Show simple item record

dc.contributor.authorFiorini, Samuele
dc.contributor.authorHajati, Farshid
dc.contributor.authorBarla, Annalisa
dc.contributor.authorGirosi, Federico
dc.date.accessioned2020-01-19T23:25:37Z
dc.date.available2020-01-19T23:25:37Z
dc.date.issued2019
dc.identifier.issn1932-6203
dc.identifier.doi10.1371/journal.pone.0211844
dc.identifier.urihttp://hdl.handle.net/10072/390600
dc.description.abstractIntroduction: The first line of treatment for people with Diabetes mellitus is metformin. However, over the course of the disease metformin may fail to achieve appropriate glycemic control, and a second-line therapy may become necessary. In this paper we introduce Tangle, a time span-guided neural attention model that can accurately and timely predict the upcoming need for a second-line diabetes therapy from administrative data in the Australian adult population. The method is suitable for designing automatic therapy review recommendations for patients and their providers without the need to collect clinical measures. Data: We analyzed seven years of de-identified records (2008-2014) of the 10% publicly available linked sample of Medicare Benefits Schedule (MBS) and Pharmaceutical Benefits Scheme (PBS) electronic databases of Australia. Methods: By design, Tangle inherits the representational power of pre-trained word embedding, such as GloVe, to encode sequences of claims with the related MBS codes. Moreover, the proposed attention mechanism natively exploits the information hidden in the time span between two successive claims (measured in number of days). We compared the proposed method against state-of-the-art sequence classification methods. Results: Tangle outperforms state-of-the-art recurrent neural networks, including attention-based models. In particular, when the proposed time span-guided attention strategy is coupled with pre-trained embedding methods, the model performance reaches an Area Under the ROC Curve of 90%, an improvement of almost 10 percentage points over an attentionless recurrent architecture. Implementation: Tangle is implemented in Python using Keras and it is hosted on GitHub at https://github.com/samuelefiorini/tangle.
dc.description.peerreviewedYes
dc.languageEnglish
dc.publisherPublic Library of Science (PLoS)
dc.relation.ispartofpagefrome0211844
dc.relation.ispartofissue10
dc.relation.ispartofjournalPLoS One
dc.relation.ispartofvolume14
dc.subject.fieldofresearchArtificial Intelligence and Image Processing
dc.subject.fieldofresearchcode0801
dc.titlePredicting diabetes second-line therapy initiation in the Australian population via time span-guided neural attention network
dc.typeJournal article
dc.type.descriptionC1 - Articles
dcterms.bibliographicCitationFiorini, S; Hajati, F; Barla, A; Girosi, F, Predicting diabetes second-line therapy initiation in the Australian population via time span-guided neural attention network., PLoS One, 2019, 14 (10), pp. e0211844-
dcterms.dateAccepted2019-09-18
dcterms.licensehttp://creativecommons.org/licenses/by/4.0/
dc.date.updated2020-01-19T23:22:54Z
dc.description.versionPublished
gro.rights.copyright© 2019 Fiorini et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
gro.hasfulltextFull Text
gro.griffith.authorHajati, Farshid


Files in this item

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record