AI Model Integrating Imaging and Clinical Data for Predicting CSF Diversion in Neonatal Hydrocephalus: A Preliminary Study.
Authors
Affiliations (10)
Affiliations (10)
- Department of Neurology, Second Xiangya Hospital of Central South University, Changsha, Hunan, China.
- Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University, Baltimore, Maryland, USA.
- Department of Diagnostic Imaging, Brown University Health, Providence, Rhode Island, USA.
- Department of Radiology, Xiangya Hospital of Central South University, Changsha, Hunan, China.
- National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University, Changsha, Hunan, China.
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, USA.
- Department of Neurosurgery, Montefiore Medical Center and the Albert Einstein College of Medicine, New York, USA.
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA.
- Department of Neurosurgery, Johns Hopkins University, Baltimore, Maryland, USA.
- National Engineering Research Center of Personalized Diagnostic and Therapeutic Technology, Xiangya Hospital of Central South University, Changsha, China.
Abstract
Predictive tools for stratifying neonatal hydrocephalus into low- and high-risk groups for cerebrospinal fluid (CSF) diversion are currently lacking. We developed and validated an artificial intelligence (AI) model that integrates multimodal imaging and clinical data to predict CSF diversion needs. The development cohort included 116 neonates with suspicion of raised intracranial pressure (ICP) from a Chinese tertiary referral hospital (80 with intracranial pressure > 80 mm H<sub>2</sub>O, 36 with intracranial pressure ≤ 80 mm H<sub>2</sub>O). The external validation cohort consisted of 21 neonates with hydrocephalus from an American medical center, categorized by etiology: prenatal myelomeningocele (MMC) closure (n = 5), postnatal MMC closure (n = 6), and post-hemorrhagic hydrocephalus (PHH) (n = 10). Inclusion criteria required available MRI and complete clinical follow-up to confirm CSF diversion outcomes. The primary outcome was the need for CSF diversion. Model performance was assessed using under the receiver operating characteristics curve (AUC), sensitivity, and specificity. The hybrid AI model achieved an AUC of 0.824 in the development cohort in predicting raised ICP, outperforming both the clinical-only model (AUC 0.528, p < 0.001) and the image-only model (AUC 0.685, p = 0.007). In the external validation cohort, the fused MRI-based model achieved an AUC of 0.808. The model correctly predicted CSF diversion in 4/5 prenatal MMC, 4/6 postnatal MMC, and 9/10 PHH cases. The AI model demonstrated robust performance in predicting the need for CSF diversion, particularly in PHH cases, and has the potential to assist decision-making, especially in settings with limited pediatric neurosurgical expertise. Future work should focus on further refining model performance for complex etiologies such as MMC-associated hydrocephalus.