Neuroanesthesia & neurocritical care
Accelerometer-derived movement features as predictive biomarkers for muscle atrophy in neurocritical care: a prospective cohort study
Authors' conclusion
Active movement, as measured with thigh-fixed accelerometers, is a key risk factor for muscle atrophy in neurocritical care patients.
Study context
- Population
- Neurocritical care patients (MINCE registry)91 accelerometer datasets
- Participants
- 53 patients
- Outcome
- Atrophy of rectus femoris muscle (RFM) relative to baseline (day 0)
- Follow-up
- Days 3, 7 and 10 after ICU admission
Methodological detailssingle-centre, observational, machine learning (generalized linear mixed model with LASSO regularization, nested cross-validation)
- Single-centre
- Observational
- Machine learning (generalized linear mixed model with LASSO regularization, nested cross-validation)
Main finding
As reported in the abstract
Predictors of RFM atrophy (12 candidate variables)
Baseline rectus femoris muscle (RFM) muscle mass, beta (95% CI - 7.9 to - 3.8)
- 5.1
Proportion of active movement (% activity), beta
1.6
95% CI 0.1 to 4.9
Model performance on unseen test set, R2 including movement features
79%
Model performance on unseen test set, R2 excluding movement features
55%
Observational data: associations, not effects.
Further findings
Change in RFM thickness · day 10
- Mean change in RFM thickness (SD 12.0)
- - 19.5%
Original publication
Accelerometer-derived movement features as predictive biomarkers for muscle atrophy in neurocritical care: a prospective cohort study. Crit Care. Published 31 August 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →