Use of Open-Source Large Language Models for Automatic Synthesis of the Entire Imaging Medical Records of Patients: A Feasibility Study
Tomography · 2025
DOI: 10.3390/tomography11040047 ↗Kurz gefasst
Fachartikel in der Zeitschrift Tomography, 2025. Verfasst von Fabio Mattiussi und 6 weiteren Autor:innen. Beteiligte Einrichtung: Imaging Institute of Southern Switzerland, Ente Ospedaliero Cantonale (EOC), 6900 Lugano, Switzerland. Hauptthemen laut MEDLINE: Electronic Health Records, Radiology Information Systems, Natural Language Processing, Diagnostic Imaging. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background/Objectives: Reviewing the entire history of imaging exams of a single patient’s records is an essential step in clinical practice, but it is time and resource consuming, with potential negative effects on workflow and on the quality of medical decisions. The main objective of this study was to evaluate the applicability of three open-source large language models (LLMs) for the automatic generation of concise summaries of patient’s imaging records. Secondary objectives were to assess correlations among the LLMs and to evaluate the length reduction provided by each model.
Methods
Three state-of-the-art open-source large language models were selected: Llama 3.2 11B, Mistral 7B, and Falcon 7B. Each model was given a set of radiology reports. The summaries produced by the models were evaluated by two experienced radiologists and one experienced clinical physician using standardized metrics.
Results
A variable number of radiological reports (n = 12–56) from four patients were selected and evaluated. The summaries generated by the three LLM showed a good level of accuracy compared with the information contained in the original reports, with positive ratings on both clinical relevance and ease of reference. According to the experts’ evaluations, the use of the summaries generated by LLMs could help to reduce the time spent on reviewing the previous imaging examinations performed, preserving the quality of clinical data.
Conclusions
Our results suggest that LLMs are able to generate summaries of the imaging history of patients, and these summaries could improve radiology workflow making it easier to manage large volumes of reports.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Imaging Institute of Southern Switzerland, Ente Ospedaliero Cantonale (EOC), 6900 Lugano, Switzerland.
- Facoltà di Scienze Biomediche, Università della Svizzera italiana, 6900 Lugano, Switzerland.
- Private Practice, 21100 Varese, Italy.
ORCID-Profile: Fabio Mattiussi, Francesco Magoga, Simone Schiaffino, Ermidio Rezzonico, Filippo Del Grande, Stefania Rizzo
Zitieren
APA
Mattiussi, F., Magoga, F., Schiaffino, S., Ferrari, V., Rezzonico, E., Del Grande, F., & Rizzo, S. (2025). Use of Open-Source Large Language Models for Automatic Synthesis of the Entire Imaging Medical Records of Patients: A Feasibility Study. Tomography. https://doi.org/10.3390/tomography11040047
Vancouver
Mattiussi F, Magoga F, Schiaffino S, Ferrari V, Rezzonico E, Del Grande F, et al. Use of Open-Source Large Language Models for Automatic Synthesis of the Entire Imaging Medical Records of Patients: A Feasibility Study. Tomography. 2025. doi:10.3390/tomography11040047
BibTeX
@article{Mattiussi2025,
author = {Mattiussi, Fabio and Magoga, Francesco and Schiaffino, Simone and Ferrari, Vittorio and Rezzonico, Ermidio and Del Grande, Filippo and Rizzo, Stefania},
title = {Use of Open-Source Large Language Models for Automatic Synthesis of the Entire Imaging Medical Records of Patients: A Feasibility Study},
journal = {Tomography},
year = {2025},
doi = {10.3390/tomography11040047}
}
EUVIMED