EUVIMEDEUVIMED entdecken
Crossref

Machine learning-based differentiation of congenital and adolescent idiopathic scoliosis using routine radiographic parameters

Alaaddin Ates iD, Cafer Ikbal Gulsever iD, Cigdem Ozkara Bilgili, Asli Kazanc Afsin iD, Deniz Oke iD, Neslin Sahin

European Spine Journal · 16.11.2026

DOI: 10.1007/s00586-026-10515-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Spine Journal, online erschienen am 16.11.2026. Verfasst von Alaaddin Ates und 5 weiteren Autor:innen. Beteiligte Einrichtung: Hakkari State Hospital, Hakkari, Turkey. Die Arbeit nennt 17 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Accurate differentiation of congenital scoliosis (CS) from adolescent idiopathic scoliosis (AIS) is important for appropriate diagnostic evaluation and subsequent imaging work-up. We evaluated machine learning models using routinely available demographic and radiographic variables to distinguish CS from AIS.

Methods

In this retrospective single-center study, 166 pediatric patients with scoliosis who underwent standing radiography and MRI between 2018 and 2025 were included. Etiological classification was based on clinical and imaging findings, including whole-spine MRI. Demographic and conventional radiographic variables were used to develop Logistic Regression, Support Vector Machine (SVM), Random Forest, and k-Nearest Neighbors (k-NN) models. Model performance was assessed using accuracy, sensitivity, specificity, precision, F1-score, receiver operating characteristic area under the curve (ROC-AUC), calibration analysis, decision curve analysis, and SHAP-based interpretability.

Results

Of the 166 patients, 96 (57.8%) had AIS and 70 (42.2%) had congenital scoliosis. Logistic Regression achieved the highest overall accuracy (79.4%), whereas Random Forest demonstrated the highest discriminative performance (ROC-AUC, 0.829). Pairwise comparisons using the DeLong test showed no statistically significant differences between the evaluated models. SHAP analysis identified Cobb angle, age, vertebral level, and Nash–Moe rotation grade as the most influential predictors. Calibration performance varied across models, while decision curve analysis demonstrated the greatest net benefit for Logistic Regression.

Conclusion

Machine learning models demonstrated moderate diagnostic performance in differentiating congenital scoliosis from AIS. However, their limited sensitivity and potential for false-negative predictions preclude independent clinical use. Larger studies and external validation are required before their potential role as adjunctive decision-support tools can be established.

Schlagwörter

Stichwörter der Autor:innen

Adolescent idiopathic scoliosisCongenital scoliosisMachine learningMagnetic resonance imagingRadiography

Autor:innen und Institutionen

  • Hakkari State Hospital, Hakkari, Turkey.
  • Hakkari State Hospital, Hakkari, Turkey. cafer.gulsever@gmail.com.
  • Gaziosmanpaşa Eğitim Ve Araştırma Hastanesi, Istanbul, Turkey.

ORCID-Profile: Alaaddin Ates, Cafer Ikbal Gulsever, Asli Kazanc Afsin, Deniz Oke

Zitieren

APA

Ates, A., Gulsever, C. I., Ozkara Bilgili, C., Kazanc Afsin, A., Oke, D., & Sahin, N. (2026). Machine learning-based differentiation of congenital and adolescent idiopathic scoliosis using routine radiographic parameters. European Spine Journal. https://doi.org/10.1007/s00586-026-10515-0

Vancouver

Ates A, Gulsever CI, Ozkara Bilgili C, Kazanc Afsin A, Oke D, Sahin N. Machine learning-based differentiation of congenital and adolescent idiopathic scoliosis using routine radiographic parameters. European Spine Journal. 2026. doi:10.1007/s00586-026-10515-0

BibTeX
@article{Ates2026,
  author = {Ates, Alaaddin and Gulsever, Cafer Ikbal and Ozkara Bilgili, Cigdem and Kazanc Afsin, Asli and Oke, Deniz and Sahin, Neslin},
  title = {Machine learning-based differentiation of congenital and adolescent idiopathic scoliosis using routine radiographic parameters},
  journal = {European Spine Journal},
  year = {2026},
  doi = {10.1007/s00586-026-10515-0}
}
Kostenlos starten →