Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul 4;25(1):267.
doi: 10.1186/s12880-025-01807-w.

Machine learning-based prognostic prediction for acute ischemic stroke using whole-brain and infarct multi-PLD ASL radiomics

Zhenyu Wang #  1   2 , Chaojun Jiang #  3 , Xianxian Zhang  4 , Tianchi Mu  2 , Qingqing Li  5 , Shu Wang  2 , Congsong Dong  2 , Yuan Shen  6 , Zhenyu Dai  7   8 , Fei Chen  9   10
Affiliations

Machine learning-based prognostic prediction for acute ischemic stroke using whole-brain and infarct multi-PLD ASL radiomics

Zhenyu Wang et al. BMC Med Imaging. .

Abstract

Introduction: Accurate early prognostic prediction for acute ischemic stroke (AIS) is essential for guiding personalized treatment. This study aimed to assess the predictive value of radiomics features from whole-brain and infarct cerebral blood flow (CBF) images using multiple post-labeling delay arterial spin labeling (multi-PLD ASL), and to develop a prediction model incorporating clinical risk factors.

Methods: Radiomics features were extracted from the whole-brain and infarct regions based on multi-PLD ASL CBF images of 110 AIS patients. Five machine learning algorithms were used to construct radiomics models (whole-brain, infarct, and combined), clinical models, and comprehensive models integrating radiomics and clinical data. Model performance and clinical utility were assessed using receiver operating characteristic and decision curve analyses. Model stability was evaluated via 5000 permutation tests, and differences in the area under the curve (AUC) were compared using the DeLong test. Shapley Additive exPlanation was used to interpret feature contributions.

Results: The whole-brain and infarct radiomics models showed similar predictive performance. The combined radiomics models generally outperformed the infarct-only models. Additionally, no significant differences were observed between the combined radiomics models and the clinical models across the five algorithms. The comprehensive models, which integrated both radiomics and clinical features, demonstrated superior performance compared to both the clinical and combined radiomics models. Among all models, the comprehensive model based on a support vector machine achieved the highest predictive performance (AUC = 0.904). Its predictive capability was primarily driven by the baseline National Institutes of Health Stroke Scale score, age, infarct shape features, and higher-order statistical and texture features derived from both infarct and whole-brain CBF images.

Conclusions: The whole-brain CBF radiomics features of multi-PLD ASL can replace the infarct radiomics features that need to be delineated. Combined radiomics models outperformed infarct-only models and performed similarly to clinical models, which is applicable to AIS patients with incomplete clinical data. The comprehensive model integrates multi-PLD ASL CBF radiomics and clinical data, providing a safe and accurate tool for early prognosis prediction in AIS patients.

Keywords: Acute ischemic stroke; Arterial spin labeling; Cerebral blood flow; Machine learning; Radiomics.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: This study was conducted according to the tenets of the Declaration of Helsinki. Informed consent was obtained from each patient. The study was approved by the Ethics Committee of the Yancheng Third People’s Hospital (Ethics Approval No. 2020-77). Consent for publication: Not applicable. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Study enrollment process. AIS: acute ischemic stroke; MRI: magnetic resonance imaging; mRS: modified rankin scale
Fig. 2
Fig. 2
Receiver operating characteristic curve of models in predicting prognosis of AIS. (A) infarct radiomics models. (B) whole-brain radiomics models. (C) combined radiomics models. (D) clinical models. (E) comprehensive models. LR: logistic regression; SVM: support vector machine; RF: random forest; XGBoost: extreme gradient boosting; LightGBM: light gradient boosting machine
Fig. 3
Fig. 3
Decision curve analysis of the SVM models
Fig. 4
Fig. 4
The SHAP values of the SVM comprehensive model. NIHSS: national institutes of health stroke scale
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Arnalich-Montiel A, Burgos-Santamaría A, Pazó-Sayós L, Quintana-Villamandos B. Comprehensive management of stroke: from mechanisms to therapeutic approaches. Int J Mol Sci. 2024;25(10):5252. - PMC - PubMed
    1. Pu L, Wang L, Zhang R, Zhao T, Jiang Y, Han L. Projected global trends in ischemic stroke incidence, deaths and Disability-Adjusted life years from 2020 to 2030. Stroke. 2023;54(5):1330–9. - PubMed
    1. Tu W-J, Wang L-D, Yan F, Peng B, Hua Y, Liu M, et al. China stroke surveillance report 2021. Mil Med Res. 2023;10(1):23. - PMC - PubMed
    1. Wu S, Wu B, Liu M, Chen Z, Wang W, Anderson CS, et al. Stroke in china: advances and challenges in epidemiology, prevention, and management. Lancet Neurol. 2019;18(4):394–405. - PubMed
    1. Feigin VL, Owolabi MO, Feigin VL, Abd-Allah F, Akinyemi RO, Bhattacharjee NV, et al. Pragmatic solutions to reduce the global burden of stroke: a world stroke Organization–Lancet neurology commission. Lancet Neurol. 2023;22(12):1160–206. - PMC - PubMed

LinkOut - more resources