Go offline with the Player FM app!
Dr. Ronald (James) Cotton Grand Rounds: Opportunities of AI Powered Gait Analysis for Rehabilitation, Part 2
Manage episode 499987284 series 78980
Dr. Ronald (James) Cotton who is an electrical engineer, neuroscientist, and physiatrist working as a physician scientist at Shirley Ryan Ability Lab, and assistant professor in the Northwestern University Department of Physical Medicine and Rehabilitation.
We have this one paper where we can use diffusion models and generate a bunch of probabilistic samples of movements and they constrain them by what we see in the cameras and have shown that we can actually estimate the confidence and the uncertainty in a reliable way. He indicated that we can use something called the myoskeleton that allows us to track all joints in the body down to the individual fingers. Our Portable Biomechanics Laboratory is kind of a combination of a smartphone app that records the rotation and movement of the phone itself. He discussed how he would like to establish validity as a predictive biomarker. He asked what do we actually want and what do we mean by precision rehabilitation? In his mind, the best formalism of it is something called the optimal dynamic treatment regime, which essentially is some kind of function, probably a learned function that looks at all the health information, all the biomarkersof an individual at any point in rehabilitation, kind of condenses that into a phenotype, and then predicts what is the next intervention that should be given. He spoke briefly about a case studythat applies to another line of research in his lab, which is EMG-based biofeedback and also about Next Generation Brain Machine Interface Chips.
114 episodes
Manage episode 499987284 series 78980
Dr. Ronald (James) Cotton who is an electrical engineer, neuroscientist, and physiatrist working as a physician scientist at Shirley Ryan Ability Lab, and assistant professor in the Northwestern University Department of Physical Medicine and Rehabilitation.
We have this one paper where we can use diffusion models and generate a bunch of probabilistic samples of movements and they constrain them by what we see in the cameras and have shown that we can actually estimate the confidence and the uncertainty in a reliable way. He indicated that we can use something called the myoskeleton that allows us to track all joints in the body down to the individual fingers. Our Portable Biomechanics Laboratory is kind of a combination of a smartphone app that records the rotation and movement of the phone itself. He discussed how he would like to establish validity as a predictive biomarker. He asked what do we actually want and what do we mean by precision rehabilitation? In his mind, the best formalism of it is something called the optimal dynamic treatment regime, which essentially is some kind of function, probably a learned function that looks at all the health information, all the biomarkersof an individual at any point in rehabilitation, kind of condenses that into a phenotype, and then predicts what is the next intervention that should be given. He spoke briefly about a case studythat applies to another line of research in his lab, which is EMG-based biofeedback and also about Next Generation Brain Machine Interface Chips.
114 episodes
Kaikki jaksot
×Welcome to Player FM!
Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.