Author(s) :

Mrs.Ch.Sowjanya.

Volume/Issue :

Abstract :

Stroke is a leading cause of disability and mortality, placing substantial burdens on healthcare systems worldwide. Radiomics analysis, an advanced artificial intelligence (AI) technique, transforms medical imaging into quantitative features to enhance predictive modeling and support precision medicine. This study systematically reviewed the application of radiomics in predicting disability outcomes following ischemic stroke. Using PRISMA guidelines, six studies were identified, focusing on predictive models integrating radiomics and clinical features. The findings demonstrated that combined models consistently outperformed those relying on either clinical or radiomics features alone, achieving excellent predictive accuracy with area under the ROC curve (AUC) values ranging from 0.92 (95% CI: 0.75–0.86) to 0.98 (95% CI: 0.87–0.97). The Radiomics Quality Score (RQS) reflected moderate methodological quality (median score: 15), while the PROBAST tool identified a high risk of bias in participant selection. These results underscore the potential of combined radiomics and clinical models to improve the prediction of stroke disability outcomes and guide personalized treatment strategies. However, further validation in diverse clinical settings is necessary to ensure their reliability and clinical utility.

No. of Downloads :

0