MS in Kinesiology

Our Clinical Exercise Physiology concentration prepares you to become an American College of Sports Medicine Certified Clinical Exercise Physiologist
Learn more

A Predictive Mobility Limitation Algorithm

Model on classifying mobility limitation using the Medicare Current Beneficiary Survey questions
A model on classifying mobility limitation using the Medicare Current Beneficiary Survey Questions. If a person states they cannot walk or receive help from a person to walk, they are classified as severe limitation. If a person states they have difficulty walking but not need help from a person or that they use special equipment, they are labeled as moderate limitation. Additionally, a person can be labeled as mild limitation if they don’t need assistance from a person to walk or don’t use special equipment, and if they are either unable, have a lot of or some difficulty walking ¼ of a mile. If a person does not have any difficulty walking and are able to walk ¼ of a mile with little to none difficulty, they are classified with no limitation. For information not known for those who have difficulty walking ¼ of a mile, they are unclassified.

The goal of this project is to advance research on mobility limited populations by developing and validating a method to reliably classify mobility limitation-severity within large healthcare datasets. Using innovative machine learning techniques and healthcare administrative data on veterans enrolled in VA healthcare, we will develop and validate an algorithm to accurately identify and distinguish between individuals with differing levels of mobility limitation (none to severe).

Funding Heading link

UIC College of Applied Health Science Interdisciplinary Pilot Grant

Previous funding provided by the Center for Large Data Research and Data Sharing in Rehabilitation UTMB sub-award No. 18-015

IRB information
IRB is part of a larger study called the Weight and Veterans Environments Study.

Acknowledgment of VA support:
This material is the result of work supported with resources and the use of facilities at the Edward Hines, Jr. VA Hospital.

Disclaimer:
The views expressed in this article are those of the authors and do not necessarily reflect the position or policy of the Department of Veterans Affairs or the United States government.

Publications and resources Heading link

Eisenberg, Y., Powell, L. M., Zenk, S. N., & Tarlov, E. (2020). Development of a Predictive Algorithm to Identify Adults With Mobility Limitations Using VA Health Care Administrative Data. Medical Care Research and Review, 1077558720950880.

Team Heading link

Principal investigator
Yochai Eisenberg, UIC College of Applied Health Sciences

Co-investigators
Jiehuan Sun, UIC School of Public Health

Call 312.996.2079
312.996.2079
Apply now
Contact us