Machine Learning-Based Clinical Adjusted Selection of Predicting Risk Factors for Shunt Infection in Children

Ehsan Moradi,Zohreh Habibi,Farideh Nejat,Nasrin Shahbazi,Malihe Sabeti

doi:10.34172/icnj.2021.28

Abstract

Background: Shunt Infection is a common complication of shunt insertion in children which can lead to bad neuro-developmental conditions and impose a considerable economic burden for the health care system. So, identifying predictive factors of shunt infection could help us in the proper improvement of this deteriorating condition. Methods: In this study, related risk factors of 68 patients with history of shunt infection and 80 matched controls without any history of shunt infection, who were all operated in a single referral hospital were assessed. Three machine learning (ML)-based measures including sparsity, correlation, and redundancy along with specialist’s score were applied to select the most important predictive risk factors for shunt infection. ML was determined by summation of sparsity, correlation and redundancy measures, and the final total score was considered as normalization (ML-based score + specialist score). Results: According to the total score, prematurity, first ventriculoperitoneal shunting (VPS) age, intraventricular hemorrhage (IVH), myelomeningocele (MMC) and low birth weight had higher weights as shunt infection risk factors. icterus, trauma, co-infection and tumor had the lowest weights and history of meningitis and number of shunt revisions were defined as intermediate risk factors. Conclusion: The "ML-based clinical adjusted" method may be used as a complementary tool to help neurosurgeons in better patient selection and more accurate follow-up of children with higher risk of shunt infection.

Highlights

Cerebrospinal fluid (CSF) is continuously secreted in the central nervous system (CNS), flows through ventricles and the sub-arachnoid space and mainly absorbed in brain venous blood system
Hydrocephalus identified by excessive volume of CSF in brain ventricles or sub arachnoid space, which is mostly related to obstruction in CSF drainage pathways or decrease in brain blood flow absorption
Among more than 800 ventriculoperitoneal shunt procedures that have been performed by the senior author (Habibi et al5) in Children’s Medical Center hospital of Tehran (Iran) on hydrocephalus patients under the age of 12, 148 patients with hydrocephalus were selected by considering a set of meticulous inclusion/ exclusion criteria. 68 patients with shunt infection were consecutively enrolled, and 80 patients without shunt infection who have had undergone shunting procedure in the same week were considered as controls for each case

Summary

Introduction

Cerebrospinal fluid (CSF) is continuously secreted in the central nervous system (CNS), flows through ventricles and the sub-arachnoid space and mainly absorbed in brain venous blood system. A precise balance between secretion and absorption of CSF is crucial for the maintenance of normal intracranial pressure (ICP).[1] Hydrocephalus identified by excessive volume of CSF in brain ventricles or sub arachnoid space, which is mostly related to obstruction in CSF drainage pathways or decrease in brain blood flow absorption. The most common etiologies of hydrocephalus are tumors, CNS infections, head trauma and brain developmental abnormalities. Three machine learning (ML)-based measures including sparsity, correlation, and redundancy along with specialist’s score were applied to select the most important predictive risk factors for shunt infection. Conclusion: The “ML-based clinical adjusted” method may be used as a complementary tool to help neurosurgeons in better patient selection and more accurate follow-up of children with higher risk of shunt infection.

Methods

Results

Conclusion