Robust solutions via optimisation and predictive process monitoring for the scheduling of the interventional radiology procedures

Interventional radiology (IR) is an increasingly used medical specialty relying on the possibilities offered by medical imaging guidance technologies to perform minimally invasive procedures (both diagnostic and therapeutic) through very small incisions or body orifices. Although the operative context is quite similar to that of the classical operating room (OR) literature, to the best of our knowledge management problems arising in the IR operative context never appeared in the healthcare management literature. This is even more true for studies that combine the OR approach with automatic extraction of information from real hospital health record data as in the present study. Two specific features characterise our case study with respect to the traditional OR literature: due to the Italian legislation, the anaesthetist (usually in a very limited number) must be present for the entire duration of the procedure (C1$C1$), and the IR does not have its own ward but receives inpatients from different wards (C2$C2$). The aim of this paper is to introduce a novel approach to determine a robust solution for our case study problem addressing both features C1$C1$ and C2$C2$. Our approach is based on the interplay between optimisation and predictive process monitoring (PPM) models. The obtained results show that the proposed approach produces schedules that achieve higher usage rate, lower overtime and more patients operated on than the original schedule. We also show that the integration of PPM models within the optimisation workflow improves the quality of the output schedule with respect to the standard one-shot optimisation.