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.