Automatic de-identification of textual documents in the electronic health record: a review of recent research
BMC Medical Research MethodologyPublished 2 August 2010Open access
Stéphane M. Meystre, F Jeffrey Friedlin, Brett R. South, Shuying Shen, Matthew H. Samore
Citations322
SJR quartileQ1
SJR score1.67
SNIP1.73
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A review of recent research in automated de-identification of narrative text documents from the electronic health record finds methods based on dictionaries performed better with PHI that is rarely mentioned in clinical text, but are more difficult to generalize.
Abstract
In general, methods based on dictionaries performed better with PHI that is rarely mentioned in clinical text, but are more difficult to generalize. Methods based on machine learning tend to perform better, especially with PHI that is not mentioned in the dictionaries used. Finally, the issues of anonymization, sufficient performance, and "over-scrubbing" are discussed in this publication.
Keywords
Computer ScienceDecision SciencesHealth Professions
Yearbook of Medical InformaticsExtracting Information from Textual Documents in the Electronic Health Record: A Review of Recent Research
896 Citations2008Guergana Savova, Karin Kipper-Schuler +2 more
Performance of information extraction systems with clinical text has improved since the last systematic review in 1995, but they are still rarely applied outside of the laboratory they have been developed in.
Journal of the American Medical Informatics AssociationEvaluating the State-of-the-Art in Automatic De-identification
456 Citations2007Özlem Uzuner, Yuan Luo +1 more
An overview of this de-identification challenge is provided, the data and the annotation process are described, the evaluation metrics are explained, the nature of the systems that addressed the challenge are discussed, the results of received system runs are analyzed, and directions for future research are identified.
BMC Medical Informatics and Decision MakingAutomated de-identification of free-text medical records
423 Citations2008Ishna Neamatullah, Margaret Douglass +8 more
Journal of the American Medical Informatics AssociationIdentifying Patient Smoking Status from Medical Discharge Records
359 Citations2007Özlem Uzuner, Ira Goldstein +2 more
A Natural Language Processing (NLP) challenge on automatically determining the smoking status of patients from information found in their discharge records and analysis of the results highlighted the fact that discharge summaries express smoking status using a limited number of textual features.
PubMedReplacing Personally-Identifying Information in Medical Records, the Scrub System
252 Citations1996Latanya Sweeney
A new approach to locating and replacing personally-identifying information in medical records that extends beyond straight search-and-replace procedures is defined, and techniques for minimizing risk to patient confidentiality are provided.
Journal of the American Medical Informatics AssociationRecognizing Obesity and Comorbidities in Sparse Data
232 Citations2009Özlem Uzuner
PubMedA broad-coverage natural language processing system.
232 Citations2000C Friedman
This paper describes multiple extensions of an NLP system called MedLEE, which was originally developed for the domain of radiological reports of the chest, but has subsequently been extended to mammography, discharge summaries, all of radiology, electrocardiography, echocardiography, and pathology.
American Journal of Clinical PathologyEvaluation of a Deidentification (De-Id) Software Engine to Share Pathology Reports and Clinical Documents for Research
150 Citations2004Dilip Gupta, Melissa Saul +1 more
By the end of the evaluation, the system was reliably and specifically removing safe-harbor identifiers and producing highly readable deidentified text without removing important clinical information.
Journal of the American Medical Informatics AssociationRapidly Retargetable Approaches to De-identification in Medical Records
127 Citations2007Ben Wellner, M. Huyck +7 more
This paper describes a successful approach to de-identification that was developed to participate in a recent AMIA-sponsored challenge evaluation, and developed a method for tuning the balance of recall vs. precision in the Carafe system.
Journal of the American Medical Informatics AssociationState-of-the-art Anonymization of Medical Records Using an Iterative Machine Learning Framework
119 Citations2007György Szarvas, Richárd Farkas +1 more
A de-identification model that can successfully remove personal health information (PHI) from discharge records to make them conform to the guidelines of the Health Information Portability and Accountability Act is developed.
BMC Medical Informatics and Decision MakingDevelopment and evaluation of an open source software tool for deidentification of pathology reports
111 Citations2006Bruce A. Beckwith, Rajeshwarri Mahaadevan +2 more
An open source, Health Insurance Portability and Accountability Act (HIPAA) compliant, deidentification tool tailored for pathology reports, designed a three-step process for removing potential identifiers.
Journal of the American Medical Informatics AssociationA Software Tool for Removing Patient Identifying Information from Clinical Documents
108 Citations2008F Jeffrey Friedlin, C. J. McDonald
The Medical De-identification System (MeDS), a software tool that de-identifies clinical documents, successfully de-identified a wide range of medical documents from numerous sources and creates scrubbed reports that retain their interpretability, thereby maintaining their usefulness for research.
Lecture notes in computer scienceA Multilingual Named Entity Recognition System Using Boosting and C4.5 Decision Tree Learning Algorithms
104 Citations2006György Szarvas, Richárd Farkas +1 more
A multilingual Named Entity Recognition system that uses statistical modeling techniques and a split and recombine technique to fully exploit its potentials, which makes the system extremely successful when used in combination with CoNLL modells.
PubMedMedical document anonymization with a semantic lexicon.
99 Citations2000Patrick Ruch, Robert Baud +3 more
An original system for locating and removing personally-identifying information in patient records, using natural language processing tools provided by the MEDTAG framework: a semantic lexicon specialized in medicine, and a toolkit for word-sense and morpho-syntactic tagging.
Artificial Intelligence in MedicineA de-identifier for medical discharge summaries
93 Citations2007Özlem Uzuner, Tawanda Sibanda +2 more
Archives of Pathology & Laboratory MedicineConcept-Match Medical Data Scrubbing
84 Citations2003Jules J. Berman
Computerized scrubbing can render the textual portion of a pathology report harmless for research purposes, and this article addresses the problem of data scrubbing.
Methods of Information in MedicineAssessing the Difficulty and Time Cost of De-identification in Clinical Narratives
76 Citations2006Wendell F Phillips, Shobha Phansalkar +3 more
Manual de-identification of free-text notes is tedious and time-consuming, but even simple PHI is difficult to automatically identify with the exactitude required under HIPAA.
PubMedA successful technique for removing names in pathology reports using an augmented search and replace method.
73 Citations2002S. M. Thomas, Burke W. Mamlin +2 more
A tool based on the fact that the vast majority of proper names in pathology reports occur in pairs that was easy to implement and was largely based on publicly available data sources to achieve accuracy similar to previous attempts at de-identification.
HIDE: An Integrated System for Health Information DE-identification
73 Citations2008James Gardner, Li Xiong
This paper presents a prototype system for de-identifying health information including both structured and unstructured data and deploys a conditional random fields based technique for extracting identifying attributes from unstructuring data and k-anonymization based technique from structured data while preserving maximum data utility.
PubMedIdentification of patient name references within medical documents using semantic selectional restrictions.
71 Citations2002Ricky K. Taira, Alex A. T. Bui +1 more
The proposed algorithm is based on estimating the fitness of candidate patient name references to a set of semantic selectional restrictions that place tight contextual requirements upon candidate words in the report text and are determined automatically from a manually tagged corpus of training reports.
Journal of the American Medical Informatics AssociationRepurposing the Clinical Record: Can an Existing Natural Language Processing System De-identify Clinical Notes?
46 Citations2008Frances P. Morrison, Liang Li +2 more