Impact Analysis of De- dentification in Clinical Notes Classification...16th Annual Conference on Health Informatics meets Digital Health (dHealth 2022), May 24–25, 2022, Vienna, Austria.
Background: Clinical notes provide valuable data in telemonitoring systems for disease management. Such data must be converted into structured information to be effective in automated analysis. One way to achieve this is by classification (e.g. into categories). However, to conform with privacy regu...
| Publicado en: | Studies in Health Technology & Informatics Vol. 293; pp. 189 - 197 |
|---|---|
| Autores principales: | , , , , , , , |
| Formato: | algorithm proceedings research tables/charts Journal Article |
| Publicado: |
Sage Publications Inc.
2022
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=157083017&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 157083017 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 09269630 U1V jtl: Studies in Health Technology & Informatics issn: 09269630 maglogo: N pubinfo: dt: 2022 vid: 293 pid: 344 pub: Sage Publications Inc. place: Thousand Oaks, California artinfo: ui: 157083017 157083017 157083017 10.3233/SHTI220368 157083017 ppf: 189 ppct: 8 formats: tig: atl: Impact Analysis of De- dentification in Clinical Notes Classification...16th Annual Conference on Health Informatics meets Digital Health (dHealth 2022), May 24–25, 2022, Vienna, Austria. aug: au: BAUMGARTNER, Martin SCHREIER, Günter HAYN, Dieter KREINER, Karl HAIDER, Lukas WIESMÜLLER, Fabian BRUNELLI, Luca PÖLZL, Gerhard affil: Austrian Institute of Technology (AIT), Graz/Vienna, Austria. sug: subj: Electronic Health Records Classification Telehealth Privacy and Confidentiality Natural Language Processing Human Congresses and Conferences Austria Austria Data Security Descriptive Statistics Text Messaging ab: Background: Clinical notes provide valuable data in telemonitoring systems for disease management. Such data must be converted into structured information to be effective in automated analysis. One way to achieve this is by classification (e.g. into categories). However, to conform with privacy regulations and concerns, text is usually de-identified. Objectives: This study investigated the effects of de-identification on classification. Methods: Two pseudonymisation and two classification algorithms were applied to clinical messages from a telehealth system. Divergence in classification compared to clear text classification was measured. Results: Overall, de-identification notably altered classification. The delicate classification algorithm was severely impacted, especially losses of sensitivity were noticeable. However, the simpler classification method was more robust and in combination with a more yielding pseudonymisation technique, had only a negligible impact on classification. Conclusion: The results indicate that deidentification can impact text classification and suggest, that considering deidentification during development of the classification methods could be beneficial. pubtype: Academic Journal doctype: algorithm proceedings research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|