De-Identifying Swedish EHR Text Using Public Resources in the General Domain

Sensitive data is normally required to develop rule-based or train machine learning-based models for de-identifying electronic health record (EHR) clinical notes; and this presents important problems for patient privacy. In this study, we add non-sensitive public datasets to EHR training data; (i) scientific medical text and (ii) Wikipedia word vectors. The data, all in Swedish, is used to train a deep learning model using recurrent neural networks. Tests on pseudonymized Swedish EHR clinical notes showed improved precision and recall from 55.62% and 80.02% with the base EHR embedding layer, to 85.01% and 87.15% when Wikipedia word vectors are added. These results suggest that non-sensitive text from the general domain can be used to train robust models for de-identifying Swedish clinical text; and this could be useful in cases where the data is both sensitive and in low-resource languages.

Yigzaw, Kassaye YitbarekNorwegian Centre for E-health Research, Norway (författare)
Budrionis, AndriusNorwegian Centre for E-health Research, Norway (författare)
Makhlysheva, AlexandraNorwegian Centre for E-health Research, Norway (författare)
Godtliebsen, FredNorwegian Centre for E-health Research, Norway; UiT - The Arctic University of Norway, Norway (författare)
Dalianis, HerculesStockholms universitet,Institutionen för data- och systemvetenskap,Norwegian Centre for E-health Research, Norway(Swepub:su)hercules (författare)
Norwegian Centre for E-health Research, NorwayNorwegian Centre for E-health Research, Norway; UiT - The Arctic University of Norway, Norway (creator_code:org_t)

Ingår i:Digital Personalized Health and MedicineAmsterdam : IOS Press, s. 148-15297816436808289781643680835

Av författaren/redakt...: Chomutare, Tarid ...; Yigzaw, Kassaye ...; Budrionis, Andri ...; Makhlysheva, Ale ...; Godtliebsen, Fre ...; Dalianis, Hercul ...

Om ämnet

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.