Decoding accelerometry for classification and prediction of critically ill patients with severe brain injury
| Autor: | Bhattacharyay, Shubhayu, Rattray, John, Wang, Matthew, Dziedzic, Peter H, Calvillo, Eusebia, Kim, Han B, Joshi, Eshan, Kudela, Pawel, Etienne-Cummings, Ralph, Stevens, Robert D |
|---|---|
| Přispěvatelé: | Bhattacharyay, Shubhayu [0000-0001-7428-5588], Apollo - University of Cambridge Repository, Kim, Han B [0000-0001-5929-8444], Joshi, Eshan [0000-0001-5786-4078], Etienne-Cummings, Ralph [0000-0003-4445-973X], Stevens, Robert D [0000-0001-5984-7837] |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Male
639/705/1042 Cerebrovascular disorders Statistical methods Critical Illness Science 692/699/375/1370 Glasgow Outcome Scale Pilot Projects Brain injuries 692/699/375/380 Severity of Illness Index Article 692/617/375/534 Accelerometry Humans Author Correction GeneralLiterature_REFERENCE(e.g. dictionaries encyclopedias glossaries) ComputingMilieux_MISCELLANEOUS 692/699/375/1345 Neurovascular disorders Aged 692/617/375/1345 Multidisciplinary Computational science Middle Aged 631/114/2415 Stroke 639/166/985 692/617/375/1370 Medicine Female 692/617/375/380 692/699/375/534 Biomedical engineering |
| Zdroj: | Scientific Reports Scientific Reports, Vol 11, Iss 1, Pp 1-17 (2021) |
| ISSN: | 2045-2322 |
| Popis: | Funder: Gates Cambridge Trust; doi: http://dx.doi.org/10.13039/501100005370 Funder: Office of the Provost, Johns Hopkins University; doi: http://dx.doi.org/10.13039/100012800 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink