Show simple item record

dc.contributor.authorPeng, X
dc.contributor.authorLong, G
dc.contributor.authorShen, T
dc.contributor.authorWang, S
dc.contributor.authorJiang, J
dc.contributor.authorBlumenstein, M
dc.date.accessioned2020-03-23T03:23:44Z
dc.date.available2020-03-23T03:23:44Z
dc.date.issued2019
dc.identifier.isbn9781728146034
dc.identifier.issn1550-4786
dc.identifier.doi10.1109/ICDM.2019.00060
dc.identifier.urihttp://hdl.handle.net/10072/392545
dc.description.abstractIn longitudinal electronic health records (EHRs), the event records of a patient are distributed over a long period of time and the temporal relations between the events reflect sufficient domain knowledge to benefit prediction tasks such as the rate of inpatient mortality. Medical concept embedding as a feature extraction method that transforms a set of medical concepts with a specific time stamp into a vector, which will be fed into a supervised learning algorithm. The quality of the embedding significantly determines the learning performance over the medical data. In this paper, we propose a medical concept embedding method based on applying a self-attention mechanism to represent each medical concept. We propose a novel attention mechanism which captures the contextual information and temporal relationships between medical concepts. A light-weight neural net, 'Temporal Self-Attention Network (TeSAN)', is then proposed to learn medical concept embedding based solely on the proposed attention mechanism. To test the effectiveness of our proposed methods, we have conducted clustering and prediction tasks on two public EHRs datasets comparing TeSAN against five state-of-the-art embedding methods. The experimental results demonstrate that the proposed TeSAN model is superior to all the compared methods. To the best of our knowledge, this work is the first to exploit temporal self-attentive relations between medical events.
dc.description.peerreviewedYes
dc.publisherIEEE
dc.relation.ispartofconferencename2019 IEEE International Conference on Data Mining (ICDM 2019)
dc.relation.ispartofconferencetitleProceedings - IEEE International Conference on Data Mining, ICDM
dc.relation.ispartofdatefrom2019-11-08
dc.relation.ispartofdateto2019-11-11
dc.relation.ispartoflocationBeijing, China
dc.relation.ispartofpagefrom498
dc.relation.ispartofpageto507
dc.relation.ispartofvolume2019-November
dc.subject.fieldofresearchArtificial intelligence
dc.subject.fieldofresearchcode4602
dc.titleTemporal self-attention network for medical concept embedding
dc.typeConference output
dc.type.descriptionE1 - Conferences
dcterms.bibliographicCitationPeng, X; Long, G; Shen, T; Wang, S; Jiang, J; Blumenstein, M, Temporal self-attention network for medical concept embedding, Proceedings - IEEE International Conference on Data Mining, ICDM, 2019, 2019-November, pp. 498-507
dc.date.updated2020-03-23T03:19:56Z
dc.description.versionAccepted Manuscript (AM)
gro.rights.copyright© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
gro.hasfulltextFull Text
gro.griffith.authorWang, Sen
gro.griffith.authorBlumenstein, Michael M.


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record