Related Experiment Video
Updated: Jul 28, 2026
Cell-based Assay Protocol for the Prognostic Prediction of Idiopathic Scoliosis Using Cellular Dielectric Spectroscopy
Published on: October 16, 2013
Artificial intelligence in early onset scoliosis: a scoping review
Chuck Lam1, Jennifer Tasong2, Halil Bulut3
1School of Medicine, University of Birmingham, Birmingham, UK. chuck.lam2@nhs.net.
Insights
Artificial intelligence (AI) shows promise in diagnosing and predicting outcomes for early onset scoliosis (EOS). However, further research with standardized reporting and multicenter data is needed for clinical application.
Area of Science:
- Orthopaedic surgery
- Medical imaging
- Artificial intelligence
Background:
- Early onset scoliosis (EOS) presents diagnostic and management challenges in children under 10.
- Untreated EOS can lead to severe cardiopulmonary compromise, necessitating timely intervention.
- Artificial intelligence (AI) and machine learning (ML) are emerging tools in orthopaedics for improved detection, prediction, and treatment guidance.
Purpose of the Study:
- To conduct a scoping review of current AI and ML applications in early onset scoliosis.
- To map the use of AI in diagnosing, managing, and predicting outcomes for EOS patients.
- To identify trends and limitations in AI research for EOS.
Main Methods:
- Systematic literature search following PRISMA ScR standards across major databases (PubMed, Embase, Web of Science, Cochrane, Scopus).
- Inclusion criteria focused on studies developing, applying, or validating AI models for EOS diagnosis, management, or outcome prediction.
- Screening and review of 352 records, with 11 studies meeting the final inclusion criteria.
Main Results:
- The majority of studies (63.6%) utilized convolutional neural networks (CNNs) for image analysis, automating radiographic measurements and monitoring treatment.
- AI models demonstrated high accuracy (mean 91.2%) in image analysis and prediction tasks.
- Common limitations identified include small sample sizes, single-center data, and insufficient external validation.
Conclusions:
- AI holds significant potential for enhancing early onset scoliosis imaging and risk prediction.
- Methodological heterogeneity and limited external validation currently hinder the clinical translation of AI tools for EOS.
- Future research should prioritize standardized reporting, aggregation of multicenter datasets, and prospective validation in large cohorts.
Purpose:
Early onset scoliosis comprises spinal deformities in children younger than 10, creating challenges in diagnosis, risk assessment, and management. Timely intervention is vital, because untreated deformity can lead to cardiopulmonary compromise. Artificial intelligence and machine learning are reshaping orthopaedic care by improving detection, forecasting progression, and guiding treatment. This scoping review maps current use in this patient population.
Methods:
Following PRISMA ScR standards, we systematically searched PubMed, Embase, Web of Science, Cochrane, and Scopus for studies that developed, applied, or validated AI models to diagnose, manage, or predict outcomes in EOS.
Results:
After removing duplicates, 352 records were screened, 22 full texts were reviewed, and 11 studies met inclusion criteria. Most investigations (63.6%) employed convolutional neural networks (CNNs) such as Mask R CNN, EfficientNet, and U Net. Ensemble learning with gradient boosting, random forest, and logistic regression (9.1%), Gaussian Naïve Bayes (9.1%), sparse additive machines (9.1%), and unsupervised clustering (9.1%) were also used. Image analysis dominated (72.7%), automating radiographic measurements (Cobb angle, skeletal maturity) and monitoring growing-rod distraction. Predictive models (27.3%) estimated prolonged hospital stay, unplanned reoperation, or postoperative complications. Mean accuracy was 91.2% (range 86.1% to 94.0%). Common limitations were small sample sizes, single-centre data, and limited external validation.
Conclusion:
AI shows promise for EOS imaging and risk prediction, yet translation is hindered by methodological heterogeneity and scarce external validation. Future work should adopt standardised reporting, aggregate multicentre datasets, and test models prospectively in large cohorts.
