SU-F-T-462: Lessons Learned From a Machine Incident Reporting System

Purpose: Linear accelerators must operate with minimal downtime. Machine incident logs are a crucial tool to meet this requirement. They providing a history of service and demonstrate whether a fix is working. This study investigates the information content of a large department linear accelerator incident log. Methods: Our department uses an electronic reporting system to provide immediate information to both key department staff and the field service department. This study examines reports for five linac logs during 2015. The report attributes for analysis include frequency, level of documentation, who solved the problem, and type of fix used. Results: Of the reports, 36% were documented as resolved. In another 25% the resolution allowed treatment to proceed although the reported problem recurred within days. In 5% only intermediate troubleshooting was documented. The remainder lacked documentation. In 60% of the reports, radiation therapists resolved the problem, often by clearing the appropriate faults or reinitializing a software or hardware service. 22% were resolved by physics and 10% by field service engineers. The remaining 8% were resolved by IT, Facilities, or resolved spontaneously. Typical fixes, in order of scope, included clearing the fault and moving on, closing and re-opening the patient session or software, cycling power to a sub-unit, recalibrating a device (e.g., optical surface imaging), and calling in Field Service (usually resolving the problem through maintenance or component replacement). Conclusion: The reports with undocumented resolution represent a missed opportunity for learning. Frequency of who resolves a problem scales with the proximity of the person's role (therapist, physicist, or service engineer), which is inversely related to the permanence of the resolution. Review of lessons learned from machine incident logs can form the basis for guidance to radiation therapists and medical physicists to minimize equipment downtime and ensure safe operation.