Wrist-worn accelerometry for runners: Objective quantification of training load
Stiles, VH; Pearce, M; Moore, I; et al.Langford, J; Rowlands, A
Date: 31 July 2018
Article
Journal
Medicine and Science in Sports and Exercise
Publisher
Lippincott, Williams & Wilkins
Publisher DOI
Abstract
Purpose: This study aimed to apply open-source analysis code to raw habitual physical activity data from wrist-worn monitors to: 1) objectively, unobtrusively and accurately discriminate between ‘running’ and ‘non-running’ days; and 2) develop and compare simple accelerometer-derived metrics of external training load with existing ...
Purpose: This study aimed to apply open-source analysis code to raw habitual physical activity data from wrist-worn monitors to: 1) objectively, unobtrusively and accurately discriminate between ‘running’ and ‘non-running’ days; and 2) develop and compare simple accelerometer-derived metrics of external training load with existing self-report measures.
Methods: Seven-day wrist-worn accelerometer (GENEActiv, Activinsights Ltd, Kimbolton, UK) data obtained from 35 experienced runners (age, 41.9±11.4 years; height 1.72±0.08 m; mass 68.5±9.7 kg; Body Mass Index, 23.2±2.2 kg.m2; 19 [54%] women) every other week over 9-18 weeks were date-matched with self-reported training log data. Receiver-Operating-Characteristic analyses were applied to accelerometer metrics (‘Average Acceleration’, ‘Most Active-30mins’, ‘Mins≥400mg’) to discriminate between ‘running’ and ‘non-running’ days and cross-validated (leave one out cross-validation; LOOCV). Variance explained in training log criterion metrics (Miles, Duration, Training Load) by accelerometer metrics (‘Mins≥400mg’, ‘WL(workload)400-4000mg’) was examined using linear regression with LOOCV.
Results: ‘Most Active-30mins’ and ‘Mins≥400mg’ had >94% accuracy for correctly classifying ‘running’ and ‘non-running’ days, with validation indicating robustness. Variance explained in Miles, Duration and Training Load by ‘Mins≥400mg’ (67-76%) and ‘WL400-4000mg’ (55-69%) was high, with validation indicating robustness.
Conclusion: Wrist-worn accelerometer metrics can be used to objectively, unobtrusively and accurately identify running training days in runners, reducing the need for training logs or user input in future prospective research or commercial activity tracking. The high percentage of variance explained in existing self-reported measures of training load by simple, accelerometer-derived metrics of external training load supports the future use of accelerometry for prospective, preventative and prescriptive monitoring purposes in runners.
Sport and Health Sciences
Collections of Former Colleges
Item views 0
Full item downloads 0