Fine-tuning of language models for automated structuring of medical exam reports to improve patient screening and analysis
Abstract The analysis of medical imaging reports is labour-intensive but crucial for accurate diagnosis and effective patient screening. Often presented as unstructured text, these reports require systematic organisation for efficient interpretation. This study applies Natural Language Processing (N...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-05695-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849769382040829952 |
|---|---|
| author | Luis B. Elvas Rafaela Santos João C. Ferreira |
| author_facet | Luis B. Elvas Rafaela Santos João C. Ferreira |
| author_sort | Luis B. Elvas |
| collection | DOAJ |
| description | Abstract The analysis of medical imaging reports is labour-intensive but crucial for accurate diagnosis and effective patient screening. Often presented as unstructured text, these reports require systematic organisation for efficient interpretation. This study applies Natural Language Processing (NLP) techniques tailored for European Portuguese to automate the analysis of cardiology reports, streamlining patient screening. Using a methodology involving tokenization, part-of-speech tagging and manual annotation, the MediAlbertina PT-PT language model was fine-tuned, achieving 96.13% accuracy in entity recognition. The system enables rapid identification of conditions such as aortic stenosis through an interactive interface, substantially reducing the time and effort required for manual review. It also facilitates patient monitoring and disease quantification, optimising healthcare resource allocation. This research highlights the potential of NLP tools in Portuguese healthcare contexts, demonstrating their applicability to medical report analysis and their broader relevance in improving efficiency and decision-making in diverse clinical environments. |
| format | Article |
| id | doaj-art-b24d4fe91e674ec0b6e4ee3bcd4f7f74 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-b24d4fe91e674ec0b6e4ee3bcd4f7f742025-08-20T03:03:25ZengNature PortfolioScientific Reports2045-23222025-07-0115113010.1038/s41598-025-05695-6Fine-tuning of language models for automated structuring of medical exam reports to improve patient screening and analysisLuis B. Elvas0Rafaela Santos1João C. Ferreira2Department of Logistics, Molde, University CollegeISTAR, Instituto Universitário de Lisboa (ISCTE-IUL)Department of Logistics, Molde, University CollegeAbstract The analysis of medical imaging reports is labour-intensive but crucial for accurate diagnosis and effective patient screening. Often presented as unstructured text, these reports require systematic organisation for efficient interpretation. This study applies Natural Language Processing (NLP) techniques tailored for European Portuguese to automate the analysis of cardiology reports, streamlining patient screening. Using a methodology involving tokenization, part-of-speech tagging and manual annotation, the MediAlbertina PT-PT language model was fine-tuned, achieving 96.13% accuracy in entity recognition. The system enables rapid identification of conditions such as aortic stenosis through an interactive interface, substantially reducing the time and effort required for manual review. It also facilitates patient monitoring and disease quantification, optimising healthcare resource allocation. This research highlights the potential of NLP tools in Portuguese healthcare contexts, demonstrating their applicability to medical report analysis and their broader relevance in improving efficiency and decision-making in diverse clinical environments.https://doi.org/10.1038/s41598-025-05695-6Natural Language processing (NLP)Data miningLanguage modelsHealthcareNamed entity recognition (NER) |
| spellingShingle | Luis B. Elvas Rafaela Santos João C. Ferreira Fine-tuning of language models for automated structuring of medical exam reports to improve patient screening and analysis Scientific Reports Natural Language processing (NLP) Data mining Language models Healthcare Named entity recognition (NER) |
| title | Fine-tuning of language models for automated structuring of medical exam reports to improve patient screening and analysis |
| title_full | Fine-tuning of language models for automated structuring of medical exam reports to improve patient screening and analysis |
| title_fullStr | Fine-tuning of language models for automated structuring of medical exam reports to improve patient screening and analysis |
| title_full_unstemmed | Fine-tuning of language models for automated structuring of medical exam reports to improve patient screening and analysis |
| title_short | Fine-tuning of language models for automated structuring of medical exam reports to improve patient screening and analysis |
| title_sort | fine tuning of language models for automated structuring of medical exam reports to improve patient screening and analysis |
| topic | Natural Language processing (NLP) Data mining Language models Healthcare Named entity recognition (NER) |
| url | https://doi.org/10.1038/s41598-025-05695-6 |
| work_keys_str_mv | AT luisbelvas finetuningoflanguagemodelsforautomatedstructuringofmedicalexamreportstoimprovepatientscreeningandanalysis AT rafaelasantos finetuningoflanguagemodelsforautomatedstructuringofmedicalexamreportstoimprovepatientscreeningandanalysis AT joaocferreira finetuningoflanguagemodelsforautomatedstructuringofmedicalexamreportstoimprovepatientscreeningandanalysis |