Large language model–based simplification of breast imaging reports: a prospective multicentre study with 2965 patient-based evaluations
Abstract
Objective: To compare patient perceptions of radiologist-written and artificial intelligence (AI)-generated simplifications of breast imaging reports in terms of simplicity, comprehensibility, empathy, and overall preference.
Materials and methods: In this prospective multicentre survey-based study, 10 anonymized breast imaging reports (5 ultrasound, 5 mammography; one BI-RADS category 1–5 per modality) were simplified by ChatGPT-4 within a 50-word limit. After assessment by a panel of 20 physicians, paired radiologist-written and AI-generated reports were evaluated by 314 patients (2965 evaluations) who rated simplicity, comprehensibility, and empathy on a 5-point Likert scale and indicated their preferred report. The origin of each report was concealed, and each pair was presented in randomized order. Univariable and multivariable mixed-effects logistic regression analyses were performed to identify factors associated with preferring AI-generated reports.
Results: AI-generated reports were preferred in 63.3% (1876/2965) of evaluations. High simplicity and comprehensibility scores (4–5) were more frequently assigned to AI reports than to radiologist-written reports (70.0% vs 43.4% and 68.1% vs 40.4%, respectively). In multivariable analysis, higher comprehensibility was the strongest predictor in both directions: higher comprehensibility of AI-generated reports increased the odds of preferring AI (score 4: adjusted OR 1.87, 95% CI 1.08–3.23, p = 0.025), while higher comprehensibility of radiologist-written reports reduced them (score 4: adjusted OR 0.45, 95% CI 0.29–0.69, p < 0.001). Preference for AI-generated reports showed a non-significant trend toward increase with educational level.
Conclusion: AI-generated breast imaging reports were preferred by most patients and perceived as clearer, supporting a complementary and supervised use of AI-generated summaries.
Key Points: Question Patients increasingly access their own radiology reports, yet standard radiologist-written reports are often difficult to understand, highlighting the need for patient-friendly alternatives.
Findings In this study, AI-generated breast imaging reports were preferred by patients in 63.3% of evaluations, with comprehensibility emerging as the strongest predictor of preference.
Critical relevance statement : AI-generated breast imaging reports were preferred by most patients and received higher ratings for simplicity and comprehensibility than radiologist-written reports, supporting a supervised and complementary use of AI-generated summaries in clinical breast imaging.
Related
- Imaging-guided shortened interpregnancy interval following myomectomy in China: protocol for a multicentre prospective randomised controlled trial
- Impression-R1 for radiological impression generation with multicenter benchmarking and prospective evaluations
- Predictability of symptom changes following hemithyroidectomy due to compression symptoms assessed by specific questionnaires: prospective multicentre study.
- Vibroacoustic lung therapy and early postoperative oxygenation after cardiac surgery: a multicentre prospective study
- Safety and efficiency of the HEART-GP strategy with point-of-care high-sensitivity troponin testing for acute chest pain in out-of-hours primary care: a prospective multicentre diagnostic accuracy study
BibTeX
@article{magni2026large,
title = {{Large language model–based simplification of breast imaging reports: a prospective multicentre study with 2965 patient-based evaluations}},
author = {Veronica Magni and Matilde Pavan and Maria Cosentino and Maurizio Cè and Andrea Cozzi and Maria Iodice and Alessandro Liguori and Marta Montesano and Sveva Mortellaro and Luca Nicosia and Mariassunta Roberta Pannarale and Filippo Pesapane and Giulia Quercioli and Giulia Querques and Gianpaolo Carrafiello and Sonia Santicchia and Serena Carriero},
journal = {Insights into Imaging},
year = {2026},
month = nov,
doi = {10.1186/s13244-026-02423-0},
url = {https://link.springer.com/article/10.1186/s13244-026-02423-0},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Large language model–based simplification of breast imaging reports: a prospective multicentre study with 2965 patient-based evaluations
AU - Veronica Magni
AU - Matilde Pavan
AU - Maria Cosentino
AU - Maurizio Cè
AU - Andrea Cozzi
AU - Maria Iodice
AU - Alessandro Liguori
AU - Marta Montesano
AU - Sveva Mortellaro
AU - Luca Nicosia
AU - Mariassunta Roberta Pannarale
AU - Filippo Pesapane
AU - Giulia Quercioli
AU - Giulia Querques
AU - Gianpaolo Carrafiello
AU - Sonia Santicchia
AU - Serena Carriero
PY - 2026
DA - 2026/11/02
JO - Insights into Imaging
DO - 10.1186/s13244-026-02423-0
UR - https://link.springer.com/article/10.1186/s13244-026-02423-0
AB - Objective: To compare patient perceptions of radiologist-written and artificial intelligence (AI)-generated simplifications of breast imaging reports in terms of simplicity, comprehensibility, empathy, and overall preference. Materials and methods: In this prospective multicentre survey-based study, 10 anonymized breast imaging reports (5 ultrasound, 5 mammography; one BI-RADS category 1–5 per modality) were simplified by ChatGPT-4 within a 50-word limit. After assessment by a panel of 20 physicians, paired radiologist-written and AI-generated reports were evaluated by 314 patients (2965 evaluations) who rated simplicity, comprehensibility, and empathy on a 5-point Likert scale and indicated their preferred report. The origin of each report was concealed, and each pair was presented in randomized order. Univariable and multivariable mixed-effects logistic regression analyses were performed to identify factors associated with preferring AI-generated reports. Results: AI-generated reports were preferred in 63.3% (1876/2965) of evaluations. High simplicity and comprehensibility scores (4–5) were more frequently assigned to AI reports than to radiologist-written reports (70.0% vs 43.4% and 68.1% vs 40.4%, respectively). In multivariable analysis, higher comprehensibility was the strongest predictor in both directions: higher comprehensibility of AI-generated reports increased the odds of preferring AI (score 4: adjusted OR 1.87, 95% CI 1.08–3.23, p = 0.025), while higher comprehensibility of radiologist-written reports reduced them (score 4: adjusted OR 0.45, 95% CI 0.29–0.69, p < 0.001). Preference for AI-generated reports showed a non-significant trend toward increase with educational level. Conclusion: AI-generated breast imaging reports were preferred by most patients and perceived as clearer, supporting a complementary and supervised use of AI-generated summaries. Key Points: Question Patients increasingly access their own radiology reports, yet standard radiologist-written reports are often difficult to understand, highlighting the need for patient-friendly alternatives. Findings In this study, AI-generated breast imaging reports were preferred by patients in 63.3% of evaluations, with comprehensibility emerging as the strongest predictor of preference. Critical relevance statement : AI-generated breast imaging reports were preferred by most patients and received higher ratings for simplicity and comprehensibility than radiologist-written reports, supporting a supervised and complementary use of AI-generated summaries in clinical breast imaging.
SN - 1869-4101
ER -