Adolescent Idiopathic Scoliosis is a spinal deformity sometimes treated using a brace. Brace treatment is successful when it prevents progression (worsening) of the spinal curve during adolescence. However, physicians' understanding of what causes progression is unclear, so a method for predicting a braced patient's risk of progression could assist physicians in planning treatment. Some such models have been proposed, but most are ill-suited for clinical use. We applied conditional fuzzy clustering to a dataset of past Scoliosis patients, to generate prototypes representative of various treatment outcomes. New patients' outcomes were predicted by comparing them to the prototypes. This model is 76-81% accurate, highly interpretable, and easily integrated into the clinic's workflow, making it a potentially valuable support tool.
Amani Hassan, Stefan Parent, Hélène Mathieu, Charlotte Zaouter, Sirinart Molidperee, Edward T. Bagu, Soraya Barchi, Isabelle Villemure, Scott Burton Patten, Florina Moldovan
Amani Hassan, Edward T. Bagu, Scott Burton Patten, Sirinart Molidperee, Stefan Parent, Soraya Barchi, Isabelle Villemure, André Tremblay, Florina Moldovan
Monique C. Minnema, Eva Kimby, Shirley D’Sa, Luc‐Matthieu Fornecker, Stéphanie Poulain, Tom J. Snijders, Efstathios Kastritis, Stéphane Kremer, Aikaterini Fitsiori, Laurence Simon, Frédéric Davi, Michael P. Lunn, Jorge J. Castillo, Christopher J. Patterson, Magali Le Garff‐Tavernier, Myrto Costopoulos, Véronique Leblond, Marie José Kersten, Meletios A Dimopoulos, Steven P. Treon
Discussion(0)
No comments yet. Be the first to comment.