Improving linear accelerator service response with a real‐time electronic event reporting system

Abstract

To track linear accelerator performance issues, an online event recording system was developed in‐house for use by therapists and physicists to log the details of technical problems arising on our institution's four linear accelerators. In use since October 2010, the system was designed so that all clinical physicists would receive email notification when an event was logged. Starting in October 2012, we initiated a pilot project in collaboration with our linear accelerator vendor to explore a new model of service and support, in which event notifications were also sent electronically directly to dedicated engineers at the vendor's technical help desk, who then initiated a response to technical issues. Previously, technical issues were reported by telephone to the vendor's call center, which then disseminated information and coordinated a response with the Technical Support help desk and local service engineers. The purpose of this work was to investigate the improvements to clinical operations resulting from this new service model. The new and old service models were quantitatively compared by reviewing event logs and the oncology information system database in the nine months prior to and after initiation of the project. Here, we focus on events that resulted in an inoperative linear accelerator (“down” machine). Machine downtime, vendor response time, treatment cancellations, and event resolution were evaluated and compared over two equivalent time periods. In 389 clinical days, there were 119 machine‐down events: 59 events before and 60 after introduction of the new model. In the new model, median time to service response decreased from 45 to 8 min, service engineer dispatch time decreased 44%, downtime per event decreased from 45 to 20 min, and treatment cancellations decreased 68%. The decreased vendor response time and reduced number of on‐site visits by a service engineer resulted in decreased downtime and decreased patient treatment cancellations.PACS numbers: 87.56.bd, 87.55.Qr

Technical Note: Assessing the performance of monthly CBCT image quality QA

“…Incident learning systems have been used in other studies for retrospective quality improvement . The ILS employed in this study, Radiation Oncology Quality Reporting System — Machine Log (ROQRS‐ML), is an in‐house developed system used to communicate machine issues to clinical staff and the equipment vendor in real‐time and to record past and ongoing machine issues and resolutions . ROQRS‐ML was queried for CBCT‐related issues occurring between July 2014 and May 2017.…”

Radiation Oncology in the Era of Big Data and Machine Learning for Precision Medicine

“…Numerous studies [74][75][76][77][79][80][81][82][83] have conducted to develop a computerized system for QA process based on machine learning methods. We can generally categorize these QA into the machine-based and patient-based approach.…”

“…We can generally categorize these QA into the machine-based and patient-based approach. For machine-based QA approach, ML utilizations for automatic QA process of medical linear accelerator (Linac) machine [74][75][76][77] have investigated by research scientists. A study by Li et al [74] investigated the application of ANN to monitor the performance of the Linac for continuous improvement of patient safety and quality of care.…”

“…El Naqa et al [75] introduced a system utilizing anomaly detection to overcome the problem of direct modeling of QA errors and rare events in radiotherapy and to support the intent of automated QA and safety management for patients undergo radiotherapy treatment. Ford et al [76] and Hoisak et al [77] investigated quantifying the error-detection effectiveness of commonly used quality control (QC) measures [76] preventative maintenance [77] in radiation oncology. The results indicated that the effectiveness of QC measures in radiation oncology depends sensitively on which checks are used and in which combinations [76], and also a decreased machine downtime and other technical failures leading to treatment cancellations [77].…”

“…Ford et al [76] and Hoisak et al [77] investigated quantifying the error-detection effectiveness of commonly used quality control (QC) measures [76] preventative maintenance [77] in radiation oncology. The results indicated that the effectiveness of QC measures in radiation oncology depends sensitively on which checks are used and in which combinations [76], and also a decreased machine downtime and other technical failures leading to treatment cancellations [77]. The ability of these ML algorithms to automatically detect outliers allows physicists to focus attention on those aspects of a process most likely to impact the patient care, as recommended in AAPM Task Group report 100 [78].…”