Re-evaluation of the prospective risk analysis for artificial-intelligence driven cone beam computed tomography-based online adaptive radiotherapy after one year of clinical experience

Abstract

Cone-beam computed tomography (CBCT)-based online adaptation is increasingly being introduced into many clinics. Upon implementation of a new treatment technique, a prospective risk analysis is required and enhances workflow safety. We conducted a risk analysis using Failure Mode and Effects Analysis (FMEA) upon the introduction of an online adaptive treatment programme (Wegener et al., Z Med Phys. 2022).

A prospective risk analysis, lacking in-depth clinical experience with a treatment modality or treatment machine, relies on imagination and estimates of the occurrence of different failure modes. Therefore, we systematically documented all irregularities during the first year of online adaptation, namely all cases in which quality assurance detected undesired states potentially leading to negative consequences. Additionally, the quality of automatic contouring was evaluated. Based on those quantitative data, the risk analysis was updated by an interprofessional team. Furthermore, a hypothetical radiation therapist-only workflow during adaptive sessions was included in the prospective analysis, as opposed to the involvement of an interprofessional team performing each adaptive treatment.

A total of 126 irregularities were recorded during the first year. During that time period, many of the previously anticipated failure modes (almost) occurred, indicating that the initial prospective risk analysis captured relevant failure modes. However, some scenarios were not anticipated, emphasizing the limits of a prospective risk analysis. This underscores the need for regular updates to the risk analysis. The most critical failure modes are presented together with possible mitigation strategies. It was further noted that almost half of the reported irregularities applied to the non-adaptive treatments on this treatment machine, primarily due to a manual plan import step implemented in the institution’s workflow.