Barriers and facilitators to clinical implementation of radiotherapy treatment planning automation: A survey study of medical dosimetrists

Abstract

Little is known about the scale of clinical implementation of automated treatment planning techniques in the United States. In this work, we examine the barriers and facilitators to adoption of commercially available automated planning tools into the clinical workflow using a survey of medical dosimetrists. Methods/materials: Survey questions were developed based on a literature review of automation research and cognitive interviews of medical dosimetrists at our institution. Treatment planning automation was defined to include autocontouring and automated treatment planning. Survey questions probed frequency of use, positive and negative perceptions, potential implementation changes, and demographic and institutional descriptive statistics. The survey sample was identified using both a LinkedIn search and referral requests sent to physics directors and senior physicists at 34 radiotherapy clinics in our state. The survey was active from August 2020 to April 2021. Results: Thirty-four responses were collected out of 59 surveys sent.Three categories of barriers to use of automation were identified. The first related to perceptions of limited accuracy and usability of the algorithms. Eighty-eight percent of respondents reported that auto-contouring inaccuracy limited its use, and 62% thought it was difficult to modify an automated plan, thus limiting its usefulness. The second barrier relates to the perception that automation increases the probability of an error reaching the patient. Third, respondents were concerned that automation will make their jobs less satisfying and less secure. Large majorities reported that they enjoyed plan optimization, would not want to lose that part of their job, and expressed explicit job security fears. Conclusion:To our knowledge this is the first systematic investigation into the views of automation by medical dosimetrists. Potential barriers and facilitators to use were explicitly identified. This investigation highlights several concrete approaches that could potentially increase the translation of automation into the clinic, along with areas of needed research.

Clinical physicists’ perceptions of weekly chart checks and the potential role for automated image review assessed by structured interviews

“…This contrasts strongly with job security concerns related to automated treatment planning, which is a considerable source of worry for dosimetrists with one study finding that 21/34 dosimetrists explicitly voiced this concern. 40 While computers and automation can assist in the process and make the weekly checks more efficient and more effective, physicists still seem to feel that there will be a place for them in the clinic.This sentiment fits neatly within one of the stated trajectories of Medical Physics 3.0 (MP3.0), 41 namely, Sustainability, which argues for a redistribution of the medical physicist's responsibilities in order to better pursue value-based goals. Physicists can preserve a place for themselves in the clinic by advocating for new automated tools that complement their role and allow them to shift their focus to complex tasks, thereby increasing their value to the clinic overall.…”

Development and multi‐institutional validation of a convolutional neural network to detect vertebral body mis‐alignments in 2D x‐ray setup images

“…We believe our work adds significantly to this effort. Future work should focus on using implementation science to optimize the integration of such a tool into the current radiation oncology clinical workflow, since currently unstudied barriers to practical use likely exist 54 …”

Leveraging intelligent optimization for automated, cardiac-sparing accelerated partial breast treatment planning

“…While novel platforms such as RapidPlan and HyperArc (Varian Medical Systems) have provided a means of automating planning processes (11,12), many institutions still heavily rely on iterative, manual planning (13,14). Developing alternatives to manual planning would be ideal as the time required to train personnel and manually generate high-quality treatment plans remains costly (15).…”