Research Mentor(s): David Lipps
Authors: Sasha Lee, Jodi Motlagh, Amani Alkayyali, PhD Candidate, David Lipps, PhD
Current methods to measure shoulder kinematics require expensive equipment, cannot be done remotely, and require substantial time to complete, calibrating cameras, placing several motion capture markers, and then analyzing the data. A study is underway to validate a wearable shoulder patch to measure shoulder kinematics. The experiment consists of using this patch in individuals with/without shoulder pain while simultaneously collecting data using motion capture and wearable inertial measurement units (IMU). Data collection from motion capture and IMUs take significantly longer, requiring placement of 6 IMUs and 14 motion capture markers along the upper body and arm of participants. Additionally, data scrubbing took significantly longer to analyze since the markers and devices were not always captured, due to occlusion, by the motion camera. The kirigami shoulder patch only needs to be applied to the dominant/affected shoulder and is compatible with the depth camera, meaning further development is being made so shoulder kinematics can be measured with a cellphone camera, making this device portable and easily accessible for patients to use. Collected and analyzed via Python and the scikit-learn machine learning package, the device has the potential to predict shoulder range of motion and activities of daily living. The kirigami shoulder patch is an upcoming measurement device that will provide a cheaper, efficient, and portable method to measure shoulder kinematics in breast cancer patients who encounter shoulder pain.