Development and Internal Validation of the CLIMPOUT Score: A Multimodal Prediction Model for Neurological Outcome After Pediatric Intracerebral Hemorrhage.

Spontaneous pediatric intracerebral hemorrhage (sICH) is a rare but devastating neurological emergency associated with high mortality and long-term disability. Existing prognostic scores rely on a reduced number of variables and have shown limited validation, highlighting the need for comprehensive tools. This study describes the protocol for the development and internal validation of the CLIMPOUT (Clinical, Laboratory, and Imaging Predictive Outcome) score, a multimodal model designed to improve early prognostic assessment in pediatric sICH. This single-center retrospective cohort study will include consecutive patients (1 month-18 years) admitted to a tertiary pediatric intensive care unit (PICU) with spontaneous sICH between 2018 and 2025. Predictor variables will be restricted to baseline information available at PICU admission, including demographics, clinical status, laboratory markers, and quantitative neuroimaging features. Hematoma and intraventricular hemorrhage volumes will be measured using standardized three-dimensional segmentation. The primary outcome will be poor neurological status at 12 months, defined by the Pediatric Stroke Outcome Measure (PSOM). We will develop a multivariable logistic regression model following contemporary recommendations, including prespecified predictor selection, multiple imputation for missing data, and internal validation by 1000 bootstrap resamples. The CLIMPOUT score is expected to identify independent predictors of poor neurological outcome and provide a standardized, multimodal risk stratification model with improved prognostic performance compared with currently available pediatric scores. This protocol establishes a rigorous framework for developing a clinically applicable prediction model that may support early individualized decision-making, optimize neurocritical care management, and provide the foundation for future multicenter validation.