Use of Open-Source Large Language Models for Automatic Synthesis of the Entire Imaging Medical Records of Patients: A Feasibility Study
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.
Authors
- Stefania Rizzo (ORCID: https://orcid.org/0000-0002-5151-0866)
- Simone Schiaffino (ORCID: https://orcid.org/0000-0003-4243-888X)
- Filippo Del Grande (ORCID: https://orcid.org/0000-0003-1106-5830)
- Ermidio Rezzonico (ORCID: https://orcid.org/0009-0005-4403-1989)
- Francesco Magoga (ORCID: https://orcid.org/0000-0002-7264-1072)
- Vittorio Ferrari (ORCID: https://orcid.org/0000-0002-1942-233X)
- Fabio Mattiussi (ORCID: https://orcid.org/0009-0006-6432-6722)
Institutions
- Ente Ospedaliero Cantonale (CH)
- Fondazione Audiologica Varese (IT)
- Istituto Imaging della Svizzera Italiana
- Università della Svizzera italiana (CH)
Publication Details
- Journal
- Tomography
- Published
- 2025-04-16
- DOI
- https://doi.org/10.3390/tomography11040047
- Citations
- 1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.65