Information about project titled 'Identifying ACL risk profile clusters in from cutting biomechanics through machine learning'
Identifying ACL risk profile clusters in from cutting biomechanics through machine learning
|Details about the project - category||Details about the project - value|
|Project manager:||Tron Krosshaug|
|Coworker(s):||Roald Bahr, Chris Richter, Andy Franklyn-Miller|
Intro: Cutting biomechanics is likely to influence ACL injury risk. However, we do not know which types of cutting techniques that involves higher risk.
Aim: To identify possible clusters of cutting techniques that may be associated with increased risk of ACL injury.
Method: We measured 3D kinetics and kinematics during sport-specific sidestep cutting maneuvers in 776 female elite handball and football players. Players performed sport-specific cutting maneuvers while 3D kinetics and kinematics was captured. We measured full body biomechanics and extracted key variables, characterizing player movements as well as joint loading. We will use standard clustering techniques in machine learning to describe possible clusters of cutting techniques that may be associated with increased risk of ACL injury.