Show simple item record

dc.contributor.author
Züger, Thomas
dc.contributor.author
Lehmann, Vera
dc.contributor.author
Kraus, Mathias
dc.contributor.author
Feuerriegel, Stefan
dc.contributor.author
Kowatsch, Tobias
dc.contributor.author
Wortmann, Felix
dc.contributor.author
Laimer, Markus
dc.contributor.author
Fleisch, Elgar
dc.contributor.author
Stettler, Christoph
dc.date.accessioned
2019-10-07T05:49:49Z
dc.date.available
2019-10-05T10:08:14Z
dc.date.available
2019-10-07T05:49:49Z
dc.date.issued
2019-11-14
dc.identifier.uri
http://hdl.handle.net/20.500.11850/368538
dc.identifier.doi
10.3929/ethz-b-000368538
dc.description.abstract
Background/Introduction: Despite ongoing developments in the treatment of diabetes, hypoglycaemia remains one of the most relevant acute complications associated with this disease. During hypoglycaemia cognitive, executive and psychomotor abilities significantly deteriorate. Accordingly, hypoglycaemia has consistently been shown to be associated with an increased risk of driving accidents and is, therefore, regarded as one of the relevant factors in traffic safety. Today’s cars continuously gather a broad spectrum of real-time information on various driving parameters. This may allow for an alternative approach to the problem of hypoglycaemia during driving. Using artificial intelligence constantly analyzing driving behavior it may be possible to timely detect changes in driving pattern characteristic for driving in hypoglycaemia. Based on these alterations in driving variables we aim at establishing algorithms capable of discriminating eu- and hypoglycemic driving patterns using artificial intelligence. Methods: In a proof of principle study we compared data regrading driving behavior of 5 individuals (3 non- diabetic and 2 with type 1 diabetes) tracking measurements in eu- and hypoglycemic condition while driving on a predefined route using a professional driving simulator (Carnetsoft BV). Over 60 driving parameters were assessed at a sampling rate of 30 Hz. Time series of car-based sensor data was then sliced into 5 minute windows and random forest machine learning classifier as well as deep neural networks were applied to build a system detecting hypoglycemia within 5 minute frames. Results: Car-based data provided 73'970 measurements in hypoglycemic condition (<3.9mmol/L) and 110'959 samples in euglycemic condition (4.0-10mmol/L). A simple linear logit model was used for reasons of interpretability, which confirmed statistical significance of key variables (e.g. “velocity” and “steering speed”) at the 1% level. 1-fold cross-validation on subject level (i.e. training the model on all subjects except for one, which is used for testing and repeat this until every subject has been in the testing set) using random forest from machine-learning and deep neural networks, applied because of the highly non-linear relationship resulted in a ROC-AUC in hypoglycemia prediction of 0.72 and 0.74, respectively. Conclusion: Our preliminary evaluation applying machine learning models on driving simulator based data show between-subject predictability of hypogylcemia even in a small dataset. This confirms the effectiveness of artificial intelligence in hypoglycemia detection while driving and may represent a promising novel approach to increase traffic safety in patients suffering from diabetes.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.title
HEADWIND: Design and Evaluation of a Vehicle Hypoglycemia Warning System in Diabetes - a proof of principle study
en_US
dc.type
Other Conference Item
dc.rights.license
In Copyright - Non-Commercial Use Permitted
ethz.pages.start
48
en_US
ethz.size
1 p.
en_US
ethz.version.deposit
acceptedVersion
en_US
ethz.event
Swiss Society of Endocrinology and Diabetology Annual Meeting (SGED 2019)
en_US
ethz.event.location
Bern, Switzerland
en_US
ethz.event.date
November, 14-15, 2019
en_US
ethz.grant
Design and Evaluation of a Vehicle Hypoaglycemia Warning System in Diabetes (HEADWIND Project)
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02120 - Dep. Management, Technologie und Ökon. / Dep. of Management, Technology, and Ec.::03681 - Fleisch, Elgar / Fleisch, Elgar
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02120 - Dep. Management, Technologie und Ökon. / Dep. of Management, Technology, and Ec.::09623 - Feuerriegel, Stefan (ehemalig) / Feuerriegel, Stefan (former)
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02120 - Dep. Management, Technologie und Ökon. / Dep. of Management, Technology, and Ec.::03681 - Fleisch, Elgar / Fleisch, Elgar
en_US
ethz.grant.agreementno
183569
ethz.grant.fundername
SNF
ethz.grant.funderDoi
10.13039/501100001711
ethz.grant.program
Sinergia
ethz.date.deposited
2019-10-05T10:08:22Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2019-10-07T05:50:00Z
ethz.rosetta.lastUpdated
2022-03-28T23:46:35Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&amp;rft_val_fmt=info:ofi/fmt:kev:mtx:journal&amp;rft.atitle=HEADWIND:%20Design%20and%20Evaluation%20of%20a%20Vehicle%20Hypoglycemia%20Warning%20System%20in%20Diabetes%20-%20a%20proof%20of%20principle%20study&amp;rft.date=2019-11-14&amp;rft.spage=48&amp;rft.au=Z%C3%BCger,%20Thomas&amp;Lehmann,%20Vera&amp;Kraus,%20Mathias&amp;Feuerriegel,%20Stefan&amp;Kowatsch,%20Tobias&amp;rft.genre=unknown&amp;rft.btitle=HEADWIND:%20Design%20and%20Evaluation%20of%20a%20Vehicle%20Hypoglycemia%20Warning%20System%20in%20Diabetes%20-%20a%20proof%20of%20principle%20study
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record