Data-driven patient scheduling for speech and language therapy

Abstract

The demand for pediatric Speech-Language Pathology (SLP) services has increased significantly, particularly after COVID-19, leading to extended wait times and limited access to timely intervention for children with speech and language delays. Traditional scheduling models, including continuous scheduling and Specific Timely Appointments for Triage (STAT), while beneficial in some respects, often struggle to meet growing demands without additional resources. Block scheduling has emerged as a potential alternative, offering high-intensity therapy sessions within structured periods to reduce wait times and align treatment with critical developmental windows. However, block scheduling’s rigid framework poses challenges in adapting to fluctuating patient needs and resource constraints. This study develops a mathematical model aimed at optimizing block scheduling in SLP clinics, balancing treatment intensity, wait times, and operational resources. The model leverages real-world variables, such as patient arrival rates and therapist availability, to inform decisions on block length and sequencing, enhancing the efficiency of SLP services without adding to clinician workload. This approach addresses key limitations in current scheduling methods, offering a flexible framework that supports timely intervention during crucial developmental stages. Our findings suggest that optimized block scheduling can reduce administrative burdens, improve service accessibility, and lead to better outcomes for pediatric patients requiring SLP intervention.