1126 - Re-Irradiation Incident Analysis with AI: Identifying Opportunities for Workflow Optimization and Improvement

04:15pm - 04:20pm ET

Room 256

Presenter(s)

Abbas Jinia, PhD - Memorial Sloan Kettering Cancer Center, New York, NY

A. J. Jinia¹, K. L. Chapman¹, S. Liu¹, C. Della Biancia¹, E. Hipp¹, E. Lin¹, R. Moulder², D. R. Parikh³, J. Cordero³, M. Gil³, J. Ford⁴, A. Li¹, and J. M. Moran¹; ¹Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, ²Division of Quality and Safety, Memorial Sloan Kettering Cancer Center, New York, NY, ³Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York, NY, ⁴Department of Nursing, Memorial Sloan Kettering Cancer Center, New York, NY

Purpose/Objective(s):

We developed an artificial intelligence (AI) powered incident analysis and learning system (AI-ILS) to analyze radiotherapy incidents using the Human Factors Analysis and Classification System (HFACS) framework, which systematically identifies contributing factors to human errors. Given that approximately 30% of patients at our institution undergo re-irradiation, we analyzed re-irradiation-specific incidents to identify opportunities to improve workflow, safety, and efficiency.

Materials/Methods:

Under an IRB-approved protocol, we retrospectively reviewed all reported incidents from 01/01/2019-09/30/2024. Re-irradiation-related incidents were identified using a large language model in combination with keyword-based filtering. Incident severity and reporter roles were assessed. Incidents were analyzed using AI-ILS to generate aggregated HFACS classifications. We additionally identified the workflow stages at which incidents occurred and were detected.

Results:

Out of 9,919 reported incidents, 267 incidents (< 3%) involved re-irradiation. Of these, 76% were near misses and 24% reached the patient without resulting in harm. Incidents were most frequently reported by plan check physicists (58%), followed by planner physicists or dosimetrists (25%), radiation therapists (11%), and physicians (0.75%).

HFACS analysis identified the most common contributing factors as Personnel Factors (79%; e.g., miscommunication), Organizational Processes (65%; e.g., inadequate rules and procedures), and Errors (57%; e.g., missing contours of prior targets).

123 incidents (46%) occurred during pre-planning documentation (e.g., placement of consultation note and simulation order). 43 incidents (16%) occurred during planner review of the pre-planning documentation. 69 incidents (26%) occurred during treatment planning (e.g., incorrect cumulative EQD2 estimation, misinterpretation of prior dose metrics). 10 incidents (4%) occurred during post-planning and pre-treatment review of the plan and corresponding documentation (e.g., special physics consultation document was not signed).

Regarding incident detection, 65 incidents (24%) were identified during planner document review, 29 (11%) during planning, and 134 (50%) during physicist plan check.

Conclusion:

This analysis found workflow inefficiencies and system vulnerabilities in documentation, cumulative dose assessment, and interdisciplinary communication. With approximately 30% of cases at our institution categorized as re-irradiation, these inefficiencies lead to additional work at multiple stages, thereby resulting in significant time loss. Targeted mitigation strategies, including automated re-irradiation status flags tailored to user roles and enhanced software tools for cumulative EQD2 analysis, are being implemented. AI-ILS classification provides insights to strengthen safety, standardize processes, and improve efficiency in complex re-irradiation workflows.