Machine-learning prediction of curve progression and core stabilization exercises for adolescents with idiopathic scoliosis.

Machine Learning-Based Prediction of Disease Progression in Adolescent Idiopathic Scoliosis Following Core Stabilization Exercise: A Retrospective Model Development and Prospective Validation Study

Not applicable Interventional Istanbul University · NCT07556042

This project will test whether a machine-learning tool can predict curve progression and whether a course of core stabilization exercises helps adolescents aged 10–18 with idiopathic scoliosis.

Quick facts

PhaseNot applicable
Study typeInterventional
Enrollment30 (estimated)
Ages10 Years to 18 Years
SexAll
SponsorIstanbul University Academic / other
Drugs / interventionsradiation
Locations1 site (Istanbul, Eyupsultan)
Trial IDNCT07556042 on ClinicalTrials.gov

What this trial studies

This interventional protocol combines a core stabilization exercise program with a machine-learning approach to predict disease progression in adolescents with idiopathic scoliosis. Participants aged 10–18 with Cobb angles of 10–40° who are not receiving other scoliosis-specific exercise treatment will be enrolled and followed at a single center in Istanbul. Clinical and imaging measures (including Cobb angle and axial rotation) will be tracked over time and used to train and validate predictive models while patients complete the exercise intervention. Patients with prior recent surgery or comorbid conditions that preclude exercise are excluded.

Who should consider this trial

Good fit: Ideal candidates are adolescents aged 10–18 with idiopathic scoliosis and Cobb angles between 10° and 40° who are not currently receiving other scoliosis-specific exercise treatment.

Not a fit: Patients with Cobb angles under 10° or over 40°, prior spinal surgery, recent surgery within three months, or medical/neurological conditions that prevent exercise are unlikely to benefit from this protocol.

Why it matters

Potential benefit: If successful, the approach could allow earlier, more personalized decisions about monitoring, bracing, or exercise and potentially slow curve progression for some patients.

How similar studies have performed: Exercise programs for AIS have shown mixed but sometimes positive effects on progression, and emerging machine-learning models have shown promise for predicting curve progression, though combining them is relatively novel.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* being between the ages of 10 and 18
* having a Cobb angle between 10 and 40 degrees
* not receiving any other exercise treatment (scoliosis-specific exercises, etc.) from a different center that would affect the patient's scoliosis

Exclusion Criteria:

* history of scoliosis surgery
* patients who had undergone any type of surgical procedure within the last 3 months were excluded
* orthopedic, neurological, or systemic diseases that would hinder exercise
* Intellectual, behavioral, or communication disorders affecting understanding of instructions or exercise performance, or participation in any exercise

Where this trial is running

Istanbul, Eyupsultan

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Adolescence Idiopathic Scoliosisscoliosisexercise therapymachine learningArtificial Intelligence
Last reviewed 2026-06-09 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.