Automated De-Identification of Free-Text Medical Records

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Applying deep neural networks to unstructured text notes in electronic medical records for phenotyping youth depression (2017, methodology): “22 We customised De-id for our purposes to include a larger set of proper nouns including names and regional institutional names for more optimal deidentification.”
MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports (2019, methodology): “The free-text report was then de-identified using a rule-based approach based upon prior work 12–14 .”
MIMIC-IV, a freely accessible electronic health record dataset (2023, methodology): “Finally, we combined two published algorithms for removing PHI from free-text 17,18 .”
Learning a Health Knowledge Graph from Electronic Medical Records (2017, methodology): “Free text fields were de-identified using PhysioNet’s deid software package 25, 26 .”