Medical Information Anonymization



MEDINA (Medical Information Anonymization) is an Automatic Language Processing (NLP) tool designed to anonymize personal data contained in clinical documents written in French, in plain text format. 

In its current version, MEDINA processes information relating to the following categories (a configuration file allows you to specify the categories to be processed)  :

  • surnames and first names (without distinction between patient, family member, or member of the medical team);
  • addresses, postal codes, cities and names of hospitals;
  • ages, dates, phone, social security, serial numbers;
  • information on cardiology devices (brands and models of pacemakers).

MEDINA is available free of charge after signing a user license.

Language Coverage
French

Tool