Automated DWI Biomarker SCR-U1.8 for Malignant Cerebral Edema Risk Stratification After Stroke

In 530 acute ischemic stroke patients, the automated DWI biomarker SCR-U1.8 logistic regression model achieved 0.990 accuracy and 0.998 AUC for predicting malignant cerebral edema, though only 12 events occurred; findings are exploratory and require external validation.

• SCR-U1.8-LR outperformed a single-predictor U1.8 threshold on accuracy, precision, specificity, and F1 score, at the cost of slightly lower sensitivity (0.900 vs 1.000) and NPV (0.998 vs 1.000).
• Only 12 malignant cerebral edema events were available, making the results exploratory per the authors, who emphasize the need for external validation.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.