Machine learning–based predictive model for post-stroke dementia

• Published in: BMC medical informatics and decision making Vol. 24; no. 1; pp. 334 - 9
• Main Authors: Wei, Zemin, Li, Mengqi, Zhang, Chenghui, Miao, Jinli, Wang, Wenmin, Fan, Hong
• Format: Journal Article
• Language: English
• Published: London BioMed Central 11.11.2024; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Accuracy; Aged; Aged, 80 and over; Algorithms; Body mass index; Boruta algorithm; C-reactive protein; Cognitive ability; Comorbidity; Complications and side effects; Correlation analysis; Decision trees; Dementia; Dementia disorders; Demographic aspects; Diagnosis; Feature selection; Female; Health aspects; Health Informatics; Hemorrhage; Humans; Hypertension; Information Systems and Communication Service; Learning algorithms; Machine Learning; Male; Management of Computing and Information Systems; Medical colleges; Medical research; Medicine; Medicine & Public Health; Medicine, Experimental; Middle Aged; Mortality; Multilayer perceptrons; Post-stroke dementia; Prediction model; Prediction models; Prognosis; Qualitative analysis; Regression analysis; Risk factors; Statistical analysis; Stroke; Stroke (Disease); Stroke - complications; Stroke patients; Support vector machines; China; Stroke; Boruta algorithm; Post-stroke dementia; Machine learning; Prediction model
• ISSN: 1472-6947; 1472-6947
• DOI: 10.1186/s12911-024-02752-4

Background Post-stroke dementia (PSD), a common complication, diminishes rehabilitation efficacy and affects disease prognosis in stroke patients. Many factors may be related to PSD, including demographic, comorbidities, and examination characteristics. However, most existing methods are qualitative evaluations of independent factors, which ignore the interaction amongst various factors. Therefore, the purpose of this study is to explore the applicability of machine learning (ML) methods for predicting PSD. Methods 9 acceptable features were screened out by the Spearman correlation analysis and Boruta algorithm. We developed and evaluated 8 ML models: logistic regression, elastic net, k-nearest neighbors, decision tree, extreme gradient boosting, support vector machine, random forest, and multilayer perceptron. Results A total of 539 stroke patients were included in this study. Among the 8 models used to predict PSD, extreme gradient boosting and random forest showed the highest area under the curve (AUC) of the receiver operating characteristic curve (ROC), with values of 0.7287 and 0.7285, respectively. The most important features for predicting PSD included age, high sensitivity C-reactive protein, stroke side and location, and the occurrence of cerebral hemorrhage. Conclusion Our findings suggest that ML models, especially extreme gradient boosting, can best predict the risk of PSD.