Feature selection using a principal component analysis of the kinematics of the pivot shift phenomenon David R. Labbe a,b,n , Jacques A de Guise a,b , Neila Mezghani a , Ve ´ ronique Godbout c , Guy Grimard d , David Baillargeon e , Patrick Lavigne f , Julio Fernandes g , Pierre Ranger g , Nicola Hagemeister a,b a Laboratoire de recherche en imagerie et orthope ´die, Centre de recherche, Centre hospitalier de l’Universite´ de Montre´al (CHUM), Montre ´al, Canada b E ´ cole de technologie supe´rieure, Montre´al, Canada c Hˆ opital Notre-Dame, Montre´al, Canada d Hˆ opital Ste-Justine, Montre ´al, Canada e Hˆ opital de la Cite ´-de-la-Sante´, Laval, Canada f Hˆ opital Maisonneuve-Rosemont, Montre ´al, Canada g Hˆ opital du Sacre´-Coeur, Montre´al, Canada article info Article history: Accepted 11 August 2010 Keywords: Pivot shift Knee joint instability ACL rupture Feature selection Principal component analysis abstract The pivot shift test reproduces a complex instability of the knee joint following rupture of the anterior cruciate ligament. The grade of the pivot shift test has been shown to correlate to subjective criteria of knee joint function, return to physical activity and long-term outcome. This severity is represented by a grade that is attributed by a clinician in a subjective manner, rendering the pivot shift test poorly reliable. The purpose of this study was to unveil the kinematic parameters that are evaluated by clinicians when they establish a pivot shift grade. To do so, eight orthopaedic surgeons performed a total of 127 pivot shift examinations on 70 subjects presenting various degrees of knee joint instability. The knee joint kinematics were recorded using electromagnetic sensors and principal component analysis was used to determine which features explain most of the variability between recordings. Four principal components were found to account for most of this variability (69%), with only the first showing a correlation to the pivot shift grade (r ¼0.55). Acceleration and velocity of tibial translation were found to be the features that best correlate to the first principal component, meaning they are the most useful for distinguishing different recordings. The magnitudes of the tibial translation and rotation were amongst those that accounted for the least variability. These results indicate that future efforts to quantify the pivot shift should focus more on the velocity and acceleration of tibial translation and less on the traditionally accepted parameters that are the magnitudes of posterior translation and external tibial rotation. & 2010 Elsevier Ltd. All rights reserved. 1. Introduction The pivot shift test reproduces the complex rotational and translational instability of the tibiofemoral joint, which is associated with the episodes of giving way that are often reported by ACL-deficient patients. It is the only clinical test that correlates to subjective criteria of knee joint function following rupture of the anterior cruciate ligament (ACL) (Kocher et al., 2004; Leitze et al., 2005). As such, it is widely accepted that the objective of reconstructive surgery should be to eliminate or limit the pivot shift, which is graded subjectively by the clinician as being a grade 0 (none), grade 1 (glide), grade 2 (clunk) or grade 3 (gross clunk). During the pivot shift test, the clinician flexes the evaluated knee while applying onto it a valgus moment. As the ACL-deficient knee flexes, the tibial plateau gradually subluxates anteriorly and rotates internally. At approximately 301 of flexion, the tibia suddenly returns to its reduced position. In other words, the pivot shift is said to be a combination of posterior tibial translation and external tibial rotation (Matsumoto, 1990; Bull and Amis, 1998; Lane et al., 2008a). Different studies have attempted to measure the precise kinematics of the pivot shift in an effort to establish a more objective and quantitative measurement (Bull et al., 2002; Hoshino et al., 2007; Kubo et al., 2007; Amis et al., 2008; Lane et al., 2008b; Lopomo et al., 2009). Several studies have indeed confirmed a correlation between posterior tibial translation and Contents lists available at ScienceDirect journal homepage: www.elsevier.com/locate/jbiomech www.JBiomech.com Journal of Biomechanics 0021-9290/$ - see front matter & 2010 Elsevier Ltd. All rights reserved. doi:10.1016/j.jbiomech.2010.08.011 n Corresponding author at: Laboratoire de recherche en imagerie et orthope ´ die, Centre de recherche ´, CHUM—Hˆ opital Notre-Dame, Pavillon J.A. de S  eve, 1st floor, Room Y-1614, 1560 rue Sherbrooke est, Montre ´ al (Que ´ .), Canada H2L 4M1. Tel.: + 514 890 8000x28723; fax: + 514 412 7785. E-mail address: dlabbe@gmail.com (D.R. Labbe). Journal of Biomechanics 43 (2010) 3080–3084