Manual wheelchair users experience significant upper extremity strain, leading to a high prevalence of shoulder pain. Identifying modifiable risk factors for shoulder complaints is crucial for developing effective interventions. Consequently, it's important to quantify shoulder load (magnitude, frequency and duration) experienced by manual wheelchair users throughout the day. This study aims to quantify the magnitude of shoulder load during various daily activities, including wheelchair propulsion at different speeds and inclines, ascending and descending ramps, weight relief lift, material handling and desk work. Ten able-bodied participants performed these activities while their upper extremity kinematics and exerted forces were measured. The analysis focused on glenohumeral contact force and rotator cuff muscle forces using the Delft Shoulder and Elbow Model. Highest mean glenohumeral contact forces were found during weight relief lift (1363 ± 1204 N), followed by descending a ramp (997 ± 1043 N) and fast propulsion (802 ± 742 N). The supraspinatus muscle generated the greatest force during weight relief lift (327 ± 490 N) and fast propulsion (184 ± 205 N). These findings provide a first reference for estimating joint load in daily activities. By combining these data with the individual activity frequency and duration, personalized shoulder load exposure can be assessed, informing the development of targeted interventions to reduce shoulder pain in manual wheelchair users.

Shoulder problems (pain and pathology) are highly prevalent in manual wheelchair users with spinal cord injury. These problems lead to limitations in activities of daily life (ADL), labor- and leisure participation, and increase the health care costs. Shoulder problems are often associated with the long-term reliance on the upper limbs, and the accompanying “shoulder load”. To make an estimation of daily shoulder load, it is crucial to know which ADL are performed and how these are executed in the free-living environment (in terms of magnitude, frequency, and duration). The aim of this study was to develop and validate methodology for the classification of wheelchair related shoulder loading ADL (SL-ADL) from wearable sensor data. Ten able bodied participants equipped with five Shimmer sensors on a wheelchair and upper extremity performed eight relevant SL-ADL. Deep learning networks using bidirectional long short-term memory networks were trained on sensor data (acceleration, gyroscope signals and EMG), using video annotated activities as the target. Overall, the trained algorithm performed well, with an accuracy of 98% and specificity of 99%. When reducing the input for training the network to data from only one sensor, the overall performance decreased to around 80% for all performance measures. The use of only forearm sensor data led to a better performance than the use of the upper arm sensor data. It can be concluded that a generalizable algorithm could be trained by a deep learning network to classify wheelchair related SL-ADL from the wearable sensor data.