What question did this study set out to answer?

Evaluate whether open-weight large language models can enhance readability and understanding of radiology reports for medical laypersons compared to closed-weight models.

February 14, 2026Open Access

Simplifying radiology reports with large language models: privacy-compliant open- versus closed-weight models

Key Points

Evaluate whether open-weight large language models can enhance readability and understanding of radiology reports for medical laypersons compared to closed-weight models.
Translated 60 radiology reports into lay-friendly versions using different LLMs: GPT-4o (closed-weight), Llama-3-70b, and Mixtral-8x22B (open-weight).
Assessed readability using Flesch reading ease, reading time, word and sentence count.
Evaluated understandability with 21 medical laypeople using a 5-point Likert scale.
Employed linear mixed-effects models and H-Kruskal–Wallis test for statistical analysis.
LLM-generated reports had significantly higher Flesch reading ease scores: GPT-4o (46 ± 7), Llama-3-70b (44 ± 6), Mixtral-8x22B (44 ± 6), original reports (17 ± 13; p < 0.001).
Layperson-understandability ratings improved significantly for all LLM reports compared to originals (e.g., GPT-4o: 4.4 ± 0.1 vs. original: 1.5 ± 0.1; p < 0.001).
No significant difference in understandability between GPT-4o and Llama-3-70B (p = 0.136).
Mixtral-8x22B and Llama-3-70B had a higher error rate than GPT-4o (p = 0.005 and p = 0.025 respectively).
Imaging modality did not affect understandability (all p > 0.05).

Abstract

Abstract Objectives Large language models (LLMs) like generative pre-trained transformer (GPT) can simplify radiology reports for medical laypersons, but privacy concerns limit their clinical applicability. This study compares closed-weight and in-hospital deployed privacy-compliant open-weight LLMs in generating patient-friendly radiology reports. Materials and methods A total of 60 radiology reports containing indication and impression sections (15 each from X-ray, ultrasound, CT, and MRI) were translated into lay-friendly versions using different LLMs: one commercial closed-weight model (GPT-4o) and two in-hospital deployed open-weight models (Llama-3-70b, Mixtral-8x22B). All reports were evaluated for readability (Flesch reading ease, reading time, word and sentence count). 21 medical laypeople assessed understandability using a 5-point Likert scale. Linear mixed-effects models and H-Kruskal–Wallis test were used for statistical analysis. Results LLM-generated reports demonstrated significantly improved readability, achieving higher Flesch reading ease scores (GPT-4o: 46 ± 7, Llama-3-70b: 44 ± 6, Mixtral-8x22B: 44 ± 6, original: 17 ± 13; p 0.05). Conclusion LLMs substantially improved layperson understanding of radiology reports. Open-weight, on-premises LLMs like Llama-3-70B show strong potential for real-world clinical use, though human oversight is still required. Key Points Question Can locally deployed open-weight large language models (LLMs) improve the readability and understandability of radiology reports for medical laypersons at a level comparable to closed-weight models? Findings LLMs significantly improved quantitative readability scores and qualitative ratings of layperson understandability; Llama-3-70B and GPT-4o showed comparable performance, and although the open-source models exhibited a higher error rate, they still performed well overall. Clinical relevance Open-weight LLMs provide a privacy-compliant way to generate a template for patient-friendly radiology reports suitable for real-world clinical use. Graphical Abstract

Bookmark

View Full Paper

Cite This Study

Proff et al. (Thu,) studied this question.

synapsesocial.com/papers/699010f22ccff479cfe574c5 https://doi.org/https://doi.org/10.1007/s00330-026-12329-6

Bookmark

View Full Paper