2026-09-19T14:25:46Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1131692026-06-06T00:49:23Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Peter Szolovits.
Suresh, Harini(Harini S.)
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2018-01-12T21:15:15Z
2018-01-12T21:15:15Z
2017
http://hdl.handle.net/1721.1/113169
1017486257
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, June, 2017
"May 2017." Cataloged from PDF version of thesis.
Includes bibliographical references (pages 51-56).
Real-time prediction of clinical interventions remains a challenge within intensive care units (ICUs). This task is complicated by data sources that are noisy, sparse, heterogeneous and outcomes that are imbalanced. In this thesis, we integrate data from all available ICU sources (vitals, labs, notes, demographics) and focus on learning rich representations of this data to predict onset and weaning of multiple invasive interventions. We first investigate the ability of both deep and sequence autoencoders to effectively learn low-dimensional and dense underlying patient states in an unsupervised way. In addition, we compare these representations along with both long short-term memory networks (LSTM) and convolutional neural networks (CNN) for prediction of five intervention tasks: invasive ventilation, non-invasive ventilation, vasopressors, colloid boluses, and crystalloid boluses. Our predictions are done in a forward-facing manner to enable "real-time" performance, and predictions are made with a six hour gap time to support clinically actionable planning. We achieve state-of- the-art results on our predictive tasks using deep architectures. We explore the use of feature occlusion to interpret LSTM models, and compare this to the inter-pretability gained from examining inputs that maximally activate CNN outputs. We show that our models are able to significantly outperform baselines in intervention prediction, as well as provide insight into model learning, which is crucial for the adoption of such models in practice.
by Harini Suresh.
M.Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
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.
Clinical event prediction and understanding with deep neural networks
Thesis
application/pdf
2019-06-17T20:35:56Z
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="424dfefb-2c59-4137-a3bc-75d7ed0dcde7">
<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>Clinical event prediction and understanding with deep neural networks</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2017</PublicationDate>
<Authors>
<Author>
<DisplayName>Suresh, Harini(Harini S.)</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>Real-time prediction of clinical interventions remains a challenge within intensive care units (ICUs). This task is complicated by data sources that are noisy, sparse, heterogeneous and outcomes that are imbalanced. In this thesis, we integrate data from all available ICU sources (vitals, labs, notes, demographics) and focus on learning rich representations of this data to predict onset and weaning of multiple invasive interventions. We first investigate the ability of both deep and sequence autoencoders to effectively learn low-dimensional and dense underlying patient states in an unsupervised way. In addition, we compare these representations along with both long short-term memory networks (LSTM) and convolutional neural networks (CNN) for prediction of five intervention tasks: invasive ventilation, non-invasive ventilation, vasopressors, colloid boluses, and crystalloid boluses. Our predictions are done in a forward-facing manner to enable "real-time" performance, and predictions are made with a six hour gap time to support clinically actionable planning. We achieve state-of- the-art results on our predictive tasks using deep architectures. We explore the use of feature occlusion to interpret LSTM models, and compare this to the inter-pretability gained from examining inputs that maximally activate CNN outputs. We show that our models are able to significantly outperform baselines in intervention prediction, as well as provide insight into model learning, which is crucial for the adoption of such models in practice.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>