RMD data

Research Project

RETRIEVE

Source

C-STAR HOME

Come discover our information data sets and Rehab Measures Database

Body

Want to advance your understanding of patient function with reliable real-world data, although you are not successful with existing technologies? Maybe the data are uncontrollable, or you are unable to validate the information? You might be frustrated with the overwhelming amount of information available and lack of direction regarding the appropriate measures of patient performance. For almost 30 years, we have been named number 1 for a reason: we bring together the highest performing talent into one place. We can help you.

RMD Rehabilitation Measures Database

Body

The Rehabilitation Measures Database currently boasts over 400 measures for benchmarks and outcomes and receives over 11,000 hits a day. RMD was developed to help clinicians and researchers identify reliable and valid instruments used to assess patient outcomes during all phases of rehabilitation.

The database provides evidence-based summaries that include concise descriptions of each instrument’s psychometric properties, instructions for administering and scoring each assessment as well as a representative bibliography with citations linked to PubMed abstracts.

Whenever possible, we have also included a copy of the instrument for the users to download or information about obtaining the instrument.


The RMD is divided into ten clinical content areas within PMR including Stroke, Spinal Cord Injury, Brain Injury, Parkinson’s Disease, Neuromuscular Conditions, Vestibular Disorders, Older Adults and Geriatric Care, Cancer, Musculoskeletal Conditions and Arthritis.

The Rehabilitation Measures Database was created under the leadership of Allen Heinemann, PhD, the Director of the Center for Rehabilitation Outcomes Research [along with the following contributors] and evolved through collaboration between (CROR) at Shirley Ryan Abilitylab and the Department of Medical Social Sciences Informatics group at Northwestern University Feinberg School of Medicine with funding from the National Institute on Disability and Rehabilitation Research, U.S. Department of Education.

Body

Additional Resources to support RMD learning include the following web pages:

Statistical Terms Used  and  Educational Resources and Teaching Modules

Rich Benchmark Data Sets

Body

We have developed our own machine learning and data fusion that creates customized population-specific algorithms for physical activity metrics. By using modified smart technology we are able to take the raw sensor data (steps, energy, etc) and improve the reliability and accuracy of data estimates. Our research demonstrated that machine learning models of activity recognition from wearable sensors must be validated on both the specific patient population under investigation and on the assistive device used. 

From our research, we have developed rich content repositories of data, stay tuned for our examples of the smart use of technology and the data graphics we have compiled. 

 

CSTAR is funded by the National Institutes of Health (Grant #P2C HD101899) supported by NICHD and NINDS.

Save now, read later.