Search Articles

View query in Help articles search
e.g. John Smith or 0000-0001-6479-5330

Search Results (1 to 10 of 477 Results)

Download search results: CSV END BibTex RIS

Harnessing Moderate-Sized Language Models for Reliable Patient Data Deidentification in Emergency Department Records: Algorithm Development, Validation, and Implementation Study

Harnessing Moderate-Sized Language Models for Reliable Patient Data Deidentification in Emergency Department Records: Algorithm Development, Validation, and Implementation Study

Comparing the performance of our models with those documented in the literature presents challenges because our models are specifically fine-tuned to pseudonymize French-language clinical notes. Consequently, it is not feasible to apply them to the English-language databases traditionally used for benchmarking, such as i2b2 (i2b2 Tran SMART Foundation) [34], MIMIC II (Physio Net) [35], and MIMIC III (Physio Net) [36].

Océane Dorémus, Dylan Russon, Benjamin Contrand, Ariel Guerra-Adames, Marta Avalos-Fernandez, Cédric Gil-Jardiné, Emmanuel Lagarde

JMIR AI 2025;4:e57828

Download Citation: END BibTex RIS

Download PDF Download XML