Abstract
BACKGROUND: It is known that neuroanatomical and neurofunctional changes observed in the brain, brainstem and cerebellum play a role in the etiology of adolescent idiopathic scoliosis (AIS). This study aimed to investigate whether volumetric measurements of brain regions can be used as predictive indicators for AIS through machine learning techniques. METHODS: Patients with a severe degree of curvature in AIS (n = 32) and healthy individuals (n = 31) were enrolled in the study. Volumetric data from 169 brain regions, acquired from magnetic resonance imaging (MRI) of these individuals, were utilized as predictive factors. A comprehensive analysis was conducted using the twelve most prevalent machine learning algorithms, encompassing thorough parameter adjustments and cross-validation processes. Furthermore, the findings related to variable significance are presented. RESULTS: Among all the algorithms evaluated, the random forest algorithm produced the most favorable results in terms of various classification metrics, including accuracy (0.9083), AUC (0.993), f1-score (0.970), and Brier score (0.1256). Additionally, the most critical variables were identified as the volumetric measurements of the right corticospinal tract, right corpus callosum body, right corpus callosum splenium, right cerebellum, and right pons, respectively. CONCLUSION: The outcomes of this study indicate that volumetric measurements of specific brain regions can serve as reliable indicators of AIS. In conclusion, the developed model and the significant variables discovered hold promise for predicting scoliosis development, particularly in high-risk individuals.