Development of a hybrid automated chart checking, data collection, and analysis system

Area of Science:

• Medical Physics
• Radiation Oncology
• Health Informatics

Background:

• Radiation therapy requires rigorous chart checks to ensure patient safety and treatment accuracy.
• Manual chart review processes can be time-consuming and prone to human error.
• Integrating automation into chart review can enhance efficiency and consistency.

Purpose of the Study:

• To describe the development and clinical implementation of a hybrid automated chart review platform.
• To create an integrated system combining a database, oncology information system (OIS) interfaces, and a user interface (UI).

Main Methods:

• Developed a consensus checklist to standardize practices for clinical physics staff and residents.
• Introduced the concept of "plan attributes" for specialized, automated checklist generation.
• Implemented a hybrid automation approach combining automated steps with human review.
• Established logging and categorization of identified deficiencies.

Main Results:

• Analyzed over 4 years of data (October 2020 onwards) involving 427,073 tests and 7,882 chart checks.
• Identified 7,116 minor errors, 679 major errors, and 71 plan rejections.
• The platform demonstrated its capability in detecting significant deficiencies requiring plan remediation.

Conclusions:

• Successfully developed and implemented a hybrid-automated chart checking program.
• The software enhances per-case performance and user experience through modern database and software design.
• The chart check database facilitates high-level review and improvement of plan checking and user performance.