Show simple item record

dc.contributor.authorDai, Yang
dc.contributor.authorLokhandwala, Sharukh
dc.contributor.authorLong, William J
dc.contributor.authorMark, Roger G
dc.contributor.authorLehman, Li-Wei
dc.date.accessioned2017-12-19T18:43:15Z
dc.date.available2017-12-19T18:43:15Z
dc.date.issued2017-04
dc.date.submitted2017-02
dc.identifier.isbn978-1-5090-4179-4
dc.identifier.urihttp://hdl.handle.net/1721.1/112808
dc.description.abstractAmong critically-ill patients, hypotension represents a failure in compensatory mechanisms and may lead to organ hypoperfusion and failure. In this work, we adopt a datadriven approach for phenotype discovery and visualization of patient similarity and cohort structure in the intensive care unit (ICU). We used Hierarchical Dirichlet Process (HDP) as a non-parametric topic modeling technique to automatically learn a d-dimensional feature representation of patients that captures the latent 'topic' structure of diseases, symptoms, medications, and findings documented in hospital discharge summaries. We then used the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm to convert the d-dimensional latent structure learned from HDP into a matrix of pairwise similarities for visualizing patient similarity and cohort structure. Using discharge summaries of a large patient cohort from the MIMIC II database, we evaluated the clinical utility of the discovered topic structure in phenotyping critically-ill patients who experienced hypotensive episodes. Our results indicate that the approach is able to reveal clinically interpretable clustering structure within our cohort and may potentially provide valuable insights to better understand the association between disease phenotypes and outcomes.en_US
dc.description.sponsorshipNational Institutes of Health (U.S.) (Grant R01-EB017205)en_US
dc.description.sponsorshipNational Institutes of Health (U.S.) (Grant R01-EB001659)en_US
dc.description.sponsorshipNational Institutes of Health (U.S.) (Grant R01GM104987)en_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/BHI.2017.7897290en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourcePMCen_US
dc.titlePhenotyping hypotensive patients in critical care using hospital discharge summariesen_US
dc.typeArticleen_US
dc.identifier.citationDai, Yang, et al. “Phenotyping Hypotensive Patients in Critical Care Using Hospital Discharge Summaries.” 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), February 16-19 2017, Orlando, Florida, USA, Institute of Electrical and Electronics Engineers (IEEE), April 2017 © 2017 Institute of Electrical and Electronics Engineers (IEEE)en_US
dc.contributor.departmentInstitute for Medical Engineering and Scienceen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.mitauthorDai, Yang
dc.contributor.mitauthorLokhandwala, Sharukh
dc.contributor.mitauthorLong, William J
dc.contributor.mitauthorMark, Roger G
dc.contributor.mitauthorLehman, Li-Wei
dc.relation.journal2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI)en_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dc.date.updated2017-12-19T14:03:46Z
dspace.orderedauthorsDai, Yang; Lokhandwala, Sharukh; Long, William; Mark, Roger; Lehman, Li-wei H.en_US
dspace.embargo.termsNen_US
dc.identifier.orcidhttps://orcid.org/0000-0002-2573-388X
dc.identifier.orcidhttps://orcid.org/0000-0002-7749-1034
dc.identifier.orcidhttps://orcid.org/0000-0002-6318-2978
mit.licenseOPEN_ACCESS_POLICYen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record