Format

Send to

Choose Destination
Stud Health Technol Inform. 2019 Aug 21;264:283-287. doi: 10.3233/SHTI190228.

Impact of De-Identification on Clinical Text Classification Using Traditional and Deep Learning Classifiers.

Author information

1
Biomedical Informatics Center, Medical University of South Carolina, Charleston, SC, USA.
2
Department of Clinical Pharmacy and Outcome Sciences, Medical University of South Carolina, Charleston, SC, USA.
3
Department of Emergency Medicine, Medical University of South Carolina, Charleston, SC, USA.
4
Department of Computer Science, University of South Carolina, Columbia, SC, USA.

Abstract

Clinical text de-identification enables collaborative research while protecting patient privacy and confidentiality; however, concerns persist about the reduction in the utility of the de-identified text for information extraction and machine learning tasks. In the context of a deep learning experiment to detect altered mental status in emergency department provider notes, we tested several classifiers on clinical notes in their original form and on their automatically de-identified counterpart. We tested both traditional bag-of-words based machine learning models as well as word-embedding based deep learning models. We evaluated the models on 1,113 history of present illness notes. A total of 1,795 protected health information tokens were replaced in the de-identification process across all notes. The deep learning models had the best performance with accuracies of 95% on both original and de-identified notes. However, there was no significant difference in the performance of any of the models on the original vs. the de-identified notes.

KEYWORDS:

Data Anonymization; Machine Learning; Natural Language Processing

PMID:
31437930
DOI:
10.3233/SHTI190228
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for IOS Press Icon for PubMed Central
Loading ...
Support Center