Prediction of Early Hospital Admission (≤24 Hours) After Stroke Using Machine Learning and Deep Learning: Multicenter Study From China.

Authors

Qingjia Zeng, Jiachen Cui, Xinyu Fan, Dawei Li, Xiao Yang, Menghan Song, Shuangyang Niu, Yuhuan Wang, Yufeng Wang, Fubiao Huang, Yonghui Wang, Qiang Wu, Hongpu Hu

Published in

JMIR medical informatics. Volume 14. Pages e90852. Jun 24, 2026. Epub Jun 24, 2026.

Abstract

Timely hospital admission is a prerequisite for effective acute stroke management, yet a substantial proportion of patients fail to reach medical facilities within the optimal therapeutic window. Existing prediction models often lack temporal robustness and clinical interpretability, limiting their utility in real-world, evolving health care systems.
This study aimed to develop and temporally validate machine learning and deep learning models using multicenter clinical data to predict early hospital admission (≤24 h) after acute stroke.
In this multicenter retrospective study, we analyzed routinely collected electronic medical record data from 1327 patients across 6 hospitals in China. We developed and compared 6 predictive models: logistic regression, support vector machine, random forest, multilayer perceptron (MLP), convolutional neural network, and long short-term memory, for early admission (≤24 h from symptom onset). Model training was performed on a train set (2019-2022), followed by independent temporal validation on a testing set (2023-2025). Model prediction performance was evaluated using discrimination metrics, sensitivity, and robustness under temporal distribution shift. Model interpretability was assessed using Shapley additive explanations.
A total of 1327 patients were included, of whom 821 were assigned to the train set and 506 to the independent temporal testing set. Among the 6 candidate models, the MLP showed the best overall performance in the independent temporal testing set, achieving an area under the receiver operating characteristic curve of 0.9020 (95% CI 0.8718-0.9283), sensitivity of 91.5%, specificity of 75.6%, and F₁-score of 0.9033. Formal statistical comparisons showed that the MLP achieved significantly higher area under the receiver operating characteristic curve values than logistic regression, support vector machine, random forest, and one-dimensional convolutional neural network after false discovery rate correction, with a smaller but still statistically significant improvement over the long short-term memory. Calibration analysis further showed that the MLP had the most favorable overall calibration profile among the candidate models.
In this multicenter Chinese cohort, the MLP showed favorable temporal performance for predicting early hospital admission after stroke. The model may support future risk stratification and targeted public health interventions, although further external validation and calibration refinement are needed before deployment-oriented use.

PMID:
42342246
Bibliographic data and abstract were imported from PubMed on 25 Jun 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.