DEDUCE: A pattern matching method for automatic de-identification of Dutch medical text. Issue 4 (July 2018)

• Record Type: Journal Article
• Authors: Menger, Vincent; Scheepers, Floor; van Wijk, Lisette Maria; Spruit, Marco
• Is Part Of: Telematics and informatics. Volume 35:Issue 4(2018)
• Page Start: 727
• Page End: 736
• Publication Date: 2018-07
• Subjects: De-identification -- Dutch medical text -- Pattern matching -- Protected Health Information -- Patient privacy; Telecommunication -- Periodicals; Computer networks -- Periodicals; Télécommunications -- Périodiques; Réseaux d'ordinateurs -- Périodiques; 384
• DOI: 10.1016/j.tele.2017.08.002
• Languages: English
• ISSNs: 0736-5853

Abstract

Highlights: A de-identification method for medical text written in Dutch was developed. De-identification is done using fuzzy string matching and lookup lists. Validation shows generally good results, with a total micro-averaged recall of 0.916. For person names, a recall of 0.961 was achieved, missing no patient names. 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.