De-identification of free-text clinical notes

Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, September, 2020

Bibliographic Details
Main Author: Lin, Jing,M. Eng.Massachusetts Institute of Technology.
Other Authors: Alistair Johnson.
Format: Thesis
Language:eng
Published: Massachusetts Institute of Technology 2021
Subjects:
Online Access:https://hdl.handle.net/1721.1/129134
_version_ 1826207068451766272
author Lin, Jing,M. Eng.Massachusetts Institute of Technology.
author2 Alistair Johnson.
author_facet Alistair Johnson.
Lin, Jing,M. Eng.Massachusetts Institute of Technology.
author_sort Lin, Jing,M. Eng.Massachusetts Institute of Technology.
collection MIT
description Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, September, 2020
first_indexed 2024-09-23T13:42:58Z
format Thesis
id mit-1721.1/129134
institution Massachusetts Institute of Technology
language eng
last_indexed 2024-09-23T13:42:58Z
publishDate 2021
publisher Massachusetts Institute of Technology
record_format dspace
spelling mit-1721.1/1291342021-01-07T03:17:06Z De-identification of free-text clinical notes Lin, Jing,M. Eng.Massachusetts Institute of Technology. Alistair Johnson. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Electrical Engineering and Computer Science. Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, September, 2020 Cataloged from student-submitted PDF of thesis. Includes bibliographical references (pages 71-73). Clinical notes contain rich information that is useful in medical research and investigation. However, clinical documents often contain explicit personal information that is protected by federal laws. Researchers are required to remove these personal identifiers before publicly release the notes, a process known as de-identification. In recent years, the healthcare community has initiated several competitions to expedite the development of automated de-identification systems. Notably, models built using recurrent neural networks achieved state-of-the-art performance on the de-identification task. Since the competition, new architectures based on transformers have been developed with excellent performance on general domain natural language processing tasks. Examples include BERT and RoBERTa. In this work, we evaluated de-identification using different choices of bidirectional transformer models and classifiers. Further, we developed a hybrid system that incorporates rule-based features into the bidirectional transformer model. Our results demonstrated state-of-the-art performance with an average 98.73% binary token F1 score, a 0.45% increase from current baseline models. by Jing Lin. M. Eng. M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 2021-01-06T18:30:46Z 2021-01-06T18:30:46Z 2020 2020 Thesis https://hdl.handle.net/1721.1/129134 1227276464 eng MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided. http://dspace.mit.edu/handle/1721.1/7582 73 pages application/pdf Massachusetts Institute of Technology
spellingShingle Electrical Engineering and Computer Science.
Lin, Jing,M. Eng.Massachusetts Institute of Technology.
De-identification of free-text clinical notes
title De-identification of free-text clinical notes
title_full De-identification of free-text clinical notes
title_fullStr De-identification of free-text clinical notes
title_full_unstemmed De-identification of free-text clinical notes
title_short De-identification of free-text clinical notes
title_sort de identification of free text clinical notes
topic Electrical Engineering and Computer Science.
url https://hdl.handle.net/1721.1/129134
work_keys_str_mv AT linjingmengmassachusettsinstituteoftechnology deidentificationoffreetextclinicalnotes