ESTRO 2024 - Abstract Book

S2821

Interdisciplinary - Health economics & health services research

ESTRO 2024

Process mining (PM) has emerged as a powerful tool to analyse and optimize processes in various domains, providing benchmarks for efficiency and optimization. Radiation therapy (RT) plays a crucial role in the treatment of cancer patients and its treatment process encompasses various steps, involving multiple healthcare providers and resources. The aim of the study is to explore the workflows in a high-volume radiation oncology department using a PM approach and evaluate bottlenecks and causes of treatment suspension.

Material/Methods:

This study retrospectively analysed all patients who had scheduled treatments in the department of radiation oncology of the European Institute of Oncology (IEO) in Milan, Italy, from January 1th, 2017, to December 31th, 2021, and provided valid consent. The First Order Markov-Model graph was employed to analyse the event sequence and detect anomalies in the data. The Kruskal-Wallis test was performed to compare median completion times between the sub-cohorts identified through stratification. The analysis was performed by pMineR and R language.

Results:

The study analyzed 43,183 events associated with 8,608 treatments from 2017 to 2021. The pathway diagram depicted key events, such as Prescription, CT Simulation, Scheduling, CT Simulation, RT start, RT Cancelled, RT Suspension, and RT end. The statistical analysis revealed a significant difference in terms of median time in case of suspension event during the path, leading to a delayed in start of RT treatment (p < 0.05). The analysis of time from Prescription to RT start, stratified on primary pathologies, demonstrated a significant impact of suspension on the time interval for breast, gentitourinary, gastrointestinal, metastatic, head and neck, gynecological, thoracic, and skin cancer (p < 0.05).