Artificial Intelligence Integration in Radiation Therapy Education: A Multi-Modal Approach.

Area of Science:

• Medical Education
• Radiation Oncology
• Artificial Intelligence

Background:

• Radiation oncology faces critical workforce shortages, necessitating expansion of radiation therapy (RT) student cohorts.
• Scaling educational delivery while maintaining quality is a key challenge in training competent clinicians.
• Artificial Intelligence (AI) offers potential solutions for medical education, but its application in RT education requires further investigation.

Purpose of the Study:

• To evaluate the effectiveness and student perceptions of three AI educational innovations within a radiation therapy (RT) degree program.
• To assess the impact of AI-driven video lectures, AI-assisted feedback, and AI-simulated communication tasks on student learning.

Main Methods:

• A cross-sectional study surveyed 62 RT students across Years 1, 2, and 3.
• Three AI innovations were integrated into the curriculum: AI video lectures, AI-assisted assessment feedback, and AI-simulated communication tasks.
• Quantitative survey data and qualitative open-ended responses were analyzed.

Main Results:

• Year 1 students (73%) were satisfied with AI video lectures.
• Year 2 students showed mixed responses regarding AI feedback for assessments (54% in favor, 46% hesitant).
• Year 3 students (75%) preferred practicing with AI patients over peers.

Conclusions:

• AI integration in RT education yielded varied but generally positive student outcomes across different year levels.
• Students perceived AI tools favorably, particularly for formative learning experiences.
• A preference emerged for AI in supporting learning rather than for high-stakes assessments.