BACKGROUND
Mild to moderate ischaemic stroke accounts for one-half to two-thirds of all ischaemic stroke hospitalisations worldwide, yet prognostic models to assess functional outcome after stroke remain elusive.
OBJECTIVE
This study aimed to identify the risk factors and develop a prognostic assessment model for short-term functional outcome in patients with acute mild-to-moderate ischaemic stroke using the Bayesian Network (BN) approach.
METHODS
Patients participating in a multicentre randomised controlled trial were eligible for inclusion in this study. The least absolute shrinkage and selection operator (LASSO) regression was applied to reduce the dimensionality of the data, and synthetic minority oversampling technology (SMOTE) was used to correct data imbalances. The Bayesian network model was trained using a hill-climbing algorithm to determine the optimal network structure. The area under the receiver operating characteristic curve (AUROC) and the calibration plot were used to assess model performance.
RESULTS
A total of 2,432 patients were included for analysis, 424（17.43%）patients had unfavorable outcome in 3-month after AIS,. The BN model identified the NIH Stroke Scale (NIHSS) score, age, C-reactive protein (CRP) levels, fasting plasma glucose (FPG), and history of stroke as significant prognostic factors. The BN model outperformed the logistic regression model in accuracy, sensitivity, and F1 score in test sets, with significant differences in the AUROC as per the DeLong test (P < 0.05). The calibration plot showed good agreement between predictions and observations in both the training and test sets.
CONCLUSIONS
The NIHSS score, age, CRP levels, FPG, and history of stroke are significant predictors of functional outcome in AIS patients. The BN model demonstrates superior predictive performance compared to traditional logistic regression, suggesting its potential as a valuable tool for assessing short-term prognosis in mild-moderate ischaemic stroke patients.
CLINICALTRIAL
The trial is registered in the Chinese Clinical Trial Registry (http://www. chictr.org.cn/, ChiCTR1900026492) on 12 October 2019.