Assessing feasibility and risk to translate, de-identify and summarize medical reports using deep learning

Résumé fourni par la source

Abstract Background Precision medicine requires accurate phenotyping and data sharing, particularly for rare diseases. However, sharing medical reports across language barriers is challenging. Alternatively, inconsistent and incomplete clinical summary provided by physicians using Human Phenotype Ontology (HPO) can lead to a loss of clinical information. Methods To assess feasibility and risk of using deep learning methods to translate, de-identify and summarize medical reports, we developed an open-source deep learning multi-language software in line with health data privacy. We conducted a non-inferiority clinical trial using deep learning methods to de-identify protected health information (PHI) targeting a minimum sensitivity of 90% and specificity of 75%, and summarize non-English medical reports in HPO format, aiming a sensitivity of 75% and specificity of 90%. Results From March to April 2023, we evaluated 50 non-English medical reports from 8 physicians and 12 different groups of diseases, which included neurodevelopmental disorders, congenital disorders, fetal pathology and oncology. Reports contain in median 15 PHI and 7 HPO terms. Deep learning method achieved a sensitivity of 99% and a specificity of 87% in de-identification, and a sensitivity of 78% and a specificity of 92% in summarizing medical reports, reporting an average number of 6.6 HPO terms per report, which is equivalent to the number of HPO terms provided usually by physicians in databases (6.8 in PhenoDB). Conclusions De-identification and summarization of non-English medical reports using deep learning methods reports non-inferior performance, providing insights on AI usage to facilitate precision medicine. Graphical abstract Illustration of the non-inferiority trial for de-identification and summarization of non-english medical reports and main statistical performances.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.