ClinFly: an all-in-one method to translate, de-identify, and summarize medical reports in HPO format
NAR Genomics and Bioinformatics · 2025
DOI: 10.1093/nargab/lqaf145 ↗Kurz gefasst
Fachartikel in der Zeitschrift NAR Genomics and Bioinformatics, 2025. Verfasst von Lucas W Gauthier und 12 weiteren Autor:innen. Beteiligte Einrichtung: Genetics Department, AURAGEN, Hospices Civils de Lyon, 69500 Bron, France. Hauptthemen laut MEDLINE: Software, Biological Ontologies. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Genomic medicine relies on precise phenotyping and global data sharing, particularly in the context of rare diseases. However, exchanging medical reports across language barriers remains a major challenge. Manual annotation with the Human Phenotype Ontology (HPO) is also prone to inconsistency and incompleteness, risking the loss of clinically relevant information and potential misdiagnoses. We present ClinFly, an open-source pipeline that automatically de-identifies, translates, and summarizes medical reports into HPO terms, in compliance with health-data privacy standards and FAIR principles. In a multicenter, prospective evaluation, we benchmarked ClinFly against physician annotation for de-identification and phenotypic summarization of 50 non-English medical reports. The method achieved a recall of 99% and precision of 77% for protected health information (PHI) de-identification. For HPO summarization, high-confidence predictions reached a recall of 49% and precision of 92%, improving to 78% recall when including low-confidence terms, with an average of 6.6 HPO terms captured per report. ClinFly enables efficient, automated de-identification of PHI and summarization in HPO format to support genomic medicine across language barriers.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Genetics Department, AURAGEN, Hospices Civils de Lyon, 69500 Bron, France.
- Inserm U1183, IRMB, Reference center for congenital anomalies, Clinical Genetic Unit, CHU Montpellier, Univ Montpellier, 34000 Montpellier, France.
- Institute NeuroMyoGène, Laboratoire Physiopathologie et Génétique du Neurone et du Muscle, CNRS UMR 5261-INSERM U1315, Université Claude Bernard Lyon 1, 69000 Lyon, France.
- Clinical Cytology and Genetics Department, CHU Nîmes Carémeau, Univ Montpellier, 30000 Nîmes, France.
- Department of Pediatric Neurology, CHU Montpellier, PhyMedExp, CNRS, INSERM, Univ Montpellier, 34000 Montpellier, France.
- Medical Information Department, CHU Montpellier, 34000 Montpellier, France.
ORCID-Profile: Lucas W Gauthier, Nicolas Chatron, Claire Bardel, Kevin Yauy
Zitieren
APA
Gauthier, L. W., Willems, M., Chatron, N., Cenni, C., Meyer, P., Ruault, V., Wells, C., Gernet, E., Dunoyer, C., Sabbagh, Q., Bardel, C., Genevieve, D., & Yauy, K. (2025). ClinFly: an all-in-one method to translate, de-identify, and summarize medical reports in HPO format. NAR Genomics and Bioinformatics. https://doi.org/10.1093/nargab/lqaf145
Vancouver
Gauthier LW, Willems M, Chatron N, Cenni C, Meyer P, Ruault V, et al. ClinFly: an all-in-one method to translate, de-identify, and summarize medical reports in HPO format. NAR Genomics and Bioinformatics. 2025. doi:10.1093/nargab/lqaf145
BibTeX
@article{Gauthier2025,
author = {Gauthier, Lucas W and Willems, Marjolaine and Chatron, Nicolas and Cenni, Camille and Meyer, Pierre and Ruault, Valentin and Wells, Constance and Gernet, Enody and Dunoyer, Caroline and Sabbagh, Quentin and Bardel, Claire and Genevieve, David and Yauy, Kevin},
title = {ClinFly: an all-in-one method to translate, de-identify, and summarize medical reports in HPO format},
journal = {NAR Genomics and Bioinformatics},
year = {2025},
doi = {10.1093/nargab/lqaf145}
}
EUVIMED