A Logistic Regression Model for Monitoring and Classifying Post-ACL Rehabilitation Individuals for Return to Sport

• Activity Number: 183 - Movement in Sports and Medicine
• Type: Contributed
• Date/Time: Tuesday, August 4, 2020 : 10:00 AM to 2:00 PM
• Sponsor: Section on Statistics in Sports
• Author(s): Carolyn Morgan* and Kristin Denise Morgan and Yannis Denise Halkiadakis and Yannis Halkidadis and Helia Mahzoun Alzakerin
• Companies: Meck Limited, LLC and University of Connecticut and University of Connecticut and University of Connecticut and University of Connecticut
• Keywords: Sports; logistic regression; athletic monitoring; modelling

Abstract

Over 250,000 anterior cruciate ligament (ACL) injuries occur every year in the United States alone, often during sports and fitness activities. Following an ACL injury and reconstruction, 44% of patients fail to return to healthy and functional levels due to unresolved neuromuscular impairments. These impairments can cause an individual to adopt adverse gait patterns resulting in detrimental compressive knee loading. Tools and methods for measuring, tracking, and classifying healthy knee function of an individual are needed. This paper proposes the use of time-based and frequency-based techniques to extract traditional and non-traditional metrics, such as, stride time variability, fast Fourier transform amplitudes, and ground reaction force peaks to evaluate the restoration of healthy limb dynamics. These metrics will be used to develop a logistic regression model to aid in the classification of the healthy and ACL injured populations. This model will be helpful to clinicians and rehabilitation scientists in monitoring and developing programs for successful return-to-sport for post-ACL reconstruction individuals.