Deep Learning and Radiomics Models for Predicting 90-Day Outcomes in Ischemic Stroke: A Systematic Review and Meta-Analysis
Abstract
BackgroundAccurate prediction of 90-day outcomes following ischemic stroke is crucial for optimizing clinical strategies. This study aimed to systematically review and meta-analyze studies using deep learning (DL) and hand-crafted radiomics (HCR) models for predicting 90-day modified Rankin Scale (mRS) outcomes after ischemic stroke.
MethodsWe followed the PRISMA guidelines for systematic reviews. Four databases (PubMed, Embase, Web of Science, and Cochrane Library) were searched comprehensively for studies published up to September 2025. Inclusion criteria encompassed original research focusing on ischemic stroke patients with mRS at 90 days as the primary outcome and predictive models utilizing imaging biomarkers from CT or MRI. Quality assessment of the included studies was conducted using the PROBAST and and METhodological RadiomICs Score (METRICS) tools.
ResultsSeventeen studies were included in the quantitative meta-analysis. Models demonstrated good prognostic performance for 90-day outcomes, with pooled AUCs of 0.85 (95% CI: 0.80-0.86) for internal and 0.74 (95% CI: 0.67-0.89) for external validation sets, with no significant difference (p=0.42). Deep learning and hand-crafted radiomics models showed comparable diagnostic accuracy in the primary analysis (p=0.667); a difference in sensitivity favouring hand-crafted radiomics emerged only in a post-hoc analysis after exclusion of one outlier study. Models incorporating clinical variables significantly outperformed imaging-only models (p<0.01). CT- and MRI-based models showed similar performance. Treatment-specific analyses revealed higher sensitivity for IVT-based models and higher specificity for combined MT+IVT models.
ConclusionsDL and HCR models demonstrate robust potential for predicting 90-day outcomes in ischemic stroke. Future research should focus on standardizing model evaluation metrics and incorporating explainable AI techniques to improve clinical applicability.
Related
- Comparison of Cranial Ultrasound and Amplitude‐Integrated Electroencephalography in Predicting Neurodevelopmental Outcomes in Neonates With Hypoxic–Ischemic Encephalopathy: A Systematic Review and Meta‐Analysis
- Ultrasound-based deep learning radiomics with explainable machine learning for predicting benign and malignant thyroid nodules in lymphocytic thyroiditis: a multicenter study
- Interpretable deep learning and radiomics for predicting the occurrence of brain metastases following prophylactic brain irradiation in small cell lung cancer
- Multiparametric MRI radiomics and machine learning for outcome prediction in acute ischemic stroke: a retrospective study of 353 patients
- CT imaging-based radiomics and deep learning models for predicting chemotherapy response in advanced pancreatic cancer
BibTeX
@misc{kiani2026deep,
title = {{Deep Learning and Radiomics Models for Predicting 90-Day Outcomes in Ischemic Stroke: A Systematic Review and Meta-Analysis}},
author = {I. Kiani and K. Darmiani and P. Valizade and P. Jannatdoust and S. Bordbar and A. H. Majidzade Moqadam and B. Khosravi},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.13.26365396},
url = {https://www.medrxiv.org/content/10.64898/2026.10.13.26365396v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Deep Learning and Radiomics Models for Predicting 90-Day Outcomes in Ischemic Stroke: A Systematic Review and Meta-Analysis
AU - I. Kiani
AU - K. Darmiani
AU - P. Valizade
AU - P. Jannatdoust
AU - S. Bordbar
AU - A. H. Majidzade Moqadam
AU - B. Khosravi
PY - 2026
DA - 2026/10/13
PB - medRxiv
DO - 10.64898/2026.10.13.26365396
UR - https://www.medrxiv.org/content/10.64898/2026.10.13.26365396v1
AB - BackgroundAccurate prediction of 90-day outcomes following ischemic stroke is crucial for optimizing clinical strategies. This study aimed to systematically review and meta-analyze studies using deep learning (DL) and hand-crafted radiomics (HCR) models for predicting 90-day modified Rankin Scale (mRS) outcomes after ischemic stroke. MethodsWe followed the PRISMA guidelines for systematic reviews. Four databases (PubMed, Embase, Web of Science, and Cochrane Library) were searched comprehensively for studies published up to September 2025. Inclusion criteria encompassed original research focusing on ischemic stroke patients with mRS at 90 days as the primary outcome and predictive models utilizing imaging biomarkers from CT or MRI. Quality assessment of the included studies was conducted using the PROBAST and and METhodological RadiomICs Score (METRICS) tools. ResultsSeventeen studies were included in the quantitative meta-analysis. Models demonstrated good prognostic performance for 90-day outcomes, with pooled AUCs of 0.85 (95% CI: 0.80-0.86) for internal and 0.74 (95% CI: 0.67-0.89) for external validation sets, with no significant difference (p=0.42). Deep learning and hand-crafted radiomics models showed comparable diagnostic accuracy in the primary analysis (p=0.667); a difference in sensitivity favouring hand-crafted radiomics emerged only in a post-hoc analysis after exclusion of one outlier study. Models incorporating clinical variables significantly outperformed imaging-only models (p<0.01). CT- and MRI-based models showed similar performance. Treatment-specific analyses revealed higher sensitivity for IVT-based models and higher specificity for combined MT+IVT models. ConclusionsDL and HCR models demonstrate robust potential for predicting 90-day outcomes in ischemic stroke. Future research should focus on standardizing model evaluation metrics and incorporating explainable AI techniques to improve clinical applicability.
ER -