Graduation Year

2025

Document Type

Thesis

Degree

M.S.

Degree Name

Master of Science (M.S.)

Degree Granting Department

Computer Science and Engineering

Major Professor

John M. Templeton, Ph.D.

Committee Member

Dayane Reis, Ph.D.

Committee Member

Seungbae Kim, Ph.D.

Committee Member

Nathan Schilaty, D.C., Ph.D.

Keywords

Dimensionality Reduction, Feature Selection, Machine Learning, Sports Medicine, Multi-Class Classification

Abstract

Anterior cruciate ligament (ACL) injury is a prevalent and significant concern in sports medicine, often resulting in long-term consequences that affect quality of life. Despite advancements in medical technology, current methods for addressing the problem of ACL injuries remain inefficient, subjective, and limited in their predictive power. This study explores the potential of Linear Discriminant Analysis (LDA), a supervised machine learning (ML) technique, to improve the diagnosis and risk profiling of ACL injuries. This research aims to create an objective, effective, and precise technique for determining the risk of ACL injuries by examining key biomechanical, physical, and demographical features. The primary objectives include evaluating LDA’s ability to classify ACL injuries based on biomechanical data, identifying relevant biomechanical features associated with ACL injury mechanisms, and determining the feasibility of using LDA to develop personalized risk profiles. The results of this study could lead to more reliable injury prevention strategies, early diagnosis, and better patient outcomes in both clinical and sports settings.

Share

COinS