To investigate risk factors associated with increased intracranial pressure (ICP) in children with sepsis-associated encephalopathy (SAE), and to construct a risk-predicting nomogram.

This single-center prospective observational study included 154 pediatric patients with SAE admitted to the pediatric intensive care unit (PICU) of Chengdu Women's and Children's Central Hospital from May 2022 to June 2024. The cohort comprised 56 patients with elevated ICP and 98 patients without elevated ICP. Clinical characteristics and noninvasive multimodality brain monitoring indices—including the disturbance coefficient (DC), systolic velocity of middle cerebral artery (VsMCA), mean velocity of middle cerebral artery (VmMCA), diastolic velocity of middle cerebral artery (VdMCA), pulsatility index (PI), and regional cerebral oxygen saturation (rScO₂)—were compared among patients. Univariate and multivariate logistic regression analyses were used to identify independent predictors of increased ICP. Then a nomogram was developed using R software. Model performance was evaluated by the receiver operating characteristic curve and area under the curve (AUC). Internal validation was performed via bootstrap resampling.

Multivariate logistic regression analysis identified three independent risk factors for elevated ICP: lower Glasgow coma scale (GCS) score at PICU admission [odds ratio (OR) = 0.560, 95% confidence interval (CI) (0.382, 0.837), P = 0.009], elevated VsMCA on the first day [OR = 1.053, 95%CI (1.010, 1.098), P = 0.025], and elevated rScO₂ on the first day [OR = 1.199, 95%CI (1.063, 1.348), P = 0.004]. The nomogram achieved an AUC of 0.927 [95%CI (0.887, 0.967), P < 0.001], a sensitivity of 92.9%, and a specificity of 79.6%. Calibration curves showed excellent agreement between predictions and observations.

The GCS-VsMCA-rScO₂-based nomogram provides accurate and clinically feasible prediction of elevated ICP in pediatric SAE, thus facilitating early intervention.