Abstract

Our 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.

Details

Title
Decoding accelerometry for classification and prediction of critically ill patients with severe brain injury
Author
Bhattacharyay Shubhayu 1 ; Rattray, John 2 ; Wang, Matthew 3 ; Dziedzic, Peter H 4 ; Calvillo Eusebia 5 ; Kim, Han B 6 ; Joshi Eshan 3 ; Kudela Pawel 7 ; Etienne-Cummings, Ralph 2 ; Stevens, Robert D 8 

 Johns Hopkins University, Laboratory of Computational Intensive Care Medicine, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311); University of Cambridge, Department of Clinical Neurosciences, Cambridge, UK (GRID:grid.5335.0) (ISNI:0000000121885934); Johns Hopkins University, Department of Biomedical Engineering, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311); Johns Hopkins University, Department of Applied Mathematics and Statistics, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311) 
 Johns Hopkins University, Department of Electrical and Computer Engineering, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311) 
 Johns Hopkins University, Department of Biomedical Engineering, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311) 
 Johns Hopkins University, Laboratory of Computational Intensive Care Medicine, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311); Johns Hopkins University, Department of Neurology, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311) 
 Johns Hopkins University, Department of Neurology, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311) 
 Johns Hopkins University, Laboratory of Computational Intensive Care Medicine, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311); Johns Hopkins University, Department of Anesthesiology and Critical Care Medicine, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311) 
 Johns Hopkins University, Department of Neurosurgery, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311) 
 Johns Hopkins University, Laboratory of Computational Intensive Care Medicine, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311); Johns Hopkins University, Department of Neurology, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311); Johns Hopkins University, Department of Anesthesiology and Critical Care Medicine, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311); Johns Hopkins University, Department of Neurosurgery, Baltimore, USA (GRID:grid.21107.35) (ISNI:0000 0001 2171 9311) 
Publication year
2021
Publication date
2021
Publisher
Nature Publishing Group
e-ISSN
20452322
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2607919719
Copyright
© The Author(s) 2022. corrected publication 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.