C-STAR Course: Machine Learning and Sensors to Enhance Rehabilitation Research
This is an ON-DEMAND COURSE that is accessed virtually using the Academy Learning Portal. You will have 3 months from the date of registration to complete and review course materials.
*NOTE: There are two options to choose from at checkout. If you are an SLP seeking credit, please select "SLPs Only". All other disciplines please select the option "PTs and All Others"
DESCRIPTION: Over recent years, there has been an explosion of interest in wearable sensors, video, and computer vision for healthcare and patient monitoring. Many commercial and research-grade wearables can now capture continuous, high-resolution measurements about vital signs, activity, sleep, biomechanical metrics, and even physiological signals such as from the muscles or brain. However, translating this complex data into meaningful clinical information poses many substantial challenges. Machine learning is a powerful tool to address some of these challenges. In machine learning, computers themselves are learning from data and create models to make predictions about that data. In this introductory course, we will take a practical approach to understand how machine learning and sensors can be applied in the rehabilitation field, pitfalls to avoid, how to get started, and how these tools can create reliable digital biomarkers. This on-demand course consists of recordings of sessions that were delivered live on May 17, 2023.
- Arun Jayaraman, PT, Ph.D. Director, Max Näder Center for Rehabilitation Technologies & Outcomes Research; Director & Business Development Officer, Office of Translational Research, Associate Professor of PM&R, Medical Social Science, PTHMS, Northwestern University
- Joy Ku, Ph.D. Director of Promotions and Didactic Interactions for the NIH-funded Restore Center; Director of Education and Communications for the Mobilize Center; Manager of SimTK
- Eric Perreault, Ph.D. Professor of Biomedical Engineering at Northwestern University; Associate Dean for Research in Northwestern’s McCormick School of Engineering and Applied Sciences
- Matt Petrucci, Ph.D. Research Engineer, Bioengineering. Program Manager, Mobilize and Restore Centers, Stanford University
- Paolo Bonato, Ph.D. Director of the Motion Analysis Laboratory at Spaulding Rehabilitation Hospital, Boston; Associate Professor, Department of Physical Medicine and Rehabilitation at Harvard Medical School
- Scott Delp, Ph.D. Director, Human Performance Alliance at Stanford; James H. Clark Professor in the School of Engineering, Stanford University; Professor of Bioengineering, mechanical engineering, and orthopaedic surgery, Stanford University
- Jennifer Hicks, Ph.D. Deputy Director, Wu Tsai Human Performance Alliance at Stanford; Director of Research, Mobilize Center; Directory of Research, Restore Center; Research and Development Manager, OpenSim Project
- Konrad Kording, PhD The Nathan Francis Mossell Professor; University of Pennsylvania, Philadelphia PA
- Richard L. Lieber, Ph.D. Senior Vice President & Chief Scientific Officer, Shirley Ryan AbilityLab
- Megan K. O'Brien, PhD Research Scientist, Technology and Innovation Hub (tiHUB) Research Assistant Professor of PM&R, Northwestern University
- Joseph Hitt, Ph.D. CEO and Co-Founder GoX Labs, Inc.
- Hulya Emir-Farinas, Ph.D. Senior Staff Research Scientist, Consumer Health Research Team of Fitbit
- Steve Xu, MD, MSc CEO of Sibel Health
Engineers, Data Scientists, Physical Therapists, Physical Therapist Assistants, Occupational Therapists, Occupational Therapy Assistants, Nurses, Physicians and Speech-Language Pathologists.
- List different types of machine learning techniques that have been useful in rehabilitation research and clinical applications
- Identify 5 practical considerations and barriers to using machine learning in real-world rehabilitation problems
- Evaluate open source and publicly available tools and determine which would be a good starting point for a clinical problem
CONTINUING EDUCATION CREDIT:
This course has been approved by the Illinois Physical Therapy Board 6.0 Contact Hours. Approval #216-000069
The Shirley Ryan AbilityLab is recognized by the New York State Education Department's State Board for Physical Therapy as an approved provider of physical therapy and physical therapist assistant continuing education. This course has been approved for 6.0 Contact Hours
The following states require continuing education units with no state-specific approval: CT, IA, and WA
To participate, you will need access to a computer with an Internet connection. High-speed broadband access (LAN, Cable or DSL) is highly recommended.
- Internet connection: broadband wired or wireless (3G or better)
- Web browser:
Latest stable version of one of the following: Apple Safari, Google Chrome, Mozilla Firefox or Microsoft Edge.
- Speaker or headset to listen to audio files and participate in Zoom calls
- Do NOT use Internet Explorer, as it is not supported.
BROUGHT TO YOU BY C-STAR AND RESTORE:
The Center for Smart Use of Technologies to Assess Real World Outcomes (C-STAR), and RESTORE are two of six national resource centers comprising the Medical Rehabilitation Research Resource network (MR3) of the National Institutes of Health.
C-STAR is a joint grant between Northwestern University and Shirley Ryan AbilityLab, conceived out of a need to equip investigators with the skills and know-how to accurately employ technologies to measure and interpret data relevant to sensorimotor and cognitive function in the lab, clinic and real world. Our mission is to connect researchers with the right tools to develop and accurately assess technologies in the field of rehabilitation science. Leveraging the collective experience of clinicians, scientists, engineers and patients, our center provides the expertise, instruction and mentorship to empower researchers on the meaningful use of the vast array of technologies that are readily available but notoriously difficult to implement consistently across diverse patient populations.
The Restore Center (the Center for Reliable Sensor Technology-Based Outcomes for Rehabilitation) is an NIH MR3 Resource Center focused on enabling real-world assessments in rehabilitation. Based at Stanford University, we provide research infrastructure and training to enable rehabilitation scientists to use mobile sensors and video technology to assess movement and factors affecting movement.
Our Center brings together expertise from statistics, computer science, bioengineering, mobile health, and clinical rehabilitation. Together, we are developing software tools and easy-to-use, standardized workflows for real-world monitoring in rehabilitation. These resources, along with programs such as pilot project grants and virtual office hours, will establish a vibrant research community to achieve the potential of mobile technology to improve our knowledge and care of individuals with impaired movement.