On-Field Deployment and Validation for Wearable Devices

Abstract

Wearable sensors are an important tool in the study of head acceleration events and head impact injuries in sporting and military activities. Recent advances in sensor technology have improved our understanding of head kinematics during on-field activities; however, proper utilization and interpretation of data from wearable devices requires careful implementation of best practices. The objective of this paper is to summarize minimum requirements and best practices for on-field deployment of wearable devices for the measurement of head acceleration events in vivo to ensure data evaluated are representative of real events and limitations are accurately defined. Best practices covered in this document include the definition of a verified head acceleration event, data windowing, video verification, advanced post-processing techniques, and on-field logistics, as determined through review of the literature and expert opinion. Careful use of best practices, with accurate acknowledgement of limitations, will allow research teams to ensure data evaluated is representative of real events, will improve the robustness of head acceleration event exposure studies, and generally improve the quality and validity of research into head impact injuries.

Keywords: Best practices; Concussion; Head acceleration events; Machine learning; On field validation; Time windowing; Video verification; Wearable devices.

Figure 1

Head acceleration events (HAEs) may be subdivided into direct (i.e., head impacts, involve primary collision with the head or helmet) and indirect (i.e., without head contact, involve primary collision to the individual’s body resulting in inertial motion of the head) HAEs.

Figure 2

Common methods to establish a final dataset of valid HAE events.