TY - GEN
T1 - Discriminating motion patterns of ACL reconstructed patients from healthy individuals
AU - Kusakunniran, Worapan
AU - Dirakbussarakom, Nattaporn
AU - Prachasri, Nantawat
AU - Yangchaem, Duangkamol
AU - Vanrenterghem, Jos
AU - Robinson, Mark
N1 - Publisher Copyright:
© 2015 MVA organization.
PY - 2015/7/8
Y1 - 2015/7/8
N2 - Injury to the Anterior Cruciate Ligament (ACL) can lead to inadequate movement during sport and daily life activities, leading to increased risk of reinjury or dropouts from any form of physical activity. Thus, it is important to detect such movement problems so that they can be prevented through focused rehabilitation programmes. This paper proposes a method to seek out differences of movement patterns between an ACL reconstructed group and a healthy control group. Principal Component Analysis (PCA) is applied to movement data in a training dataset. Then, Cohen's d is used to select such principle components (PCs) that can efficiently distinguish movement patterns of ACL reconstructed patients from healthy individuals. In our experiment, 10 subjects are used to evaluate the proposed method. Each subject contains nine observed variables of movement information. The proposed method can achieve a promising performance of above 90% accuracy to discriminating motion patterns of ACL reconstructed patients from healthy individuals. Also, vector loads of the selected PCs are plotted and visualized. Four variables significantly discriminated the ACL reconstructed group from the healthy control group, which are: 1) ground reaction force, 2) hip joint moment, 3) knee joint moment, and 3) ankle joint moment. Some of which have been identified as key predictors of ACL injury risk.
AB - Injury to the Anterior Cruciate Ligament (ACL) can lead to inadequate movement during sport and daily life activities, leading to increased risk of reinjury or dropouts from any form of physical activity. Thus, it is important to detect such movement problems so that they can be prevented through focused rehabilitation programmes. This paper proposes a method to seek out differences of movement patterns between an ACL reconstructed group and a healthy control group. Principal Component Analysis (PCA) is applied to movement data in a training dataset. Then, Cohen's d is used to select such principle components (PCs) that can efficiently distinguish movement patterns of ACL reconstructed patients from healthy individuals. In our experiment, 10 subjects are used to evaluate the proposed method. Each subject contains nine observed variables of movement information. The proposed method can achieve a promising performance of above 90% accuracy to discriminating motion patterns of ACL reconstructed patients from healthy individuals. Also, vector loads of the selected PCs are plotted and visualized. Four variables significantly discriminated the ACL reconstructed group from the healthy control group, which are: 1) ground reaction force, 2) hip joint moment, 3) knee joint moment, and 3) ankle joint moment. Some of which have been identified as key predictors of ACL injury risk.
UR - https://www.scopus.com/pages/publications/84941236880
U2 - 10.1109/MVA.2015.7153107
DO - 10.1109/MVA.2015.7153107
M3 - Conference contribution
AN - SCOPUS:84941236880
T3 - Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015
SP - 447
EP - 450
BT - Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 14th IAPR International Conference on Machine Vision Applications, MVA 2015
Y2 - 18 May 2015 through 22 May 2015
ER -