Literature DB >> 34864486

Validation of open-source step-counting algorithms for wrist-worn tri-axial accelerometers in cardiovascular patients.

Riccardo Femiano1, Charlotte Werner2, Matthias Wilhelm3, Prisca Eser4.   

Abstract

BACKGROUND: Accurate quantification of daily steps in a cardiovascular patient population is of high importance for primary and secondary prevention. While sensor derived step counts have been sufficiently validated for hip-worn devices and commercial wrist-worn devices, there is a lack of knowledge on validity of freely available step counting algorithms for raw acceleration data collected at the wrist. RESEARCH QUESTION: How accurate are step-counting algorithms for wrist worn tri-axial accelerometers in a cardiac rehabilitation training setting?
METHODS: Two step counting algorithms (Windowed Peak Detection, Autocorrelation) for tri-axial accelerometers (Axivity AX-3), were tested. Steps were recorded by chest-mounted GoPro video cameras as gold standard. Cardiovascular patients without neurological impairments enrolled in an ambulatory rehabilitation program were recruited. Recordings were performed during one 45-90 min outdoor physical therapy session of which 5-min segments of six movement categories, namely Walking, Running, Nordic, Stairs, Arm Movement [AM] With [+] and Without [-] Walking [W] were identified and analyzed. Mean absolute difference and mean absolute percentage error [MAPE] with regard to true steps measured from video are reported to report accuracy.
RESULTS: Training sessions of 22 patients were recorded and analyzed. Steps were overestimated during AM-W and underestimated during Walking, Running and Stairs. Windowed Peak Detection algorithm was more accurate during AM+W and AM-W and Autocorrelation performed better during Nordic. A MAPE of close or below 10% was achieved by both algorithms for the categories: Walking, Running, Stairs and Nordic. SIGNIFICANCE: Both algorithms provided accurate results for estimation of step counts in a controlled setting of a cardiovascular patient population. The quantification of daily number of steps recorded by wrist-worn accelerometers delivering raw data analyzed by freely available algorithms is a cost-effective option for research studies.
Copyright © 2021 The Authors. Published by Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Accelerometry; Algorithm; CVD; Open-source; Step-counting

Mesh:

Year:  2021        PMID: 34864486     DOI: 10.1016/j.gaitpost.2021.11.035

Source DB:  PubMed          Journal:  Gait Posture        ISSN: 0966-6362            Impact factor:   2.840


  3 in total

1.  Association of Daily Step Count and Intensity With Incident Dementia in 78 430 Adults Living in the UK.

Authors:  Borja Del Pozo Cruz; Matthew Ahmadi; Sharon L Naismith; Emmanuel Stamatakis
Journal:  JAMA Neurol       Date:  2022-10-01       Impact factor: 29.907

2.  Objectively measured adherence to physical activity among patients with coronary artery disease: Comparison of the 2010 and 2020 World Health Organization guidelines and daily steps.

Authors:  Prisca Eser; Nathalia Gonzalez-Jaramillo; Selina Weber; Jan Fritsche; Riccardo Femiano; Charlotte Werner; Flurina Casanova; Arjola Bano; Oscar H Franco; Matthias Wilhelm
Journal:  Front Cardiovasc Med       Date:  2022-09-28

3.  Prognostic impact of physical activity patterns after percutaneous coronary intervention. Protocol for a prospective longitudinal cohort. The PIPAP study.

Authors:  Nathalia Gonzalez-Jaramillo; Prisca Eser; Flurina Casanova; Arjola Bano; Oscar H Franco; Stephan Windecker; Lorenz Räber; Matthias Wilhelm
Journal:  Front Cardiovasc Med       Date:  2022-09-30
  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.