M Coyne*, Q Diot, R Lanning, A Mahl, L Schubert, K Stuhr, J Backus, S Stoehr, M Miften, D Thomas, University of Colorado School of Medicine, Aurora, CO

• 
  M Coyne

• 
  
• 
  
• 
  
• 
  
• 
  
• 
  
• 
  

(Saturday, 3/26/2022)   [Central Time (GMT-5)]

Purpose: To identify causes of error, and present an automated technique that improves efficiency and helps to reduce transcription and manual data entry errors in the treatment planning of electron beam therapy (EBT).

Methods: Analysis of reports submitted to a department incident learning system (ILS) was performed to identify potential avenues for improvement by implementation of automation of the treatment planning process for EBT. Following this analysis, it became clear that while the individual components of the EBT planning process were well implemented, the manual ‘bridging’ of the components (interpolating data, manual data entry etc.) was a high potential source of error. This was especially evident for patients without a CT simulation, where monitor units are calculated by hand and a phantom plan is manually added to Eclipse. A C#-based plug-in treatment planning script was developed to remove the manual parts of the treatment planning workflow that were contributing to increased risk.

Results: We present an example of the implementation of “Glue” programming, combining treatment planning C# scripts with existing spreadsheet calculation worksheets. Prior to the implementation of automation, 28 incident reports related to EBT were submitted to the ILS over a 2-year period. While no incidents reached patients, reports ranged from minor accessory coding errors caught by machine interlocks, to incorrectly interpolated insert factors with the potential for mistreatment if not caught before delivery. Implementation of automated treatment planning for electrons is expected to reduce treatment planning time per patient and decrease potential incidents.

Conclusion: Manual treatment planning techniques may be standard approach for EBT, but they are time-intensive and have potential for error. Often the barrier to automation becomes the time required to “re-code” existing solutions in unfamiliar computer languages. This presented workflow is proof of concept that automation may help improve clinical efficiency and safety for EBT.

ePosters

• 174-60721-16021654-182788-108369251.pdf (M Coyne)

Keywords

Electron Therapy, Treatment Planning

Taxonomy

TH- External Beam- Electrons: Treatment planning using machine learning/automation

Contact Email