1. Does machine learning improve prediction accuracy of the Endoscopic Third Ventriculostomy Success Score? A contemporary Hydrocephalus Clinical Research Network cohort study.
- Author
-
Malhotra AK, Kulkarni AV, Verhey LH, Reeder RW, Riva-Cambrin J, Jensen H, Pollack IF, McDowell M, Rocque BG, Tamber MS, McDonald PJ, Krieger MD, Pindrik JA, Isaacs AM, Hauptman JS, Browd SR, Whitehead WE, Jackson EM, Wellons JC 3rd, Hankinson TC, Chu J, Limbrick DD Jr, Strahle JM, and Kestle JRW
- Subjects
- Humans, Female, Male, Infant, Child, Preschool, Cohort Studies, Child, Treatment Outcome, Neuroendoscopy methods, Machine Learning, Hydrocephalus surgery, Hydrocephalus diagnostic imaging, Ventriculostomy methods, Third Ventricle surgery, Third Ventricle diagnostic imaging
- Abstract
Purpose: This Hydrocephalus Clinical Research Network (HCRN) study had two aims: (1) to compare the predictive performance of the original ETV Success Score (ETVSS) using logistic regression modeling with other newer machine learning models and (2) to assess whether inclusion of imaging variables improves prediction performance using machine learning models., Methods: We identified children undergoing first-time ETV for hydrocephalus that were enrolled prospectively at HCRN sites between 200 and 2020. The primary outcome was ETV success 6 months after index surgery. The cohort was randomly divided into training (70%) and testing (30%) datasets. The classic ETVSS variables were used for logistic regression and machine learning models. Predictive performance of each model was evaluated on the testing dataset using area under the receiver operating characteristic curve (AUROC)., Results: There were 752 patients that underwent first time ETV, of which 185 patients (24.6%) experienced ETV failure within 6 months. For aim 1, using the classic ETVSS variables, machine learning models did not outperform logistic regression with AUROC 0.60 (95% CI: 0.52-0.69) for Naïve Bayes (highest machine learning model performance) and 0.68 (95% CI: 0.60-0.76) for logistic regression. After inclusion of imaging features (aim 2), machine learning model prediction improved but remained no better than the above logistic regression with the highest AUROC of 0.67 (95% CI: 0.59-0.75) attained using Naïve Bayes architecture compared to 0.68 (95% CI: 0.59-0.76) for logistic regression., Conclusions: This contemporary multicenter observational cohort study demonstrated that machine learning modeling strategies did not improve performance of the ETVSS model over logistic regression., Competing Interests: Declarations. Competing interests: The authors declare no competing interests., (© 2024. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)
- Published
- 2024
- Full Text
- View/download PDF