Shoulder strength data are im
portant for
post-o
perative assessment of shoulder function and have been used in diagnosis of rotator cuff
pathology. Su
pport vector machines (SVM) em
ploy com
plex analysis techniques to solve classification and regression
problems. A SVM, a machine learning technique, can be used for analysis and classification of shoulder strength data. The goals of this study were to determine the diagnostic com
petency of SVM based on shoulder strength data and to a
pply SVM analysis in efforts to derive a single re
presentative shoulder strength score. Data were taken from fourteen isometric shoulder strength measurements of each shoulder (involved and uninvolved) in 45 rotator cuff tear
patients. SVM diagnostic
proficiency was found to be com
parable to re
ported ultrasound values. Im
provement of shoulder function was accurately re
presented by a single score in
pairwise com
parison of the
pre-o
perative and the 12 month
post-o
perative grou
p (
P<0.004). Thus, the SVM-based score may be a
promising metric for summarizing rotator cuff strength data.