Machine learning identifies clusters of the normal adolescent spine based on sagittal balance.

PURPOSE: This study applied a machine learning semi-supervised clustering approach to radiographs of adolescent sagittal spines from a single pediatric institution to identify patterns of sagittal alignment in the normal adolescent spine. We sought to explore the inherent variability found in adolescent sagittal alignment using machine learning to remove bias and determine whether clusters of sagittal alignment exist. METHODS: Multiple semi-supervised machine learning clustering algorithms were applied to 111 normal adolescent sagittal spines. Sagittal parameters for resultant clusters were determined. RESULTS: Machine learning analysis found that the spines did cluster into distinct groups with an optimal number of clusters ranging from 3 to 5. We performed an analysis on both 3 and 5-cluster groups. The 3-cluster groups analysis found good consistency between methods with 96 of 111, while the analysis of 5-cluster groups found consistency with 105 of 111 spines. When assessing for differences in sagittal parameters between the groups for both analyses, there were differences in T4-12 TK, L1-S1 LL, SS, SVA, PI-LL mismatch, and TPA. However, the only parameter that was statistically different for all groups was SVA. CONCLUSIONS: Based on machine learning, the adolescent sagittal spine alignments do cluster into distinct groups. While there were distinguishing features with TK and LL, the most important parameter distinguishing these groups was SVA. Further studies may help to understand these findings in relation to spinal deformities.

Comparison of baseline characteristics and postoperative complications in neuromuscular, syndromic and congenital scoliosis.

Nonidiopathic scoliosis encompasses a group of diagnoses, including neuromuscular scoliosis, syndromic scoliosis and congenital scoliosis. The objective of this study was to compare the preoperative and postoperative clinical differences in pediatric nonidiopathic scoliosis patients with neuromuscular scoliosis vs. syndromic scoliosis/congenital scoliosis. This is a single-center retrospective review of all pediatric patients undergoing spinal instrumentation for nonidiopathic scoliosis during a 5-year period. Neuromuscular scoliosis patients ( n = 144), syndromic scoliosis patients ( n = 44) and congenital scoliosis patients ( n = 52) were compared. Demographics, patient characteristics and outcomes were compared. Neuromuscular scoliosis patients had lower BMI z-scores and were more likely to have pulmonary disease, technology dependence and seizure disorder. Additionally, neuromuscular scoliosis patients underwent bigger procedures with more levels fused and a higher rate of pelvis fixation. By direct comparison, neuromuscular scoliosis patients tended to have more complications including deep surgical site infections, readmission in 30 days, return to operating room in 90 days and emergency care visits in 90 days. When controlling for the differences in their preexisting conditions and surgical procedure, we found that pelvic fixation was a major confounding factor, whereas the others had no effect. We further subanalyzed cerebral palsy patients and found this group to exhibit no difference in complications compared to other neuromuscular scoliosis subtypes. Neuromuscular scoliosis patients have different characteristics and subsequent postoperative complications than those with syndromic scoliosis and congenital scoliosis. The difference in complication profile is mainly due to differences in surgical procedure and a higher rate of pelvic fixation. This should be considered when planning nonidiopathic scoliosis surgery among multidisciplinary teams.