A validated composite model to predict risk of curve progression in adolescent idiopathic scoliosis

Abstract

Background: In adolescent idiopathic scoliosis (AIS), the continuous search for effective prognostication of significant curve progression at the initial clinical consultation to inform decision for timely treatment and to avoid unnecessary overtreatment remains a big challenge as evidence of the multifactorial etiopathogenic nature is increasingly reported. This study aimed to formulate a composite model composed of clinical parameters and circulating markers in the prediction of curve progression. Method: This is a two-phase study consisting of an exploration cohort (120 AIS, mean Cobb angle of 25° § 8.5 at their first clinical visit) and a validation cohort (51 AIS, mean Cobb angle of 23° § 5.0°at the first visit). Patients with AIS were followed-up for a minimum of six years to formulate a composite model for prediction. At the first visit, clinical parameters were collected from routine clinical practice, and circulating markers were assayed from blood. Finding: We constructed the composite predictive model for curve progression to severe Cobb angle > 40°w ith a high HR of 27.9 (95% CI of 6.55 to 119.16). The area under curve of the composite model is higher than that of individual parameters used in current clinical practice. The model was validated by an independent cohort and achieved a sensitivity of 72.7% and a specificity of 90%. Interpretation: This is the first study proposing and validating a prognostic composite model consisting of clinical and circulating parameters which could quantitatively evaluate the probability of curve progression to a severe curvature in AIS at the initial consultation. Further validation in clinic will facilitate application of composite model in assisting objective clinical decision.

Curve type, flexibility, correction, and rotation are predictors of curve progression in patients with adolescent idiopathic scoliosis undergoing conservative treatment

“…cite this article: Bone Joint J 2022;104-B(4):424-432. introduction accurate forecasting of curve progression in adolescent idiopathic scoliosis (ais), using readily available radiological predictors, is challenging due to the multifactorial nature and variable progression of ais curves. 1 the prognostication of curve progression requires identification of threshold levels of relevant factors and corresponding effect sizes for each predictor to enable clinical risk classification. 2 this allows appropriate follow-up for patients at higher risk, and explanation of the likely outcome.…”

Potential Muscle-Related Biomarkers in Predicting Curve Progression to the Surgical Threshold in Adolescent Idiopathic Scoliosis—A Pilot Proteomic Study Comparing Four Non-Progressive vs. Four Progressive Patients vs. A Control Cohort

“…A number of circulating proteins have been proposed as prognostic factors of AIS, such as melatonin and calmodulin [ 33 , 34 , 35 , 36 , 37 ]. Recently, our group proposed a composite model composed of plasma miR-145 and total procollagen type 1 N-terminal propeptide (P1NP) together with clinical parameters to predict the risk of curve progression in AIS, achieving a sensitivity of 72.2% and a specificity of 90% [ 38 ]. Despite there being a close interaction between bone and muscle, there are, as of yet, no muscle-related biomarkers for AIS.…”

An artificial intelligence powered platform for auto-analyses of spine alignment irrespective of image quality with prospective validation

“…Thus, current diagnoses and follow-up assessments require extensive clinical experience and expertise to interpret the alignment parameters manually and assess the patient physical appearance, making fast and accurate alignment analyses challenging. 4 AI has shown great promise in managing spine disease, including disease detection 5 , classification, 6,7 segmentation, 8 and progression prediction, 9 mainly based on medical images. Previous studies on automatic spine alignment analysis [10][11][12] could directly or indirectly regress CAs from radiographs of the major curve but could not compute heterogeneous curve patterns 13 or investigate the curve types.…”

“…AI has shown great promise in managing spine disease, including disease detection 5 , classification, 6 7 segmentation, 8 and progression prediction, 9 mainly based on medical images. Previous studies on automatic spine alignment analysis 10 , 11 , 12 could directly or indirectly regress CAs from radiographs of the major curve but could not compute heterogeneous curve patterns 13 or investigate the curve types.…”