A support vectors classifier approach to predicting the risk of progression of adolescent idiopathic scoliosis
ABSTRACT A support vector classifier (SVC) approach was employed in predicting the risk of progression of adolescent idiopathic scoliosis (AIS), a condition that causes visible trunk asymmetries. As the aetiology of AIS is unknown, its risk of progression can only be predicted from measured indicators. Previous studies suggest that individual indicators of AIS do not reliably predict its risk of progression. Complex indicators with better predictive values have been developed but are unsuitable for clinical use as obtaining their values is often onerous, involving much skill and repeated measurements taken over time. Based on the hypothesis that combining common indicators of AIS using an SVC approach would produce better prediction results more quickly, we conducted a study using three datasets comprising a total of 44 moderate AIS patients (30 observed, 14 treated with brace). Of the 44 patients, 13 progressed less than 5° and 31 progressed more than 5°. One dataset comprised all the patients. A second dataset comprised all the observed patients and a third comprised all the brace-treated patients. Twenty-one radiographic and clinical indicators were obtained for each patient. The result of testing on the three datasets showed that the system achieved 100% accuracy in training and 65%-80% accuracy in testing. It outperformed a "statistically equivalent" logistic regression model and a stepwise linear regression model on the said datasets. It took less than 20 min per patient to measure the indicators, input their values into the system, and produce the needed results, making the system viable for use in a clinical environment.
- SourceAvailable from: ipd.gu.se
Article: Adolescent idiopathic scoliosis.[show abstract] [hide abstract]
ABSTRACT: The effective treatment of adolescent idiopathic scoliosis (AIS) is predicted on timely detection and appropriate intervention. School screening programs have resulted in a reduced incidence of advanced curvature upon referral. Studies of the natural history of AIS demonstrate that a number of factors are of predictive value in assigning risk for progressive curvature and subsequent deformity and/or morbidity. These are age at time of diagnosis, stage of skeletal maturity, and magnitude and pattern of curvature. The options in treating AIS are observation, orthosis, and operation. Spinal orthoses are designed to arrest the progression of curvature during skeletal maturation. Newer brace designs and protocols facilitate compliance with long-term bracing and may reduce the incidence of curves requiring operative intervention. The goal in scoliosis surgery is to reduce curvature and to create a stable framework on which vertebral fusion can occur. Technical advances have yielded a number of instrumentation options for achieving this goal. Basic technical comparisons are made among of prototypes of posterior spinal instrumentation. The newest of these, Cotrel-Dubousset, may supplant Harrington rod instrumentation as the preferred standard in the operative treatment of AIS.Orthopaedic review 02/1990; 19(1):35-43.
- [show abstract] [hide abstract]
ABSTRACT: In an attempt to find prognostic factors for mild scoliosis, the first clinical and radiologic data of 159 subjects with idiopathic scoliosis less than 30 degrees were correlated with the annual speed of progression estimated graphically by further examinations. Thoracic and double major are more progressive than thoracolumbar and lumbar. The correlation with rate of progression is better for supine angle than for standing angle. Curves with low supine angles are those that have great relative collapse and low risk of progression. Only the rib hump of thoracic and thoracolumbar are correlated with evolutivity. Predictive equations give less approximation for individual prognosis than a previous graphic method, so they are not used. Approximately 73% of scoliosis have evolutivities less than 6 degrees per year and required nocturn corrective treatment.Spine 07/1985; 10(5):421-4. · 2.16 Impact Factor