1. Developing and validating an accelerometer-based algorithm with machine learning to classify physical activity after acquired brain injury
- Author
-
Rikke Gade, Helene Honoré, Inger Mechlenburg, and Jørgen Feldbæk Nielsen
- Subjects
030506 rehabilitation ,Monitoring ,Computer science ,Monitoring, Ambulatory [E01.370.520.500) ,Neuroscience (miscellaneous) ,Physical activity ,Accelerometer ,Machine learning ,computer.software_genre ,Algorithms [G17.035] ,Machine Learning ,03 medical and health sciences ,0302 clinical medicine ,Accelerometry ,Developmental and Educational Psychology ,medicine ,Validation Study [V03.950] ,Ambulatory [E01.370.520.500) ,Humans ,Exercise ,Acquired brain injury ,Home environment ,business.industry ,medicine.disease ,Brain Injuries [C10.228.140.199] ,Brain Injuries ,Neurology (clinical) ,Artificial intelligence ,0305 other medical science ,business ,Neurological Rehabilitation [E02.760.169.063.500.477] ,computer ,Algorithm ,Algorithms ,030217 neurology & neurosurgery - Abstract
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.
- Published
- 2021
- Full Text
- View/download PDF