Deep learning models based on DWI-MRI for prognosis prediction in acute ischemic stroke receiving intravenous thrombolysis: Development and validation - 29/10/25
Highlights |
• | Developed predictive models for AIS prognosis based on DWI-MRI and clinical data. |
• | Deep learning models outperformed traditional machine learning models. |
• | Combined deep learning and clinical features achieved the highest predictive accuracy. |
• | Findings support the clinical potential of deep learning models in stroke management. |
Abstract |
Objective |
To develop and validate predictive models based on diffusion-weighted imaging MRI (DWI-MRI) for assessing the prognosis of patients with acute ischemic stroke (AIS) treated with intravenous thrombolysis, and to compare the performance of deep learning versus traditional machine learning methods.
Materials and methods |
A retrospective analysis was conducted on 682 AIS patients from two hospitals. Data from Hospital 1 were divided into a training set (70 %) and a test set (30 %), while data from Hospital 2 were used for external validation. Five predictive models were developed: Model A (clinical features), Model B (radiomic features based on DWI-MRI), Model C (deep learning features), Model D (clinical + radiomic features), and Model E (clinical + deep learning features). Performance metrics included Area Under the Curve (AUC), sensitivity, specificity, and accuracy.
Results |
In the test set, Models A, B, and C achieved AUCs of 0.760, 0.820, and 0.857, respectively. The combined models, D and E, showed superior performance with AUCs of 0.904 and 0.925, respectively. Model E outperformed Model D and also demonstrated robust performance in external validation (AUC = 0.937).
Conclusion |
Deep learning models integrating DWI-MRI and clinical features outperformed traditional methods, demonstrating strong generalizability in external validation. These models may support clinical decision-making in AIS prognosis.
Le texte complet de cet article est disponible en PDF.Keyword : Acute Ischemic Stroke, DWI-MRI, Intravenous Thrombolysis, Machine Learning, Deep Learning
Plan
Vol 52 - N° 6
Article 101391- novembre 2025 Retour au numéro
Article précédent
- Diagnostic value of centrally restricted diffusion in differentiating radiation necrosis from tumor progression in brain metastases: A single-center observational study
- Valentin Laigle, Laure Thomas, Thiebaud Picart, Emanuele Tommasino, Chloé Dumot, Anne d’Hombres, Loïc Feuvret, Emilien Jupin-Delevaux, Delphine Gamondès, Marc Hermier, François Cotton, Jérôme Honnorat, François Ducray, Yves Berthezène, Alexandre Bani-Sadr
- Increased 18F-FAPI-04 uptake in neurofibromatosis type 1 in a patient with synchronous bilateral breast cancer
- Yuting Wu, Chunxiu Yuan, Dongju Li, Xiaowei Ma, Jiqin Yang
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?