Predicting cerebellar mutism syndrome in children using lesion map combined with clinical features.

Abstract

Objective: This study aimed to develop a predictive model for cerebellar mutism syndrome (CMS) in pediatric patients with posterior fossa tumors, integrating lesion-symptom mapping (LSM) data with clinical factors, and to assess the model's performance.

Methods: A cohort of pediatric patients diagnosed with posterior fossa tumors and undergoing surgery at Beijing Children's Hospital from July 2013 to December 2023 was analyzed. Clinical variables gender, age at surgery, tumor characteristics, hydrocephalus, surgical route and pathology were collected. LSM was used to link tumor locations with CMS outcomes. Lasso regression and logistic regression were employed for feature selection and model construction, respectively. Model performance was assessed using area under the curve (AUC) and accuracy metrics.

Results: The study included 197 patients in total, with CMS rates consistent across training, validation, and prospective groups. Significant associations were found between CMS and gender, tumor type, hydrocephalus, paraventricular edema, surgical route, and pathology. A predictive model combining voxel location data from LSM with clinical factors achieved high predictive performance (C-index: training 0.956, validation 0.933, prospective 0.892). Gender, pathology, and voxel location were identified as key predictors for CMS.

Conclusion: The study established an effective predictive model for CMS in pediatric posterior fossa tumor patients, leveraging LSM data and clinical factors. The model's accuracy and robustness suggest its potential utility in clinical practice for early CMS risk assessment and intervention planning.