Assessing Shoulder Biomechanics of Healthy Elderly Individuals During Activities of Daily Living Using Inertial Measurement Units: High Maximum Elevation Is Achievable but Rarely Used

Abstract

Current shoulder clinical range of motion (ROM) assessments (e.g., goniometric ROM) may not adequately represent shoulder function beyond controlled clinical settings. Relative inertial measurement unit (IMU) motion quantifies ROM precisely and can be used outside of clinic settings capturing "real-world" shoulder function. A novel IMU-based shoulder elevation quantification method was developed via IMUs affixed to the sternum/humerus, respectively. This system was then compared to in-laboratory motion capture (MOCAP) during prescribed motions (flexion, abduction, scaption, and internal/external rotation). MOCAP/IMU elevation were equivalent during flexion (R2 = 0.96, μError = 1.7 deg), abduction (R2 = 0.96, μError = 2.9 deg), scaption (R2 = 0.98, μError = -0.3 deg), and internal/external rotation (R2 = 0.90, μError = 0.4 deg). When combined across movements, MOCAP/IMU elevation were equal (R2 = 0.98, μError = 1.4 deg). Following validation, the IMU-based system was deployed prospectively capturing continuous shoulder elevation in 10 healthy individuals (4 M, 69 ± 20 years) without shoulder pathology for seven consecutive days (13.5 ± 2.9 h/day). Elevation was calculated continuously daily and outcome metrics included percent spent in discrete ROM (e.g., 0-5 deg and 5-10 deg), repeated maximum elevation (i.e., >10 occurrences), and maximum/average elevation. Average elevation was 40 ± 6 deg. Maximum with >10 occurrences and maximum were on average 145-150 deg and 169 ± 8 deg, respectively. Subjects spent the vast majority of the day (97%) below 90 deg of elevation, with the most time spent in the 25-30 deg range (9.7%). This study demonstrates that individuals have the ability to achieve large ROMs but do not frequently do so. These results are consistent with the previously established lab-based measures. Moreover, they further inform how healthy individuals utilize their shoulders and may provide clinicians a reference for postsurgical ROM.

Fig. 1

Example instrumentation including (a) IMU donning locations on the sternum and humerus with associated coordinate systems and (b) angle equivalency between forward flexion and abduction

Fig. 2

Upper extremity marker set utilized during validation experiments comparing IMU-based ROM and MOCAP-based ROM methods

Fig. 3

Example data removal including (a) prior to initial IMU donning via magnitude analysis and (b) data between initial donning and final doffing via variability analysis

Fig. 4

Data processing workflow including (1) raw accelerometer signal input, (2) processing accelerometer signals (bony segment differentiation, low pass filtration, offsetting anatomical/sensor misalignment, and distal to proximal coordinate transformation), (3) continuous shoulder elevation calculation, (4) daily metric calculation (average, maximum bin > 10×, maximum elevation, binned movement rate, binned percentage), (5) weekly metric averages, and (6) total subject averages

Fig. 5

Validation results comparing shoulder elevation calculated by MOCAP versus shoulder elevation calculated by IMU for two subjects during a variety of movements including (a) forward flexion, (b) abduction, (c) scaption, (d) internal/external rotation, and (e) all movements

Fig. 6

Daily shoulder elevation metrics for all subjects including average shoulder elevation, maximum binned shoulder elevation > 10 occurrences, and maximum shoulder elevation

Fig. 7

Binned shoulder elevation data in 5 deg increments with movement percentage average as bars and movement percent average ± one standard deviation as dashed lines