Andrew T Hale1,2, Jay Riva-Cambrin3, John C Wellons4,5, Eric M Jackson6, John R W Kestle7, Robert P Naftel4,5, Todd C Hankinson8, Chevis N Shannon4,5. 1. Medical Scientist Training Program, Vanderbilt University School of Medicine, 2200 Pierce Ave., Light Hall 514, Nashville, TN, 37232, USA. andrew.hale@vanderbilt.edu. 2. Surgical Outcomes Center for Kids, Monroe Carell Jr. Children's Hospital of Vanderbilt University, Nashville, TN, USA. andrew.hale@vanderbilt.edu. 3. Department of Clinical Neurosciences, Alberta Children's Hospital, University of Calgary, Calgary, Alberta, Canada. 4. Surgical Outcomes Center for Kids, Monroe Carell Jr. Children's Hospital of Vanderbilt University, Nashville, TN, USA. 5. Division of Pediatric Neurosurgery, Monroe Carell Jr. Children's Hospital of Vanderbilt University, Nashville, TN, USA. 6. Department of Neurosurgery, Johns Hopkins Children's Center, Johns Hopkins University School of Medicine, Baltimore, MD, USA. 7. Department of Neurosurgery, University of Utah, Salt Lake City, UT, USA. 8. Division of Pediatric Neurosurgery, Children's Hospital Colorado, Aurora, CO, USA.
Abstract
PURPOSE: While conventional statistical approaches have been used to identify risk factors for cerebrospinal fluid (CSF) shunt failure, these methods may not fully capture the complex contribution of clinical, radiologic, surgical, and shunt-specific variables influencing this outcome. Using prospectively collected data from the Hydrocephalus Clinical Research Network (HCRN) patient registry, we applied machine learning (ML) approaches to create a predictive model of CSF shunt failure. METHODS: Pediatric patients (age < 19 years) undergoing first-time CSF shunt placement at six HCRN centers were included. CSF shunt failure was defined as a composite outcome including requirement for shunt revision, endoscopic third ventriculostomy, or shunt infection within 5 years of initial surgery. Performance of conventional statistical and 4 ML models were compared. RESULTS: Our cohort consisted of 1036 children undergoing CSF shunt placement, of whom 344 (33.2%) experienced shunt failure. Thirty-eight clinical, radiologic, surgical, and shunt-design variables were included in the ML analyses. Of all ML algorithms tested, the artificial neural network (ANN) had the strongest performance with an area under the receiver operator curve (AUC) of 0.71. The ANN had a specificity of 90% and a sensitivity of 68%, meaning that the ANN can effectively rule-in patients most likely to experience CSF shunt failure (i.e., high specificity) and moderately effective as a tool to rule-out patients at high risk of CSF shunt failure (i.e., moderately sensitive). The ANN was independently validated in 155 patients (prospectively collected, retrospectively analyzed). CONCLUSION: These data suggest that the ANN, or future iterations thereof, can provide an evidence-based tool to assist in prognostication and patient-counseling immediately after CSF shunt placement.
PURPOSE: While conventional statistical approaches have been used to identify risk factors for cerebrospinal fluid (CSF) shunt failure, these methods may not fully capture the complex contribution of clinical, radiologic, surgical, and shunt-specific variables influencing this outcome. Using prospectively collected data from the Hydrocephalus Clinical Research Network (HCRN) patient registry, we applied machine learning (ML) approaches to create a predictive model of CSF shunt failure. METHODS: Pediatric patients (age < 19 years) undergoing first-time CSF shunt placement at six HCRN centers were included. CSF shunt failure was defined as a composite outcome including requirement for shunt revision, endoscopic third ventriculostomy, or shunt infection within 5 years of initial surgery. Performance of conventional statistical and 4 ML models were compared. RESULTS: Our cohort consisted of 1036 children undergoing CSF shunt placement, of whom 344 (33.2%) experienced shunt failure. Thirty-eight clinical, radiologic, surgical, and shunt-design variables were included in the ML analyses. Of all ML algorithms tested, the artificial neural network (ANN) had the strongest performance with an area under the receiver operator curve (AUC) of 0.71. The ANN had a specificity of 90% and a sensitivity of 68%, meaning that the ANN can effectively rule-in patients most likely to experience CSF shunt failure (i.e., high specificity) and moderately effective as a tool to rule-out patients at high risk of CSF shunt failure (i.e., moderately sensitive). The ANN was independently validated in 155 patients (prospectively collected, retrospectively analyzed). CONCLUSION: These data suggest that the ANN, or future iterations thereof, can provide an evidence-based tool to assist in prognostication and patient-counseling immediately after CSF shunt placement.