CliniDeID, an Open Source Solution for Accurate Clinical Text De-Identification Passed
Wednesday May 24, 2023 11:05 - 11:35 Open Seminar Area
Lecturer: Stephane Meystre
Track: Open Seminar Area, MIE: Special Topic: Caring is Sharing - exploiting value in data for health and innovation
The automatic de-identification of clinical narrative text offers efficient patient data privacy protection and eases reuse of clinical data. CliniDeID applies an ensemble method combining deep and shallow machine learning with rule-based algorithms and is released as free and open-source solution to de-identify unstructured clinical text with high accuracy. It was recently evaluated with a selection of clinical text corpora and reached high sensitivity and positive predictive value.
Language
English
Seminar type
On site only
Level of knowledge
Advanced
Conference
MIE
Authors
Stéphane Meystre, Gary Underwood, Paul Heider
Lecturers
Stephane Meystre Lecturer
Scientific Director for Data Science and AI
OnePlanet & imec
Dr. Stephane Meystre is scientific director at the OnePlanet Research Center, guiding data science, AI, and data platform efforts in precision health, nutrition and behavior as well as precision agriculture, food and environment. He has a medical and biomedical informatics background, with extensive academic research and technology transfer experience in AI applications in healthcare to enable reuse of clinical data, from natural language processing applications for clinical information extraction and text de-identification, to clinical trial eligibility surveillance and predictive analytics applied to COVID-19 as examples. He has been elected fellow of the American College of Medical Informatics (FACMI), fellow of the International Academy of Health Sciences Informatics (IAHSI) and fellow of the American Medical Informatics Association (FAMIA).