Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{203974,
        author = {Dr N.Meena and Haripriya. D},
        title = {Artificial Intelligence–Based Prediction of Physiotherapy Outcomes in Children with Cerebral Palsy: A systematic Review},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {2233-2243},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203974},
        abstract = {Background: Outcomes following conventional physiotherapy in children with cerebral palsy (CP) vary considerably due to heterogeneity in clinical presentation, severity, comorbidities, and therapy characteristics. Artificial intelligence (AI) and machine learning (ML) method have demonstrated the potential to model complex, non-linear rehabilitation data and predict individualized treatment responses. 
Objective: To systematically review the evidence on AI-based models used to predict physiotherapy outcomes in children with cerebral palsy and evaluate their clinical applicability.
Design: Systematic review. 
Data Sources: PubMed, Scopus, Web of Science, Cochrane Library, IEEE Xplore, and Google Scholar were searched from inception to March 2025. 
Eligibility Criteria: Studies involving children with 0–18 years of age with Cerebral Palsy receiving physiotherapy management and employing AI/ML tools for outcome prediction were included.
 Methods: Two reviewers independently screened studies, extracted data, and assessed risk of bias using PROBAST and ROBINS-I tools. Due to methodological heterogeneity, a narrative synthesis was conducted. 
Results: Eighteen studies involving 1,842 children with Cerebral palsy were included. AI techniques included support vector machines, random forest, artificial neural networks, gradient boosting, and regression-based Machine Learning models. Predictive performance was moderate to high with R² values ranging from 0.52–0.89 and Area Under Curve values ranging from 0.71–0.93. External validation was limited. 
Conclusion: AI-based prediction models demonstratepromising potential in forecasting physiotherapy outcomes in children with Cerebral Palsy.However, limitations including small sample sizes, methodological heterogeneity, and limited external validation currently restrict routine clinical implementation.},
        keywords = {Cerebral palsy; Physiotherapy; Artificial Intelligence; Machine learning; Outcome prediction; Predictive modeling},
        month = {June},
        }