Towards Process Mining in Pediatric Oncology: A Scoping Review and Case Study of Barriers and Facilitators (Preprint)

BACKGROUND Pediatric oncology is characterized by highly protocolized but complex clinical pathways with high levels of variability. Gaining insight into real-world treatment delivery is essential for improving quality of care and research. Process mining offers a data-driven approach to reconstruct and analyze real-world clinical pathways using routinely collected data from healthcare systems. While process mining has been applied in adult oncology, its use in pediatric oncology has not yet been explored, despite its potential to improve quality of care. It is unclear which factors hinder or enable its application. OBJECTIVE This study aimed to identify barriers and facilitators influencing the application of process mining in pediatric oncology. METHODS A broad, systematic scoping review was conducted to identify barriers and facilitators for process mining in adult oncology. Identified factors were thematically mapped using the Human, Organization, and Technology–fit (HOT-fit) framework. Findings were then triangulated with barriers and facilitators identified during a retrospective case study applying process mining to clinical pathways of pediatric patients with neuroblastoma. RESULTS A total of 199 factors were identified across 34 themes in adult oncology. Technology-related factors were most prominent, particularly issues related to data quality, data complexity, and algorithm suitability, while human knowledge and expertise emerged as key facilitators. Many themes translated directly to the pediatric oncology setting, including pervasive data quality issues and high model complexity. Several additional aspects were identified, including limited awareness of organizational research, low patient numbers, and clinician perceptions of process mining. Facilitators unique to pediatric oncology included a highly protocolized care environment and strong international collaborations, which offer opportunities to mitigate limited data availability resulting from low patient numbers. CONCLUSIONS Process mining shows clear potential to provide insight into real-world pediatric oncology pathways, but its broader adoption is constrained by persistent technical, organizational, and human challenges. Advancing process mining in pediatric oncology will require both methodological development of process mining techniques and progress within oncology itself, including improved data awareness, data quality, and stronger engagement with organizational and data-driven research.