There is a confusing amount of information flooding into our field about how AI and Machine Learning are impacting today’s clinical solutions. It is difficult for practicing clinicians to determine what is a promising research project from what is available in commercial applications. Nowhere is this challenge more prevalent than powered upper limb prosthetics. For over 10 years, “pattern recognition” myoelectric control has been a Machine Learning option for upper limb devices, but many practitioners have had limited formal education on how it is differentiated from conventional myoelectric approaches. This instructional course aims to fill the gap for the experienced or beginning practitioner, covering the pattern recognition myoelectric control topic that receives limited coverage in undergraduate curricula.
Attendees will be taught the practical application of pattern recognition myoelectric control, including how this form of Machine Learning acts as a decoder of neurological intent to provide the modern-technological approach to prosthesis control personalization. The course will also cover the underlying aspects of AI that work to benefit the users' learning process as well as foster the user-clinician relationship. Attendees who have used, or understand, pattern recognition myoelectric control will gain advanced knowledge on the future direction of the commercial applications and attendees who are new to the concept will come away with a solid understanding and confidence in applying the solution to their patients. The presenters will welcome any, and as many, questions as time permits.
Statement of the objective / learning objectives
Attendees will gain a solid understanding of pattern recognition myoelectric control, learn how it is differentiated from conventional myoelectric control, and leave with the confidence to apply the solution for the benefit of their patients.
