A fuzzy classifier approach to assessing the progression of adolescent idiopathic scoliosis from radiographic indicators

A fuzzy classifier approach was used to predict the progression of adolescent idiopathic scoliosis (AIS). Past studies indicate that individual indicators of AIS do not reliably predict progression. Complex indicators having improved predictive values have been developed but are unsuitable for clinical use. Based on the hypothesis that combining some common indicators with a fuzzy classifier could produce better results, we conducted a study using radiographic indicators measured from 44 moderate AIS patients. We clustered the data using a fuzzy c-means classifier and designed fuzzy rules to represent each cluster. We classified the records in the dataset using the resulting rules. This approach outperformed a binary logistic regression method and a stepwise linear regression method. Less than fifteen minutes per patient is required to measure the indicators, input the data into the system and generate results enabling its use in a clinical environment to aid in the management of AIS.

[1]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[2]  G. Duval-Beaupère,et al.  Scoliosis at less than 30 degrees. Properties of the evolutivity (risk of progression). , 1985, Spine.

[3]  G. Duval-Beaupère,et al.  Rib Hump and Supine Angle as Prognostic Factors for Mild Scoliosis , 1992, Spine.

[4]  J. Risser,et al.  The Classic: The Iliac Apophysis: An Invaluable Sign in the Management of Scoliosis , 2009, Clinical orthopaedics.

[5]  Magne Setnes,et al.  Fuzzy relational classifier trained by fuzzy clustering , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[6]  J. M. Carlson,et al.  The prediction of curve progression in untreated idiopathic scoliosis during growth. , 1984, The Journal of bone and joint surgery. American volume.

[7]  A. Nachemson,et al.  Prediction of progression of the curve in girls who have adolescent idiopathic scoliosis of moderate severity. Logistic regression analysis based on data from The Brace Study of the Scoliosis Research Society. , 1995, The Journal of bone and joint surgery. American volume.

[8]  Doug Hill,et al.  Prototypes stability analysis in the design of fuzzy classifiers to assess the severity of scoliosis , 2003, CCECE 2003 - Canadian Conference on Electrical and Computer Engineering. Toward a Caring and Humane Technology (Cat. No.03CH37436).

[9]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[10]  Jan Lidstrom,et al.  Prediction of Progression of the Curve in Girls Who Have Adolescent Idiopathic Scoliosis of Moderate Severity , 2006 .

[11]  D L Hill,et al.  Trunk distortion in adolescent idiopathic scoliosis. , 1998, Journal of pediatric orthopedics.

[12]  L. Karol,et al.  Progression of the curve in boys who have idiopathic scoliosis. , 1993, The Journal of bone and joint surgery. American volume.

[13]  Nelson G. Durdle,et al.  A support vectors classifier approach to predicting the risk of progression of adolescent idiopathic scoliosis , 2005, IEEE Transactions on Information Technology in Biomedicine.