<- Back to digest

Spine Journal - 2026-10-01 - Journal Article; Multicenter Study

From 3 to 8 clusters: a machine learning-based classification of operated adult spinal deformity patients.

Roscop C, Bourghli A, Baroncini A, Alanay A, Pellise F, Kleinstueck F, Pizones J, Charles YP, ESSG, Larrieu D, Boissière L, Obeid I

retrospective cohortLOE IIIn = 471N/A if not reported.

Topics

spinepediatrics
PMID: 42214688DOI: 10.1016/j.spinee.2026.05.003View on PubMed ->

Key Takeaway

An 8-cluster k-means model classified 471 operated ASD patients with 91.4% LDA prediction accuracy, outperforming prior 3-cluster unsupervised models in clinical granularity.

Summary Depth

Choose how much analysis to show on this article page.

Summary

This multicenter retrospective study applied k-means clustering to 12 demographic, radiographic, and functional variables in 471 operated ASD patients to compare 3-cluster versus 8-cluster phenotypic solutions. The 8-cluster model identified clinically distinct subgroups including young idiopathic, structural hyperkyphosis, early sagittal decompensation, and elderly clusters differentiated by pain profile, frailty, and coronal-versus-sagittal collapse dominance. LDA achieved 91.4% classification accuracy across 50 testing splits, outperforming KNN.

Key Limitation

The absence of postoperative functional outcome data (ODI, SRS-22 change scores, complication rates per cluster) means the clinical utility of the 8-cluster model for predicting surgical results is entirely unvalidated.

Original Abstract

BACKGROUND CONTEXT

Adult spinal deformity (ASD) is a heterogeneous condition encompassing diverse etiologies, clinical presentations, and surgical challenges. While previous unsupervised learning models have stratified ASD patients into 3 broad phenotypes, these often lack clinical granularity for surgical decision-making.

PURPOSE

To refine the classification of operated ASD patients using unsupervised machine learning and assess whether expanding from 3 to 8 clusters improves clinical discrimination and predictive robustness.

STUDY DESIGN

Retrospective multicenter study using machine learning clustering.

PATIENT SAMPLE

A total of 471 adult patients who underwent surgery for ASD across 6 specialized spine centers.

OUTCOME MEASURES

ODI, SRS-22, spinal alignment metrics, surgical strategy, and postoperative complications.

METHODS

A k-means clustering algorithm was applied to a selected set of 12 demographic, radiographic, and functional variables (C12). Clustering solutions with 3 and 8 groups were compared. Each cluster was analyzed for age, etiology, disability scores (ODI, SRS-22), spinal alignment, surgical strategy, and complication rates. Predictive models using LDA and KNN assessed classification accuracy for new patient assignment.

RESULTS

The 8-cluster model identified clinically distinct phenotypes, including subgroups of young patients with idiopathic scoliosis, structural hyperkyphosis, and early sagittal decompensation. In elderly patients, clusters differentiated pain profiles, alignment, and frailty. The most severe clusters distinguished coronal-dominant vs sagittal collapse deformities, with differing risks and outcomes. LDA maintained robust accuracy (91.4%) in predicting cluster assignment across 50 testing splits, outperforming KNN.

CONCLUSIONS

To our knowledge, this is among the most granular unsupervised ML-based phenotypic classifications of operated ASD patients reported to date. This refined 8-cluster model enhances clinical phenotyping in ASD surgery, offering more precise subgroup stratification than traditional 3-cluster models. It supports the integration of unsupervised learning into personalized surgical planning, risk stratification, and multicenter outcome trials.