Automating Treatment Recommendations for Children with Cerebral Palsy Based on Multi-Modal Clinical Data

Abstract

Physical disability of children caused by Cerebral Palsy has a prevalence of 2.5 per 1000 births and disrupts body movements such as gait that is essential for healthy pediatric development and overall well-being. Using a diagnostic matrix of clinical history, physical examination, imaging, and gait analysis data, clinicians can quantify how musculoskeletal impairments are impacting movement as evidence-based treatment planning. However, subjectivity and variability in gait analysis interpretation leads to low agreement among clinicians or institutions for cerebral palsy (CP) intervention. Consequently, the treatment planning process varies and takes years of expertise and significant effort to reach the level of competency necessary to synthesize data. In this study, we developed an evidence-based clinical decision support system (CDSS) that automatically recommends treatment options for CP pediatric patients based on an expert-verified clinical workflow. We integrated multi-modal clinical data such as patient demographic, physical exam, and gait analysis information. We validated the automated clinical workflow using de-identified patient data and achieved an accuracy of 0.612 for nine potential treatment options. We generated interpretable results to assist clinicians in using the automated clinical workflows. Our work serves as the foundation for evidence-based, data-driven treatment planning in pediatric CP clinical practice and clinical research, thereby enhancing the efficiency and accuracy in cerebral palsy patient care.