Key result
An accelerometer-based machine learning algorithm accurately classified physical activities in patients with acquired brain injury, achieving a weighted sensitivity of 89.3%.
Why the study?
To develop and validate an accelerometer-based algorithm to classify physical activity in people with acquired brain injury in a laboratory setting resembling a real home environment.
Can an accelerometer-based machine learning algorithm accurately classify physical activity in patients with acquired brain injury?
Observational (n=36)
No
Can an accelerometer-based machine learning algorithm accurately classify physical activity in patients with acquired brain injury?
An accelerometer-based machine learning algorithm can accurately classify physical activities in patients with acquired brain injury in a laboratory setting.
Promising lab accuracy for activity classification in acquired brain injury; leaves open free-living validation and clinical utility.
Purpose: To develop and validate an accelerometer-based algorithm classifying physical activity in people with acquired brain injury (ABI) in a laboratory setting resembling a real home environment.Materials and methods: A development and validation study was performed. Eleven healthy participants and 25 patients with ABI performed a protocol of transfers and ambulating activities. Activity measurements were performed with accelerometers and with thermal video camera as gold standard reference. A machine learning-based algorithm classifying specific physical activities from the accelerometer data was developed and cross-validated in a training sample of 11 healthy participants. Criterion validity of the algorithm was established in 3 models classifying the same protocol of activities in people with ABI.Results: Modeled on data from 11 healthy and 15 participants with ABI, the algorithm had a good precision for classifying transfers and ambulating activities in data from 10 participants with ABI. The weighted sensitivity for all activities was 89.3% (88.3–90.4%) and the weighted positive predictive value was 89.7% (88.7–90.7%). The algorithm differentiated between lying and sitting activities.Conclusion: An algorithm to classify physical activities in populations with ABI was developed and its criterion validity established. Further testing of precision in home settings with continuous activity monitoring is warranted.
No takes yet. Share an insight, caveat, or question.
Honoré et al. (2021) conducted an observational in Acquired brain injury (n=36). Accelerometer-based machine learning algorithm vs. Thermal video camera (gold standard) was evaluated on Weighted sensitivity for classifying all physical activities (95% CI 88.3-90.4). An accelerometer-based machine learning algorithm accurately classified physical activities in patients with acquired brain injury, achieving a weighted sensitivity of 89.3%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: