Loss of mobility caused by aging, injury, or disease affects millions of Americans, reducing their independence and quality of life. Human movement depends on many body systems working together. The brain and spinal cord send signals to muscles, muscles move bones and joints, and pain or other sensory signals can change how a person moves. Most current computer models study only one of these systems at a time. As a result, the models cannot fully explain why movement changes or predict how treatments will help. This project will create a new “digital twin” of human movement: a computational model that combines these systems into one tool. Researchers at Boise State University and University of Denver will use patient data to build a model of the leg that includes the nervous system, muscles, bones, joints, and the effects of pain. The model will show how injury, disease, and aging changes the way people walk. This work will lead to new machine learning assisted tools to help doctors and therapists choose better treatments tailored for individuals. It will lead to better rehabilitation plans and improved quality of life for people with movement problems.
This project will develop a multiscale and subject-specific model that links cortical and spinal control, physiology, mechanics, and pain. The goal of the model is to predict changes in mobility due to injury and aging. Machine learning-assisted surrogate modeling will determine sensitivity of movement and muscle loading to anatomy and neural factors. The model will be personalized using imaging and functional data from people with osteoarthritis and patellofemoral pain. Software and datasets developed by the project will be openly shared to promote reproducibility.
This award reflects NSF’s statutory mission and has been deemed worthy of support through evaluation using the Foundation’s intellectual merit and broader impacts review criteria.