In our study, we evaluated ChatGPT-4o’s ability to simplify breast imaging reports while maintaining accuracy and completeness. Radiology reports often contain complex terminology, creating barriers to patient understanding. We aimed to assess whether AI-driven simplifications could enhance clarity without introducing errors.
Our results show that AI-generated summaries maintained high factual accuracy (median score: 2/5) and completeness (2/5), with a low risk of misinterpretation (5/5). Reports classified as BI-RADS 0–2 were effectively simplified, while BI-RADS 3–6—particularly BI-RADS 3—posed greater challenges, with statistically significant differences in completeness (p = 0.001). Despite this, non-healthcare readers demonstrated good comprehension across all imaging modalities.
While AI shows promise in improving patient communication, it requires oversight, particularly for complex cases. Given its accessibility, ensuring AI reliability is essential to prevent misinformation. Moreover, regulatory constraints, such as the EU AI Act, currently limit its clinical implementation.
Our findings highlight AI’s potential as a supportive tool in radiology, fostering patient-centered care. However, human expertise remains irreplaceable. Future developments should focus on refining AI models to enhance clarity while ensuring clinical accuracy and safety.
Key points:
- AI simplifies complex breast imaging reports, enhancing patient understanding.
- Simplified reports from AI maintain accuracy, improving patient comprehension significantly.
- Implementing AI reports enhances patient engagement and communication in breast imaging.
Authors: Roberto Maroncelli, Veronica Rizzo, Marcella Pasculli, Federica Cicciarelli, Massimo Macera, Francesca Galati, Carlo Catalano & Federica Pediconi
