Optimizing immunization in pediatric oncology: Development and evaluation of an automated scheduling tool.
AI interpretation is pending for this paper.
Open original publication →What the AI sees
Not AI summarized yet.
Research significance
Pending deeper interpretation.
Source abstract
BACKGROUND: Pediatric cancer patients often struggle to adhere to vaccination schedules, requiring personalized catch-up immunization after treatment. Currently, healthcare professionals create these schedules manually, which is time-consuming, error-prone, and limited in accessibility. We developed and validated an automated clinical decision support system to optimize this process through algorithmic schedule generation. METHODS: Following PRISMA guidelines, we systematically reviewed vaccination recommendations for pediatric cancer patients to develop comprehensive scheduling algorithms. The system implements multi-step optimization modeling incorporating age-dependent dosing, minimum intervals, and treatment-related timing rules for 27 vaccines. We validated the tool through a technical evaluation comparing algorithm-generated schedules against those created by experts for representative pediatric cancer cases and through clinical assessments by healthcare professionals in real-world settings. RESULTS: Technical validation revealed high agreement between algorithm-generated and expert-created schedules, with only minor acceptable variations. Clinical evaluation demonstrated strong user acceptance, with 70% (95% CI: 58.1%-81.9%) of professionals using the system for schedule validation, 61% (95% CI: 48.3%-73.7%) for schedule creation, and 47% (95% CI: 34.0%-60.0%) for vaccination history verification. Users reported median time savings of 20 min per schedule and rated the tool's quality highly (median 4.5/5). CONCLUSIONS: Our clinical decision support system demonstrates technical accuracy and clinical usefulness. It offers an effective solution for managing post-cancer treatment immunizations while alleviating healthcare professionals' workloads, particularly in resource-limited settings.