Machine Learning for Optical Motion Capture-driven Musculoskeletal Modeling from Inertial Motion Capture Data

Marker-based Optical Motion Capture (OMC) systems and the associated musculoskeletal (MSK) modeling predictions have offered the ability to gain insights into in vivo joint and muscle loading non-invasively as well as aid clinical decision-making. However, an OMC system is lab-based, expensive, and requires a line of sight. A widely used alternative is the Inertial Motion Capture (IMC) system, which is portable, user-friendly, and relatively low cost, although it is not as accurate as an OMC system. Irrespective of the choice of motion capture technique, one needs to use an MSK model to obtain the kinematic and kinetic outputs, which is a computationally expensive tool increasingly well approximated by machine learning (ML) methods. Here, we present an ML approach to map IMC data to the human upper-extremity MSK outputs computed from OMC input data. Essentially, we attempt to predict high-quality MSK outputs from the relatively easier-to-obtain IMC data. We use OMC and IMC data simultaneously collected for the same subjects to train an ML (feed-forward multi-layer perceptron) model that predicts OMC-based MSK outputs from IMC measurements. We demonstrate that our ML predictions have a high degree of agreement with the desired OMC-based MSK estimates. Thus, this approach will be instrumental in getting the technology from 'lab to field' where OMC-based systems are infeasible.