The advanced computational analysis of large data sets holds great promise for the field of neurosurgery and for medicine at large. Machine learning algorithms help uncover the contribution of nonlinear variables in complex environments, with applications such as predicting tumor growth or identifying surgical candidacy.1 Hydrocephalus is an area that may benefit from automated image analysis and predictive modeling. Although the cerebral ventricular system may be thought of in simple terms as a balloon that expands when fluid pressure is high, the more detailed reality is of an interconnected series of fluid compartments with regional compliance that can vary with symmetry relationships that change by individual and predisposing conditions. Given this reality, modern analysis software can isolate the ventricles through automated segmentation and can detect structural associations that potentially highlight unrecognized aspects of hydrocephalus.
Chiarelli PA, Hauptman JS, Browd SR. Machine Learning and the Prediction of Hydrocephalus: Can Quantitative Image Analysis Assist the Clinician? JAMA Pediatr. 2018;172(2):116–118. doi:10.1001/jamapediatrics.2017.4450
Coronavirus Resource Center
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: