Elective surgery – surgery that is organised in advance – requires careful planning within NHS hospitals. This involves a potentially complex process that directly affects patient safety and waiting times. Long surgical procedures increase the risk of infection, as extended operating time is associated with higher rates of surgical site infections. Additionally, patients carrying antimicrobial resistant (AMR) organisms (AMR-positive patients) are often scheduled at the end of an operating list to reduce the risk of transmission to other patients, which might reduce the number of cases completed in a session. As AMR becomes more common, this constraint will increasingly affect how many patients can be treated.
Currently, scheduling decisions are largely made manually, which is time-consuming and does not always account for these infection-related factors. We aim to use routinely collected hospital data to develop models that can predict surgical duration and identify infection-related scheduling constraints. These models could help automate and optimise theatre scheduling, reducing Referral-to-Treatment (RTT) waiting times while incorporating infection prevention priorities such as providing timely additional doses of antibiotics during long cases and appropriate placement of AMR-positive patients on operating lists.