DEDUCE: A pattern matching method for automatic de-identification of Dutch medical text

V. Menger; F.E. Scheepers; L.M. van Wijk; M. Spruit

doi:10.1016/j.tele.2017.08.002

DEDUCE: A pattern matching method for automatic de-identification of Dutch medical text

V. Menger, F.E. Scheepers, L.M. van Wijk, M. Spruit

Sub Organization and Information

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

In order to use medical text for research purposes, it is necessary to de-identify the text for legal and privacy reasons. We report on a pattern matching method to automatically de-identify medical text written in Dutch, which requires a low amount of effort to be hand tailored. First, a selection of Protected Health Information (PHI) categories is determined in cooperation with medical staff. Then, we devise a method for de-identifying all information in one of these PHI categories, that relies on lookup tables, decision rules and fuzzy string matching. Our de-identification method DEDUCE is validated on a test corpus of 200 nursing notes and 200 treatment plans obtained from the University Medical Center Utrecht (UMCU) in the Netherlands, achieving a total micro-averaged precision of 0.814, a recall of 0.916 and a F1-score of 0.862. For person names, a recall of 0.964 was achieved, while no names of patients were missed.

Original language	English
Pages (from-to)	727-736
Journal	Telematics and Informatics
Volume	35
Issue number	4
DOIs	https://doi.org/10.1016/j.tele.2017.08.002
Publication status	Published - Jul 2018

Keywords

De-identification
Dutch medical text
Pattern matching
Protected Health Information
Patient privacy

Access to Document

10.1016/j.tele.2017.08.002

DEDUCEFinal published version, 293 KBLicence: Taverne

Cite this

@article{9e3cc5a11601449688ea68f7dc27348c,

title = "DEDUCE: A pattern matching method for automatic de-identification of Dutch medical text",

abstract = "In order to use medical text for research purposes, it is necessary to de-identify the text for legal and privacy reasons. We report on a pattern matching method to automatically de-identify medical text written in Dutch, which requires a low amount of effort to be hand tailored. First, a selection of Protected Health Information (PHI) categories is determined in cooperation with medical staff. Then, we devise a method for de-identifying all information in one of these PHI categories, that relies on lookup tables, decision rules and fuzzy string matching. Our de-identification method DEDUCE is validated on a test corpus of 200 nursing notes and 200 treatment plans obtained from the University Medical Center Utrecht (UMCU) in the Netherlands, achieving a total micro-averaged precision of 0.814, a recall of 0.916 and a F1-score of 0.862. For person names, a recall of 0.964 was achieved, while no names of patients were missed.",

keywords = "De-identification, Dutch medical text, Pattern matching, Protected Health Information, Patient privacy",

author = "V. Menger and F.E. Scheepers and {van Wijk}, L.M. and M. Spruit",

year = "2018",

month = jul,

doi = "10.1016/j.tele.2017.08.002",

language = "English",

volume = "35",

pages = "727--736",

journal = "Telematics and Informatics",

issn = "0736-5853",

publisher = "Elsevier",

number = "4",

}

TY - JOUR

T1 - DEDUCE: A pattern matching method for automatic de-identification of Dutch medical text

AU - Menger, V.

AU - Scheepers, F.E.

AU - van Wijk, L.M.

AU - Spruit, M.

PY - 2018/7

Y1 - 2018/7

N2 - In order to use medical text for research purposes, it is necessary to de-identify the text for legal and privacy reasons. We report on a pattern matching method to automatically de-identify medical text written in Dutch, which requires a low amount of effort to be hand tailored. First, a selection of Protected Health Information (PHI) categories is determined in cooperation with medical staff. Then, we devise a method for de-identifying all information in one of these PHI categories, that relies on lookup tables, decision rules and fuzzy string matching. Our de-identification method DEDUCE is validated on a test corpus of 200 nursing notes and 200 treatment plans obtained from the University Medical Center Utrecht (UMCU) in the Netherlands, achieving a total micro-averaged precision of 0.814, a recall of 0.916 and a F1-score of 0.862. For person names, a recall of 0.964 was achieved, while no names of patients were missed.

AB - In order to use medical text for research purposes, it is necessary to de-identify the text for legal and privacy reasons. We report on a pattern matching method to automatically de-identify medical text written in Dutch, which requires a low amount of effort to be hand tailored. First, a selection of Protected Health Information (PHI) categories is determined in cooperation with medical staff. Then, we devise a method for de-identifying all information in one of these PHI categories, that relies on lookup tables, decision rules and fuzzy string matching. Our de-identification method DEDUCE is validated on a test corpus of 200 nursing notes and 200 treatment plans obtained from the University Medical Center Utrecht (UMCU) in the Netherlands, achieving a total micro-averaged precision of 0.814, a recall of 0.916 and a F1-score of 0.862. For person names, a recall of 0.964 was achieved, while no names of patients were missed.

KW - De-identification

KW - Dutch medical text

KW - Pattern matching

KW - Protected Health Information

KW - Patient privacy

U2 - 10.1016/j.tele.2017.08.002

DO - 10.1016/j.tele.2017.08.002

M3 - Article

SN - 0736-5853

VL - 35

SP - 727

EP - 736

JO - Telematics and Informatics

JF - Telematics and Informatics

IS - 4

ER -

DEDUCE: A pattern matching method for automatic de-identification of Dutch medical text

Abstract

Keywords

Access to Document

Fingerprint

Cite this