The goal of this observational study is to develop and validate an AI-based prediction model for functional mobility and gait outcomes in children with cerebral palsy using low-cost clinical and gait data collected in rehabilitation settings in Pakistan. The study aims to determine whether machine learning models can accurately predict mobility status, gait symmetry, and functional independence in ambulatory and non-ambulatory children with cerebral palsy.

The main questions it aims to answer are:

• Can clinical and gait-related variables accurately predict functional mobility and gait outcomes in children with spastic cerebral palsy?
• Can video-based assessment tools provide clinically useful data for AI-based rehabilitation assessment in low-resource settings?

Researchers will analyze clinical, functional, and gait data to identify patterns associated with mobility limitations and rehabilitation outcomes.

Participants will:

• Undergo clinical and functional assessments, including measures of balance, mobility, posture, and functional independence.
• Perform gait and movement tasks while data are collected using AI-based video analysis tools.
• Participate in routine rehabilitation sessions while their movement and functional performance are recorded for analysis.
• Provide demographic and clinical information relevant to cerebral palsy severity and functional status.

Children with cerebral palsy (CP) commonly experience limitations in functional independence and mobility, which significantly affect participation and quality of life. Accurate assessment of these functional abilities is essential for rehabilitation planning, prognosis estimation, and monitoring treatment outcomes. However, conventional assessment methods largely depend on therapist observation and standardized clinical scales, which may be subjective, time-consuming, and less sensitive to complex interactions among clinical variables. In low-resource rehabilitation settings, the limited availability of advanced assessment technologies further restricts objective and data-driven clinical decision-making. Therefore, there is a growing need for innovative, accessible, and reliable approaches to improve rehabilitation assessment in children with CP.

The novelty of this study lies in the application of machine learning techniques to rehabilitation assessment of functional independence and mobility in children with cerebral palsy. Unlike traditional approaches that rely solely on isolated clinical interpretation, this study aims to integrate multiple clinical and functional parameters to identify predictive patterns associated with mobility and independence outcomes. The proposed approach introduces a data-driven and potentially more objective framework for rehabilitation assessment, supporting early identification of functional limitations and personalized intervention planning. Additionally, conducting this research in a low-resource context contributes further novelty by exploring the feasibility of implementing machine learning-based rehabilitation assessment tools in settings where advanced gait laboratories and expensive technologies are not readily available.

Inclusion Criteria:

• Age 4 to18 years
• Diagnosed any motor type of cerebral palsy (spastic, dyskinetic, ataxic, mixed),)
• GMFCS levels I -III (able to walk with or without an assistive device).
• All participants must be able to ambulate at least 10 meters with or without an assistive device.
• Capable of following simple verbal instructions.
• Parental informed consent and child assent

Exclusion Criteria:

• Recent orthopedic or neurosurgical interventions (<6 months).
• Uncontrolled seizures affecting gait.
• Non-ambulatory (GMFCS IV-V) or cognitive impairments preventing cooperation.

Children with cerebral palsy classified within Gross Motor Function Classification System (GMFCS) Levels I-III who are ambulatory with or without assistive devices and receiving routine physiotherapy rehabilitation. Participants from all cerebral palsy subtypes will be included for clinical, functional, and gait assessment related to AI-based evaluation of functional mobility and gait outcomes.