Change search
ReferencesLink to record
Permanent link

Direct link
Applying deep learning on electronic health records in Swedish to predict healthcare-associated infections
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
2016 (English)In: Workshop on Biomedical Natural Language Processing, Association for Computational Linguistics , 2016Conference paper (Refereed)
Abstract [en]

Detecting healthcare-associated infections pose a major challenge in healthcare. Us- ing natural language processing and ma- chine learning applied on electronic pa- tient records is one approach that has been shown to work. However the results indi- cate that there was room for improvement and therefore we have applied deep learn- ing methods. Specifically we implemented a network of stacked sparse auto encoders and a network of stacked restricted Boltz- mann machines. Our best results were ob- tained using the stacked restricted Boltz- mann machines with a precision of 0.79 and a recall of 0.88.

Place, publisher, year, edition, pages
Association for Computational Linguistics , 2016.
National Category
Information Systems
Research subject
Computer and Systems Sciences
Identifiers
URN: urn:nbn:se:su:diva-136578OAI: oai:DiVA.org:su-136578DiVA: diva2:1055442
Available from: 2016-12-12 Created: 2016-12-12

Open Access in DiVA

No full text

By organisation
Department of Computer and Systems Sciences
Information Systems

Search outside of DiVA

GoogleGoogle Scholar

Total: 5 hits
ReferencesLink to record
Permanent link

Direct link