Share：
Share this content in WeChat
X
[Chinese] [PDF] 18 1
• Review •
Advances in imaging-data-based machine learning methods for prognosis prediction of acute ischemic stroke
ZHOU Baozhen  CHEN Fei 

Cite this article as: ZHOU B Z, CHEN F. Advances in imaging-data-based machine learning methods for prognosis prediction of acute ischemic stroke[J]. Chin J Magn Reson Imaging, 2026, 17(9): 190-198. DOI:10.12015/issn.1674-8034.2026.09.025.


[Abstract] Acute ischemic stroke (AIS) is one of the most common neurological disorders with high morbidity-mortality and disability rates worldwide. Consequently, early and accurate prognostic assessment is crucial for tailoring individualized individualized diagnosis-treatment plans. Machine learning (ML) demonstrates outstanding performance in feature mining and pattern recognition. It enables the extraction of quantitative features from imaging data such as CT and MRI and the construction of predictive models, thereby overcoming the limitations of conventional prognostic assessment paradigms. To systematically map the field's current state, this paper first employs literature statistics and visual analytic approaches to delineate the global research landscape. On this basis, this review summarizes the research status of various ML models (conventional algorithms, deep learning and ensemble learning) based on non-contrast CT, CTA, CTP and multiple MRI sequences for AIS prognosis prediction. This paper also identifies the current limitations of existing research in areas such as data heterogeneity, external validation, image standardization, model interpretability, and clinical translation; it further suggests that future efforts should focus on strengthening multicenter prospective validation studies, standardizing image data processing workflows, and enhancing model interpretability and clinical relevance to facilitate the application of these approaches in the personalized prognostic assessment of AIS.
[Keywords] acute ischemic stroke；machine learning；computed tomography；magnetic resonance imaging；prognosis

ZHOU Baozhen   CHEN Fei*  

Department of Radiology, Yancheng Clinical Medical College, Nanjing Medical University (Yancheng Third People's Hospital), Yancheng 224005, China

Corresponding author: CHEN F, E-mail: shuibin1988@163.com

Conflicts of interest   None.

Received  2026-04-27
Accepted  2026-08-12
DOI: 10.12015/issn.1674-8034.2026.09.025
Cite this article as: ZHOU B Z, CHEN F. Advances in imaging-data-based machine learning methods for prognosis prediction of acute ischemic stroke[J]. Chin J Magn Reson Imaging, 2026, 17(9): 190-198. DOI:10.12015/issn.1674-8034.2026.09.025.

[1]
SHI H Y, QIAN W Y, WANG K F, et al. Research progress of MRI in blood-brain barrier injury associated with acute ischemic stroke[J]. Chin J Magn Reson Imaging, 2025, 16(8): 154-159. DOI: 10.12015/issn.1674-8034.2025.08.023.
[2]
SAINI V, GUADA L, YAVAGAL D R. Global Epidemiology of Stroke and Access to Acute Ischemic Stroke Interventions[J]. Neurology, 2021, 97(20Suppl 2): S6-S16. DOI: 10.1212/wnl.0000000000012781.
[3]
LI X Y, KONG X M, YANG C H, et al. Global, regional, and national burden of ischemic stroke, 1990-2021: an analysis of data from the global burden of disease study 2021[J/OL]. EClinicalMedicine, 2024, 75: 102758 [2026-04-27]. https://dx.doi.org/10.1016/j.eclinm.2024.102758. DOI: 10.1016/j.eclinm.2024.102758.
[4]
LI H, CHANG C, ZHOU B, et al. Radiomics machine learning based on asymmetrically prominent cortical and deep medullary veins combined with clinical features to predict prognosis in acute ischemic stroke: a retrospective study[J/OL]. PeerJ, 2025, 13: e19469 [2026-04-27]. https://dx.doi.org/10.7717/peerj.19469. DOI: 10.7717/peerj.19469.
[5]
KUMAR S, CHOU S H, SMITH C J, et al. Addressing Systemic Complications of Acute Stroke: A Scientific Statement From the American Heart Association[J/OL]. Stroke, 2025, 56(1): e15-e29 [2026-04-27]. https://dx.doi.org/10.1161/str.0000000000000477. DOI: 10.1161/str.0000000000000477.
[6]
FEIGIN V L, BRAININ M, NORRVING B, et al. World Stroke Organization (WSO): Global Stroke Fact Sheet 2022[J]. Int J Stroke, 2022, 17(1): 18-29. DOI: 10.1177/17474930211065917.
[7]
LV J, ZHAO D, ZHAO G, et al. Efficacy and safety of butylphthalide in secondary prevention of stroke: study protocol for a multicenter, real world trial based on Internet[J/OL]. BMC Neurol, 2022, 22(1): 305 [2026-04-27]. https://dx.doi.org/10.1186/s12883-022-02815-x. DOI: 10.1186/s12883-022-02815-x.
[8]
FEIGIN V L, OWOLABI M O. Pragmatic solutions to reduce the global burden of stroke: a World Stroke Organization-Lancet Neurology Commission[J]. Lancet Neurol, 2023, 22(12): 1160-1206. DOI: 10.1016/s1474-4422(23)00277-6.
[9]
TOYODA K, YOSHIMURA S, NAKAI M, et al. Twenty-Year Change in Severity and Outcome of Ischemic and Hemorrhagic Strokes[J]. JAMA Neurol, 2022, 79(1): 61-69. DOI: 10.1001/jamaneurol.2021.4346.
[10]
YANG Q, GUO C, YUE C, et al. Methylprednisolone as Adjunct to Endovascular Thrombectomy for Large-Vessel Occlusion Stroke: The MARVEL Randomized Clinical Trial[J]. JAMA, 2024, 331(10): 840-849. DOI: 10.1001/jama.2024.0626.
[11]
JI X G, ZHANG R J, LIU Z H, et al. Research progress of imaging evaluation of hemorrhagic transformation after thrombolysis in acute ischemic stroke[J]. Chin J Magn Reson Imaging, 2025, 16(10): 130-136. DOI: 10.12015/issn.1674-8034.2025.10.021.
[12]
CHEN F, HAN Y, HU H, et al. Nonlinear association of fibrinogen levels with functional prognosis in patients with acute ischemic stroke: a prospective cohort study[J/OL]. BMC Neurol, 2024, 24(1): 163 [2026-04-27]. https://dx.doi.org/10.1186/s12883-024-03674-4. DOI: 10.1186/s12883-024-03674-4.
[13]
KHAN M S A, AHMAD S, GHAFOOR B, et al. Inpatient assessment of the neurological outcome of acute stroke patients based on the National Institute of Health Stroke Scale (NIHSS)[J/OL]. Ann Med Surg (Lond), 2022, 82: 104770 [2026-04-27]. https://dx.doi.org/10.1016/j.amsu.2022.104770. DOI: 10.1016/j.amsu.2022.104770.
[14]
WANG B, JIANG B, LIU D, et al. Early Predictive Accuracy of Machine Learning for Hemorrhagic Transformation in Acute Ischemic Stroke: Systematic Review and Meta-Analysis[J/OL]. J Med Internet Res, 2025, 27: e71654 [2026-04-27]. https://dx.doi.org/10.2196/71654. DOI: 10.2196/71654.
[15]
DU H J, LIU X Y, XU M H, et al. Application progress in prognostic prediction of acute ischemic stroke: taking machine learning prediction models as an example[J]. Chinese General Practice, 2025, 28(5): 554-560. DOI: 10.12114/j.issn.1007-9572.2024.0090.
[16]
LI J Y Z, LI G, SHAN Y, et al. Research progress of machine learning in magnetic resonance imaging evaluation of acute ischemic stroke[J]. Chin J Geriatr Heart Brain Vessel Dis, 2025, 27(12): 1755-1757. DOI: 10.3969/j.issn.1009-0126.2025.12.033.
[17]
ZHU J, LIU W. A tale of two databases: the use of Web of Science and Scopus in academic papers[J]. Scientometrics, 2020, 123(1): 321-335. DOI: 10.1007/s11192-020-03387-8.
[18]
BRUGNARA G, NEUBERGER U, MAHMUTOGLU M A, et al. Multimodal Predictive Modeling of Endovascular Treatment Outcome for Acute Ischemic Stroke Using Machine-Learning[J]. Stroke, 2020, 51(12): 3541-3551. DOI: 10.1161/strokeaha.120.030287.
[19]
XIE Y, JIANG B, GONG E, et al. JOURNAL CLUB: Use of Gradient Boosting Machine Learning to Predict Patient Outcome in Acute Ischemic Stroke on the Basis of Imaging, Demographic, and Clinical Information[J]. AJR Am J Roentgenol, 2019, 212(1): 44-51. DOI: 10.2214/ajr.18.20260.
[20]
BACCHI S, ZERNER T, OAKDEN-RAYNER L, et al. Deep Learning in the Prediction of Ischaemic Stroke Thrombolysis Functional Outcomes: A Pilot Study[J/OL]. Acad Radiol, 2020, 27(2): e19-e23 [2026-04-27]. https://dx.doi.org/10.1016/j.acra.2019.03.015. DOI: 10.1016/j.acra.2019.03.015.
[21]
WAGNER M W, NAMDAR K, BISWAS A, et al. Radiomics, machine learning, and artificial intelligence-what the neuroradiologist needs to know[J]. Neuroradiology, 2021, 63(12): 1957-1967. DOI: 10.1007/s00234-021-02813-9.
[22]
CHOI J Y. Radiomics and Deep Learning in Clinical Imaging: What Should We Do?[J]. Nucl Med Mol Imaging, 2018, 52(2): 89-90. DOI: 10.1007/s13139-018-0514-0.
[23]
XU E, VANGHELOF J, WANG Y, et al. Outcome risk model development for heterogeneity of treatment effect analyses: a comparison of non-parametric machine learning methods and semi-parametric statistical methods[J/OL]. BMC Med Res Methodol, 2024, 24(1): 158 [2026-04-27]. https://dx.doi.org/10.1186/s12874-024-02265-8. DOI: 10.1186/s12874-024-02265-8.
[24]
NGUYEN K, NGUYEN M, DANG K, et al. Early Alzheimer's disease diagnosis using an XG-Boost model applied to MRI images[J]. Biomed Res Ther, 2023, 10(9): 5896-5911. DOI: 10.15419/bmrat.v10i9.832.
[25]
BU F, CAI R, ZHANG W, et al. Explainable machine learning model for predicting the outcome of acute ischemic stroke after intravenous thrombolysis[J/OL]. Front Neurol, 2025, 16: 1668816 [2026-04-27]. https://dx.doi.org/10.3389/fneur.2025.1668816. DOI: 10.3389/fneur.2025.1668816.
[26]
YU H, WANG Z, SUN Y, et al. Prognosis of ischemic stroke predicted by machine learning based on multi-modal MRI radiomics[J/OL]. Front Psychiatry, 2022, 13: 1105496 [2026-04-27]. https://dx.doi.org/10.3389/fpsyt.2022.1105496. DOI: 10.3389/fpsyt.2022.1105496.
[27]
CHEN W, LEE B, ZANG Z, et al. Data subdivision approach enhances machine learning-based mortality prediction in pediatric ICU patients[J/OL]. PLoS One, 2026, 21(6): e0349772 [2026-04-27]. https://dx.doi.org/10.1371/journal.pone.0349772. DOI: 10.1371/journal.pone.0349772.
[28]
YASSIN M M, LU J, ZAMAN A, et al. Advancing ischemic stroke diagnosis and clinical outcome prediction using improved ensemble techniques in DSC-PWI radiomics[J/OL]. Sci Rep, 2024, 14(1): 27580 [2026-04-27]. https://dx.doi.org/10.1038/s41598-024-78353-y. DOI: 10.1038/s41598-024-78353-y.
[29]
FUSCO R, GRANATA V, GRAZZINI G, et al. Radiomics in medical imaging: pitfalls and challenges in clinical management[J]. Jpn J Radiol, 2022, 40(9): 919-929. DOI: 10.1007/s11604-022-01271-4.
[30]
HWANGBO L, KANG Y J, KWON H, et al. Stacking ensemble learning model to predict 6-month mortality in ischemic stroke patients[J/OL]. Sci Rep, 2022, 12(1): 17389 [2026-04-27]. https://dx.doi.org/10.1038/s41598-022-22323-9. DOI: 10.1038/s41598-022-22323-9.
[31]
YANG Y, GUO Y. Ischemic stroke outcome prediction with diversity features from whole brain tissue using deep learning network[J/OL]. Front Neurol, 2024, 15: 1394879 [2026-04-27]. https://dx.doi.org/10.3389/fneur.2024.1394879. DOI: 10.3389/fneur.2024.1394879.
[32]
LI L, LI M, CHEN Z, et al. Prognostic value of radiomics-based hyperdense middle cerebral artery sign for patients with acute ischemic stroke after thrombectomy strategy[J/OL]. Front Neurol, 2022, 13: 1037204 [2026-04-27]. https://dx.doi.org/10.3389/fneur.2022.1037204. DOI: 10.3389/fneur.2022.1037204.
[33]
GU H, YAN Y, HE X, et al. Predicting the clinical prognosis of acute ischemic stroke using machine learning: an application of radiomic biomarkers on non-contrast CT after intravascular interventional treatment[J/OL]. Front Neuroinform, 2024, 18: 1400702 [2026-04-27]. https://dx.doi.org/10.3389/fninf.2024.1400702. DOI: 10.3389/fninf.2024.1400702.
[34]
AVERY E W, BEHLAND J, MAK A, et al. CT angiographic radiomics signature for risk stratification in anterior large vessel occlusion stroke[J/OL]. Neuroimage Clin, 2022, 34: 103034 [2026-04-27]. https://dx.doi.org/10.1016/j.nicl.2022.103034. DOI: 10.1016/j.nicl.2022.103034.
[35]
OZKARA B B, KARABACAK M, HOSEINYAZDI M, et al. Utilizing imaging parameters for functional outcome prediction in acute ischemic stroke: A machine learning study[J]. J Neuroimaging, 2024, 34(3): 356-365. DOI: 10.1111/jon.13194.
[36]
LIU S, YANG T, WEI M, et al. Time-variant and tissue-level collaterals predict postoperative neurological recovery and clinical outcomes of patients with endovascular thrombectomy[J]. Quant Imaging Med Surg, 2025, 15(5): 4085-4100. DOI: 10.21037/qims-24-1073.
[37]
RAMOS L A, VAN OS H, HILBERT A, et al. Combination of Radiological and Clinical Baseline Data for Outcome Prediction of Patients With an Acute Ischemic Stroke[J/OL]. Front Neurol, 2022, 13: 809343 [2026-04-27]. https://dx.doi.org/10.3389/fneur.2022.809343. DOI: 10.3389/fneur.2022.809343.
[38]
LACIDOGNA G, PITOCCHI F, MASCOLO A P, et al. CT Perfusion as a Predictor of the Final Infarct Volume in Patients with Tandem Occlusion[J/OL]. J Pers Med, 2023, 13(2): 342 [2026-04-27]. https://dx.doi.org/10.3390/jpm13020342. DOI: 10.3390/jpm13020342.
[39]
WU G, WANG H, MA X, et al. SWI and CTP fusion model based on sparse representation method to predict cerebral infarction trend[J/OL]. Front Neurosci, 2024, 18: 1360459 [2026-04-27]. https://dx.doi.org/10.3389/fnins.2024.1360459. DOI: 10.3389/fnins.2024.1360459.
[40]
AMADOR K, PINEL N, WINDER A J, et al. A cross-attention-based deep learning approach for predicting functional stroke outcomes using 4D CTP imaging and clinical metadata[J/OL]. Med Image Anal, 2025, 99: 103381 [2026-04-27]. https://dx.doi.org/10.1016/j.media.2024.103381. DOI: 10.1016/j.media.2024.103381.
[41]
WINDER A J, WILMS M, AMADOR K, et al. Predicting the tissue outcome of acute ischemic stroke from acute 4D computed tomography perfusion imaging using temporal features and deep learning[J/OL]. Front Neurosci, 2022, 16: 1009654 [2026-04-27]. https://dx.doi.org/10.3389/fnins.2022.1009654. DOI: 10.3389/fnins.2022.1009654.
[42]
CUI J, YANG J, WANG Y, et al. Automatic segmentation of hemispheric CSF on MRI using deep learning: Quantifying cerebral edema following large hemispheric infarction[J/OL]. Heliyon, 2024, 10(5): e26673 [2026-04-27]. https://dx.doi.org/10.1016/j.heliyon.2024.e26673. DOI: 10.1016/j.heliyon.2024.e26673.
[43]
FANG T, JIANG Z, ZHOU Y, et al. Automatic assessment of DWI-ASPECTS for acute ischemic stroke based on deep learning[J]. Med Phys, 2024, 51(6): 4351-4364. DOI: 10.1002/mp.17101.
[44]
LIU Y, YU Y, OUYANG J, et al. Functional Outcome Prediction in Acute Ischemic Stroke Using a Fused Imaging and Clinical Deep Learning Model[J]. Stroke, 2023, 54(9): 2316-2327. DOI: 10.1161/strokeaha.123.044072.
[45]
LIVNE M, BOLDSEN J K, MIKKELSEN I K, et al. Boosted Tree Model Reforms Multimodal Magnetic Resonance Imaging Infarct Prediction in Acute Stroke[J]. Stroke, 2018, 49(4): 912-918. DOI: 10.1161/strokeaha.117.019440.
[46]
GUO Y, YANG Y, CAO F, et al. A Focus on the Role of DSC-PWI Dynamic Radiomics Features in Diagnosis and Outcome Prediction of Ischemic Stroke[J/OL]. J Clin Med, 2022, 11(18): 5364 [2026-04-27]. https://dx.doi.org/10.3390/jcm11185364. DOI: 10.3390/jcm11185364.
[47]
YANG H, GUO Y, LU J, et al. Optimizing acute ischemic stroke outcome prediction by integrating radiomics features of DSC-PWI and perfusion parameter maps[J/OL]. Front Neurol, 2025, 16: 1528812 [2026-04-27]. https://dx.doi.org/10.3389/fneur.2025.1528812. DOI: 10.3389/fneur.2025.1528812.
[48]
YASSIN M M, ZAMAN A, LU J, et al. Leveraging Ensemble Models and Follow-up Data for Accurate Prediction of mRS Scores from Radiomic Features of DSC-PWI Images[J]. J Imaging Inform Med, 2025, 38(3): 1467-1483. DOI: 10.1007/s10278-024-01280-x.
[49]
TO M N N, KIM H J, ROH H G, et al. Deep regression neural networks for collateral imaging from dynamic susceptibility contrast-enhanced magnetic resonance perfusion in acute ischemic stroke[J]. Int J Comput Assist Radiol Surg, 2020, 15(1): 151-162. DOI: 10.1007/s11548-019-02060-7.
[50]
IM J G, KIM J H, PARK S H. Simultaneous measurement of cerebral blood flow and cerebrospinal fluid flow using pseudo-continuous arterial spin labeling[J/OL]. Neuroimage, 2025, 311: 121192 [2026-04-27]. https://dx.doi.org/10.1016/j.neuroimage.2025.121192. DOI: 10.1016/j.neuroimage.2025.121192.
[51]
LIU S, FAN D, ZANG F, et al. Collateral circulation detected by arterial spin labeling predicts outcome in acute ischemic stroke[J]. Acta Neurol Scand, 2022, 146(5): 635-642. DOI: 10.1111/ane.13694.
[52]
WANG Z, JIANG C, ZHANG X, et al. Machine learning-based prognostic prediction for acute ischemic stroke using whole-brain and infarct multi-PLD ASL radiomics[J/OL]. BMC Med Imaging, 2025, 25(1): 267 [2026-04-27]. https://dx.doi.org/10.1186/s12880-025-01807-w. DOI: 10.1186/s12880-025-01807-w.
[53]
OSAMA S, ZAFAR K, SADIQ M U. Predicting Clinical Outcome in Acute Ischemic Stroke Using Parallel Multi-parametric Feature Embedded Siamese Network[J/OL]. Diagnostics (Basel), 2020, 10(11): 858 [2026-04-27]. https://dx.doi.org/10.3390/diagnostics10110858. DOI: 10.3390/diagnostics10110858.
[54]
GUO K, ZHU B, LI R, et al. Machine learning-based nomogram: integrating MRI radiomics and clinical indicators for prognostic assessment in acute ischemic stroke[J/OL]. Front Neurol, 2024, 15: 1379031 [2026-04-27]. https://dx.doi.org/10.3389/fneur.2024.1379031. DOI: 10.3389/fneur.2024.1379031.
[55]
WU N, LU W, XU M. Multimodal radiomics based on lesion connectome predicts stroke prognosis[J/OL]. Comput Methods Programs Biomed, 2025, 263: 108701 [2026-04-27]. https://dx.doi.org/10.1016/j.cmpb.2025.108701. DOI: 10.1016/j.cmpb.2025.108701.
[56]
DRAGOȘ H M, STAN A, POPA L L, et al. Functional Connectivity and MRI Radiomics Biomarkers of Cognitive and Brain Reserve in Post-Stroke Cognitive Impairment Prediction-A Study Protocol[J/OL]. Life (Basel), 2025, 15(1): 131 [2026-04-27]. https://dx.doi.org/10.3390/life15010131. DOI: 10.3390/life15010131.
[57]
PENG S J, CHEN Y W, HUNG A, et al. Connectome-based predictive modeling for functional recovery of acute ischemic stroke[J/OL]. Neuroimage Clin. 2023, 38: 103369 [2026-04-27]. https://dx.doi.org/10.1016/j.nicl.2023.103369. DOI: 10.1016/j.nicl.2023.103369.
[58]
ZHANG R, ZHANG M, WANG X, et al. Predictive Value of Machine Learning Models for Functional Recovery Following Endovascular Thrombectomy in Patients with Acute Vertebrobasilar Artery Occlusion[J]. Curr Neurovasc Res, 2026, 23(3): 174-186. DOI: 10.2174/0115672026420610260121074852.

PREV Research progress of structural and functional MRI on acupuncture treatment for post-stroke cognitive impairment after ischemic stroke
NEXT Research progress of magnetic resonance proton density fat fraction in extra-hepatic fat quantification
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn