Repository logo
 

Decoding accelerometry for classification and prediction of critically ill patients with severe brain injury.

cam.issuedOnline2021-12-08
dc.contributor.authorBhattacharyay, Shubhayu
dc.contributor.authorRattray, John
dc.contributor.authorWang, Matthew
dc.contributor.authorDziedzic, Peter H
dc.contributor.authorCalvillo, Eusebia
dc.contributor.authorKim, Han B
dc.contributor.authorJoshi, Eshan
dc.contributor.authorKudela, Pawel
dc.contributor.authorEtienne-Cummings, Ralph
dc.contributor.authorStevens, Robert D
dc.contributor.orcidBhattacharyay, Shubhayu [0000-0001-7428-5588]
dc.date.accessioned2022-01-28T14:41:46Z
dc.date.available2022-01-28T14:41:46Z
dc.date.issued2021-12-08
dc.date.submitted2021-05-25
dc.date.updated2022-01-28T14:41:44Z
dc.descriptionFunder: Gates Cambridge Trust; doi: http://dx.doi.org/10.13039/501100005370
dc.descriptionFunder: Office of the Provost, Johns Hopkins University; doi: http://dx.doi.org/10.13039/100012800
dc.description.abstractOur goal is to explore quantitative motor features in critically ill patients with severe brain injury (SBI). We hypothesized that computational decoding of these features would yield information on underlying neurological states and outcomes. Using wearable microsensors placed on all extremities, we recorded a median 24.1 (IQR: 22.8-25.1) hours of high-frequency accelerometry data per patient from a prospective cohort (n = 69) admitted to the ICU with SBI. Models were trained using time-, frequency-, and wavelet-domain features and levels of responsiveness and outcome as labels. The two primary tasks were detection of levels of responsiveness, assessed by motor sub-score of the Glasgow Coma Scale (GCSm), and prediction of functional outcome at discharge, measured with the Glasgow Outcome Scale-Extended (GOSE). Detection models achieved significant (AUC: 0.70 [95% CI: 0.53-0.85]) and consistent (observation windows: 12 min-9 h) discrimination of SBI patients capable of purposeful movement (GCSm > 4). Prediction models accurately discriminated patients of upper moderate disability or better (GOSE > 5) with 2-6 h of observation (AUC: 0.82 [95% CI: 0.75-0.90]). Results suggest that time series analysis of motor activity yields clinically relevant insights on underlying functional states and short-term outcomes in patients with SBI.
dc.description.sponsorshipThis work was partially supported by awards from the Johns Hopkins University Office of the Provost and the Hodson Trust, received by S.B. S.B. is currently funded by a Gates Cambridge fellowship
dc.identifier.doi10.17863/CAM.80462
dc.identifier.eissn2045-2322
dc.identifier.issn2045-2322
dc.identifier.others41598-021-02974-w
dc.identifier.other2974
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/333038
dc.languageen
dc.language.isoeng
dc.publisherSpringer Science and Business Media LLC
dc.publisher.urlhttp://dx.doi.org/10.1038/s41598-021-02974-w
dc.subjectAccelerometry
dc.subjectAged
dc.subjectBrain Injuries
dc.subjectCritical Illness
dc.subjectFemale
dc.subjectGlasgow Outcome Scale
dc.subjectHumans
dc.subjectMale
dc.subjectMiddle Aged
dc.subjectPilot Projects
dc.subjectSeverity of Illness Index
dc.titleDecoding accelerometry for classification and prediction of critically ill patients with severe brain injury.
dc.typeArticle
dcterms.dateAccepted2021-11-25
prism.issueIdentifier1
prism.publicationNameSci Rep
prism.volume11
rioxxterms.licenseref.urihttp://creativecommons.org/licenses/by/4.0/
rioxxterms.versionVoR
rioxxterms.versionofrecord10.1038/s41598-021-02974-w

Files

Original bundle
Now showing 1 - 3 of 3
Loading...
Thumbnail Image
Name:
41598_2021_Article_2974.pdf
Size:
2.35 MB
Format:
Adobe Portable Document Format
Description:
Published version
Licence
http://creativecommons.org/licenses/by/4.0/
Loading...
Thumbnail Image
Name:
41598_2021_2974_MOESM1_ESM.pdf
Size:
4.46 MB
Format:
Adobe Portable Document Format
Description:
Published version
Licence
http://creativecommons.org/licenses/by/4.0/
No Thumbnail Available
Name:
41598_2021_Article_2974_nlm.xml
Size:
164.28 KB
Format:
Extensible Markup Language
Description:
Bibliographic metadata
Licence
http://creativecommons.org/licenses/by/4.0/