- Department of Neurosurgery, Institute of Neuroscience, The Affiliated Lianyungang Hospital of Xuzhou Medical University, Lianyungang, China.
- Department of Neurology, Lianyungang Clinical College of Nanjing Medical University, Lianyungang, China.
- Department of Critical Care Medicine, The First Affiliated Hospital of Kangda College of Nanjing Medical University, Lianyungang, China.
- Department of Neurosurgery, The Affiliated Lianyungang Hospital of Xuzhou Medical University, Lianyungang, China.
- Department of Neurology, The First Affiliated Hospital of Kangda College of Nanjing Medical University, Lianyungang, China.
- Department of Neurology, Lianyungang Medical Education Innovation and Research Centre of Nanjing Medical University, Lianyungang, China.
Abstract
BackgroundPost-stroke cognitive impairment (PSCI) is a major vascular contributor to dementia, significantly impacting long-term recovery and quality of life. Developing accurate prediction models are essential for early identification and timely intervention in high-risk individuals.ObjectiveTo develop and validate a stacking-based multimodal machine learning model integrating clinical, demographic, and neuroimaging features for early PSCI prediction in acute ischemic stroke (AIS) patients.MethodsIn this retrospective cohort study, 1070 AIS patients admitted to Lianyungang First People's Hospital from January 2020 to August 2023 were included. Demographic, clinical, and neuroimaging data were collected, and cognitive function was assessed 3-6 months post-stroke. PSCI was defined as a z-score ≤ -2.0 in at least one of four cognitive domains. A stacking ensemble model was developed, combining six base algorithms: XGBoost, Gradient Boosting Decision Trees, CatBoost, Support Vector Machine, Logistic Regression, and LightGBM. The final prediction was generated by a meta-model trained on base model outputs.ResultsOf the 1070 patients (mean age 67.4 ± 9.3 years, 61.5% male), 37.2% developed PSCI. The stacking model achieved 98.13% accuracy, 0.9972 AUC, and 0.9744 F1-score in internal validation. External validation showed 81.00% accuracy, 0.9049 AUC, and 0.8780 recall. Key predictors of PSCI included infarct volume, cortical lesions, medial temporal lobe atrophy, and baseline NIHSS score.ConclusionsThis stacking-based multimodal machine learning model demonstrates robust predictive performance for PSCI risk in AIS patients, serving as a reliable tool for early detection that may inform personalized intervention strategies to prevent progression to post-stroke dementia.