Continuous Monitoring of Head Turns: Compliance, Kinematics, and Reliability of Wearable Sensing

Abstract

Wearable devices offer objective mobility metrics for continuous monitoring but often focus on traditional measures like step count or gait speed. Other quantitative metrics such as head kinematics may provide valuable insights into mobility, balance, and sensory integration, given the head's central role in coordinating vestibular, ocular, and postural control. Yet, basic knowledge about capturing daily living head turns, including participant compliance, algorithms, normative data, and reliability, is not yet established. This study aimed to resolve this knowledge gap by capturing head and trunk movement kinematics over a 7-day period and to establish normative data in healthy adults. Participants (n = 24) wore head-mounted sensors for an average of 16.38 hours per day (SD = 4.43), completing 5,163 (SD = 1,466) head turns daily, with 72% occurring independently of trunk motion. Head turn amplitude (M = 58.18°, SD = 4.26°) was comparable to lumbar turns, while peak velocity was higher for head turns (M = 104.49°/s, SD = 12.08°/s). By the second day, all head turn metrics achieved excellent reliability (ICC > 0.9), supporting the feasibility of multi-day monitoring. Additionally, we examined the relationship between head motion and other mobility metrics and established recommendations for implementing similar protocols for capturing future studies, including the minimum number of days required for reliable data collection. Findings from this study provide a foundation for future multi-day continuous monitoring of head kinematics in both healthy and clinical populations.

Keywords: free-living mobility; head kinematics; inertial sensors; physical activity; remote monitoring.

Fig. 1.

Overview of the data processing pipeline for extracting head and head-on-body turns from wearable sensor data. (1) Seven days of raw data are collected using IMU sensors. (2) Data are segmented into 24-hour periods (3) Preprocessing involves filtering and sensor alignment, including (3a) identifying calibration movements such as head shaking, head nodding, and jumping three times, and (3b) using large walking bouts to reorient the sensor data. (4) Turns are detected separately for head (4a) and trunk (4b) using gyroscope and accelerometer signals. (5) Head-on-body turns are identified by the diffference between head and trunk angular velocity, with thresholds (e.g., 5°/s) applied to detect significant independent head-on-body turn events.

Fig. 2.

Representative data from a single subject showing the number of head turns per hour over a 24-hour period during a full week. These data illustrate temporal variations in head turn activity within a day and across different days of the week.

Fig. 3.

The distribution of the frequency of head turns across all participants, binned by speed and amplitude, during free-living daily life.

Fig. 4.

Intraclass correlation coefficients (ICC) values for amplitude, velocity, number of head turns, step count, and head-on-body turn based on the number of days included in the average compared to a 5-day average. All measures, except amplitude, showed good reliability (ICC > 0.75) on the first day. After day two, all measures exhibited excellent reliability (ICC > 0.9) with the 5-day average.