Abstract Background and aims Cerebral Venous Thrombosis (CVT) outcomes are highly heterogeneous, and existing prognostic scores lack precision. We developed a comprehensive model to predict 6-month poor functional outcome (mRS 3–6) to improve early risk stratification and secondary prevention. Methods We conducted a retrospective observational cohort study of patients diagnosed with acute CVT from the international CoLlabOraTion on Cerebral VENoUs Thrombosis Study (CLOT-VENUS) registry (2004-2024), including two comprehensive stroke centers in the USA and Mexico. Most relevant clinical, imaging, and laboratory results were collected. Parsimonious predictors were identified using LASSO regression and recursive feature elimination. To facilitate clinical utility, a normogram was developed to provide a visual representation of the model’s predictive contributions. Then it was validated on a 1/3 held-out testing set Results Of 432 patients, 394 met the inclusion criteria. Median age was 40 years IQR 28-55, and 65% were female. Volume of ICH, altered mental status, mRS baseline, hematocrit, BMI, monocyte-to-lymphocyte ratio, and deep CVT location were identified as important predictors of poor outcome and included in a final prediction model. Performance of the final model to predict mRS 3-6 months was estimated with cross-validation to have area under the receiver operating characteristic curve of 0.88 95%CI 0.83–0.93 was estimated in the testing set to have area under the receiver operating characteristic curve of 0.79 95%CI: 0.67–0.91 Conclusions This validated scale provides a reliable tool at admission for predicting 6-month outcomes in acute CVT, facilitating individualized risk stratification and enhancing secondary prevention strategies. Conflict of interest Santiago Ortega-Gutierrez: NIH-NINDS (RO1NS127114, RO1NS138765, RO3NS126804), Leonardo Cruz-Criollo and rest of the team: nothing to disclose, Figure 1 - belongs to Conclusions
Cruz-Criollo et al. (Fri,) studied this question.