Navigating Variability in Prostate RT Planning: Real-Time Insights for Human-Centered CDS Design.

Area of Science:

• Medical Physics
• Radiation Oncology
• Human Factors Engineering

Background:

• Clinical variability in prostate radiation therapy (RT) planning is a known issue.
• Understanding the human factors behind this variability is crucial for improving treatment consistency.
• Little is known about how radiation oncologists experience and adapt to factors driving planning variability.

Purpose of the Study:

• To explore variability in prostate RT planning as a human-centered design challenge.
• To inform the design of clinical decision support (CDS) tools by gaining real-time insight into planning decisions.
• To identify contributors to variability from the perspective of radiation oncologists.

Main Methods:

• Conducted observation sessions using the think-aloud method with five radiation oncologists during prostate case contouring.
• Followed observations with semi-structured interviews to gather in-depth insights.
• Thematically analyzed contributors to variability using the Systems Engineering Initiative for Patient Safety (SEIPS) framework across tasks, technology, and organizational conditions.

Main Results:

• Variability in prostate RT planning stems from anatomical ambiguity, guideline interpretation, and individual decision-making.
• Radiation oncologists employ adaptive strategies, including reliance on prior experience and estimation under uncertainty.
• Factors contributing to variability were identified across tasks, technology, and organizational contexts.

Conclusions:

• Variability in prostate radiation therapy planning is influenced by complex cognitive and adaptive processes of radiation oncologists.
• Context-sensitive CDS tools are needed to support clinical reasoning while maintaining flexibility.
• Human-centered design approaches are essential for developing effective decision support in radiation oncology.