A computer aided treatment event recognition system in radiation therapy

Area of Science:

• Medical Physics
• Radiation Oncology
• Health Informatics

Background:

• Radiation therapy requires meticulous monitoring of treatment parameters to ensure patient safety and treatment efficacy.
• Manual review of electronic treatment records can be time-consuming and prone to oversight.
• Automated systems are needed to enhance the efficiency and accuracy of quality assurance in radiation therapy.

Purpose of the Study:

• To develop an automated system for analyzing electronic treatment records in radiation therapy.
• To detect and report treatment events and deviations from the intended plan.
• To improve the efficiency of the quality assurance process for radiation therapy treatments.

Main Methods:

• Developed the Computer Aided Treatment Event Recognition System (CATERS) for automated analysis of electronic treatment records.
• CATERS identifies logical inconsistencies and aberrant treatment parameters (e.g., beam energy, dose, table position, prescription changes, overrides).
• Evaluated CATERS over a 5-month period, analyzing 7692 fractions from 491 patients, and incorporated physicist-identified events into the system.

Main Results:

• CATERS detected 553 exception events, with no significant dosimetric impact on patient treatments.
• The most frequent events detected were couch position override (3.2%), extra cone beam imaging (1.85%), and significant couch position deviation (1.31%).
• The system processes approximately 1 second per patient on standard computing devices.

Conclusions:

• CATERS provides an effective automated tool for detecting and reporting treatment events in radiation therapy.
• Daily electronic record interrogation by CATERS can alert medical physicists to deviations sooner than traditional weekly checks.
• The system's output can serve as valuable input for failure mode and effects analysis, further enhancing safety protocols.