2026-09-19T06:09:54Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1242582026-06-06T00:56:27Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Amar Gupta.
Oguntola, Ini(Iniokuwa A.)
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2020-03-24T15:36:45Z
2020-03-24T15:36:45Z
2019
2019
https://hdl.handle.net/1721.1/124258
1145124778
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 89-93).
This thesis presents a method of extracting deep robust representations of teleICU clinical data using Transformer networks, inspired by recent machine learning literature in language modeling. The utility of these representations is evaluated in various prediction outcome tasks, in which they were able to outperform linear and neural baselines. Also examined are the probability distributions of various patient characteristics across the learned patient representation space; where corresponding high-level spatial structure suggests potential for use as a similarity metric or in combination with other patient similarity metrics. Finally, the code for the models developed is publicly provided as a starting point for further research.
by Ini Oguntola.
M.Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
93 pages
eng
Massachusetts Institute of Technology
MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Learning deep patient representations for the teleICU
Thesis
application/pdf
2020-03-24T15:36:44Z
Publication
Master
EECS
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="fd8c786c-652f-4d58-afb1-e9374a251ad1">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Learning deep patient representations for the teleICU</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2019</PublicationDate>
<Authors>
<Author>
<DisplayName>Oguntola, Ini(Iniokuwa A.)</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>This thesis presents a method of extracting deep robust representations of teleICU clinical data using Transformer networks, inspired by recent machine learning literature in language modeling. The utility of these representations is evaluated in various prediction outcome tasks, in which they were able to outperform linear and neural baselines. Also examined are the probability distributions of various patient characteristics across the learned patient representation space; where corresponding high-level spatial structure suggests potential for use as a similarity metric or in combination with other patient similarity metrics. Finally, the code for the models developed is publicly provided as a starting point for further research.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>