Results showed that AI-generated translations improve patient access to complex radiological reports while maintaining factual correctness and clarity. Patient preferences varied, with most ranking ChatGPT-4o and ChatGPT-4 highest, while Google Gemini was rarely preferred. Clarity and empathy were especially valued in BI-RADS 4 and 5 reports, where patient anxiety is heightened. ChatGPT-4 was preferred for its superior clarity and emotional sensitivity, particularly when optimized prompts were used. However, translation quality varied, emphasizing the need for prompt design and oversight.

Limitations include potential selection bias, a German-speaking participant pool, and a lack of real-world clinical follow-up.

Future research should validate findings with real-world data, expand diverse patient cohorts, and refine prompt engineering for better translations. Data protection still remains a key concern.