Does ScoliScore provide more information than traditional clinical estimates of curve progression?

Predicting radiographic outcomes of vertebral body tethering in adolescent idiopathic scoliosis patients using machine learning

Anterior Vertebral Body Tethering (AVBT) is a growing alternative treatment for adolescent idiopathic scoliosis (AIS), offering an option besides spinal fusion. While AVBT aims to correct spinal deformity through growth correction, its outcomes have been mixed. To improve surgical outcomes, this study aimed to develop a machine learning-based tool to predict short- and midterm spinal curve correction in AIS patients who underwent AVBT surgery, using the most predictive clinical, radiographic, and surgical parameters. After institutional review board approval and based on inclusion criteria, 91 AIS patients who underwent AVBT surgery were selected from the Shriners Hospitals for Children, Philadelphia. For all patients, longitudinal standing (PA or AP, and lateral) and side bending spinal Radiographs were retrospectively obtained at six visits: preop and first standing, one year, two years, five years postop, and at the most recent follow-up. Demographic, radiographic, and surgical features associated with curve correction were collected. The sequential backward feature selection method was used to eliminate correlated features and to provide a rank-ordered list of the most predictive features of the AVBT correction. A Gradient Boosting Regressor (GBR) model was trained and tested using the selected features to predict the final correction of the curve in AIS patients. Eleven most predictive features were identified. The GBR model predicted the final Cobb angle with an average error of 6.3 ± 5.6 degrees. The model also provided a prediction interval, where 84% of the actual values were within the 90% prediction interval. A list of the most predictive features for AVBT curve correction was provided. The GBR model, trained on these features, predicted the final curve magnitude with a clinically acceptable margin of error. This model can be used as a clinical tool to plan AVBT surgical parameters and improve outcomes.

Predicting curve progression for adolescent idiopathic scoliosis using random forest model

Background

Adolescent Idiopathic Scoliosis (AIS) is a three-dimensional (3D) spinal deformity characterized by coronal curvature and rotational deformity. Predicting curve progression is important for the selection and timing of treatment. Although there is a consensus in the literature regarding prognostic factors associated with curve progression, the order of importance, as well as the combination of factors that are most predictive of curve progression is unknown.

Objectives

(1) create an ordered list of prognostic factors that most contribute to curve progression, and (2) develop and validate a Machine Learning (ML) model to predict the final major Cobb angle in AIS patients.

Methods

193 AIS patients were selected for the current study. Preoperative PA, lateral and lateral bending radiographs were retrospectively obtained from the Shriners Hospitals for Children. Demographic and radiographic features, previously reported to be associated with curve progression, were collected. Sequential Backward Floating Selection (SBFS) was used to select a subset of the most predictive features. Based on the performance of several machine learning methods, a Random Forest (RF) regressor model was used to provide the importance rank of prognostic features and to predict the final major Cobb angle.

Results

The seven most predictive prognostic features in the order of importance were initial major Cobb angle, flexibility, initial lumbar lordosis angle, initial thoracic kyphosis angle, age at last visit, number of levels involved, and Risser "+" stage at the first visit. The RF model predicted the final major Cobb angle with a Mean Absolute Error (MAE) of 4.64 degrees.

Conclusion

A RF model was developed and validated to identify the most important prognostic features for curve progression and predict the final major Cobb angle. It is possible to predict the final major Cobb angle value within 5 degrees error from 2D radiographic features. Such methods could be directly applied to guide intervention timing and optimization for AIS treatment.

Association of Ligamentum Flavum Hypertrophy with Adolescent Idiopathic Scoliosis Progression-Comparative Microarray Gene Expression Analysis

The role of the ligamentum flavum (LF) in the pathogenesis of adolescent idiopathic scoliosis (AIS) is not well understood. Using magnetic resonance imaging (MRI), we investigated the degrees of LF hypertrophy in 18 patients without scoliosis and on the convex and concave sides of the apex of the curvature in 22 patients with AIS. Next, gene expression was compared among neutral vertebral LF and LF on the convex and concave sides of the apex of the curvature in patients with AIS. Histological and microarray analyses of the LF were compared among neutral vertebrae (control) and the LF on the apex of the curvatures. The mean area of LF in the without scoliosis, apical concave, and convex with scoliosis groups was 10.5, 13.5, and 20.3 mm2, respectively. There were significant differences among the three groups (p < 0.05). Histological analysis showed that the ratio of fibers (Collagen/Elastic) was significantly increased on the convex side compared to the concave side (p < 0.05). Microarray analysis showed that ERC2 and MAFB showed significantly increased gene expression on the convex side compared with those of the concave side and the neutral vertebral LF cells. These genes were significantly associated with increased expression of collagen by LF cells (p < 0.05). LF hypertrophy was identified in scoliosis patients, and the convex side was significantly more hypertrophic than that of the concave side. ERC2 and MAFB genes were associated with LF hypertrophy in patients with AIS. These phenomena are likely to be associated with the progression of scoliosis.

Idiopathic scoliosis: general characteristics and analysis of etiological theories (literature review)

Idiopathic scoliosis is a severe pathology of the musculoskeletal system that affects children and adolescents all over the world. The disease occurs in approximately 0.2-0.6% of the general population, and is the largest subgroup of spinal curvature in humans (70-90% of all known scoliosis cases). In idiopathic scoliosis, a threedimensional deformation of the vertebral column is formed, leading to the formation of a rib hump, curvature of the ribs and chest, asymmetry of the pelvis and impaired development of internal organs. The main feature of the disease is the spontaneous development of deformity during the growth of the child and the tendency to progress. Scoliosis is not only an orthopedic disease, but also a ignificant cosmetic, and, consequently, a psychological and social problem. The standard of treatment for scoliotic disease remains unchanged for a long time: observation, corset treatment and surgical correction. The prognosis for the development of pathology varies depending on the degree of deformation. The corset-therapy, hospitalization, surgery and treatment of chronic back pain have a negative impact on the psychoemotional state of children and adolescents. Despite significant advances in the methods of diagnosis of deformity, improvement of surgical treatment methods and in the study of pathogenesis, the etiological factor of pathology is still unknown. The search for the causes of idiopathic scoliosis covers almost all aspects of its possible origin: genetic, environmental, hormonal, metabolic, biochemical, neurological, and others. In recent decades, relevant theories of the development of scoliosis have been formulated, but none of the theories reveals the essence of the pathological process and has no clear justification. The greatest number of supporters is the genetic theory: genetic factors play a key role in the occurrence and development of idiopathic scoliosis. Understanding the underlying factors of the disease will enable prevention, early diagnosis, and identification of the risk groups of the patients in question.

Etiopathogenesis of adolescent idiopathic scoliosis: Review of the literature and new epigenetic hypothesis on altered neural crest cells migration in early embryogenesis as the key event

Adolescent idiopathic scoliosis (AIS) affects 2-3% of children. Numerous hypotheses on etiologic/causal factors of AIS were investigated, but all failed to identify therapeutic targets and hence failed to offer a cure. Therefore, currently there are only two options to minimize morbidity of the patients suffering AIS: bracing and spinal surgery. From the beginning of 1960th, spinal surgery, both fusion and rod placement, became the standard of management for progressive adolescent idiopathic spine deformity. However, spinal surgery is often associated with complications. These circumstances motivate AIS scientific community to continue the search for new etiologic and causal factors of AIS. While the role of the genetic factors in AIS pathogenesis was investigated intensively and universally recognized, these studies failed to nominate mutation of a particular gene or genes combination responsible for AIS development. More recently epigenetic factors were suggested to play causal role in AIS pathogenesis. Sharing this new approach, we investigated scoliotic vertebral growth plates removed during vertebral fusion (anterior surgery) for AIS correction. In recent publications we showed that cells from the convex side of human scoliotic deformities undergo normal chondrogenic/osteogenic differentiation, while cells from the concave side acquire a neuronal phenotype. Based on these facts we hypothesized that altered neural crest cell migration in early embryogenesis can be the etiological factor of AIS. In particular, we suggested that neural crest cells failed to migrate through the anterior half of somites and became deposited in sclerotome, which in turn produced chondrogenic/osteogenic-insufficient vertebral growth plates. To test this hypothesis we conducted experiments on chicken embryos with arrest neural crest cell migration by inhibiting expression of Paired-box 3 (Pax3) gene, a known enhancer and promoter of neural crest cells migration and differentiation. The results showed that chicken embryos treated with Pax3 siRNA (microinjection into the neural tube, 44 h post-fertilization) progressively developed scoliotic deformity during maturation. Therefore, this analysis suggests that although adolescent idiopathic scoliosis manifests in children around puberty, the real onset of the disease is of epigenetic nature and takes place in early embryogenesis and involves altered neural crest cells migration. If these results confirmed and further elaborated, the hypothesis may shed new light on the etiology and pathogenesis of AIS.

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

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° with 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.

Etiology of Adolescent Idiopathic Scoliosis: A Literature Review

Adolescent idiopathic scoliosis (AIS) is the peripubertal development of spinal curvature of a minimum of 10°. AIS is thought to be attributable to genetic factors, nutrition, early exposure to toxins, and hormonal dysregulation. Recent literature suggests these factors may compound to determine both disease onset and severity. Currently, treatment is limited to observation, bracing, and surgical intervention. Intervention is presently determined by severity and risk of curve progression. As they emerge, new therapies may target specific etiologies of AIS.

Brace Treatment for Adolescent Idiopathic Scoliosis

In the past, numerous non-operative treatments for adolescent idiopathic scoliosis (AIS), including exercise, physical therapy, electrical stimulation, and brace treatment, have been tried to delay or prevent the curve progression. Of these, brace treatment is the only option that is widely accepted and has demonstrated the efficacy to alter the natural history of AIS. Recently, the importance of brace treatment for AIS has been increasing since the efficacy was objectively established by the BrAIST (Bracing in Adolescent Idiopathic Scoliosis Trial) study in 2013. This editorial article summarizes the current status of brace treatment in patients with AIS and discusses future prospects on the basis of our clinical experiences.

2016 SOSORT guidelines: orthopaedic and rehabilitation treatment of idiopathic scoliosis during growth

BACKGROUND

The International Scientific Society on Scoliosis Orthopaedic and Rehabilitation Treatment (SOSORT) produced its first guidelines in 2005 and renewed them in 2011. Recently published high-quality clinical trials on the effect of conservative treatment approaches (braces and exercises) for idiopathic scoliosis prompted us to update the last guidelines' version. The objective was to align the guidelines with the new scientific evidence to assure faster knowledge transfer into clinical practice of conservative treatment for idiopathic scoliosis (CTIS).

METHODS

Physicians, researchers and allied health practitioners working in the area of CTIS were involved in the development of the 2016 guidelines. Multiple literature reviews reviewing the evidence on CTIS (assessment, bracing, physiotherapy, physiotherapeutic scoliosis-specific exercises (PSSE) and other CTIS) were conducted. Documents, recommendations and practical approach flow charts were developed using a Delphi procedure. The process was completed with the Consensus Session held during the first combined SOSORT/IRSSD Meeting held in Banff, Canada, in May 2016.

RESULTS

The contents of the new 2016 guidelines include the following: background on idiopathic scoliosis, description of CTIS approaches for various populations with flow-charts for clinical practice, as well as literature reviews and recommendations on assessment, bracing, PSSE and other CTIS. The present guidelines include a total of 68 recommendations divided into following topics: bracing (n = 25), PSSE to prevent scoliosis progression during growth (n = 12), PSSE during brace treatment and surgical therapy (n = 6), other conservative treatments (n = 2), respiratory function and exercises (n = 3), general sport activities (n = 6); and assessment (n = 14). According to the agreed strength and level of evidence rating scale, there were 2 recommendations on bracing and 1 recommendation on PSSE that reached level of recommendation "I" and level of evidence "II". Three recommendations reached strength of recommendation A based on the level of evidence I (2 for bracing and one for assessment); 39 recommendations reached strength of recommendation B (20 for bracing, 13 for PSSE, and 6 for assessment).The number of paper for each level of evidence for each treatment is shown in Table 8.

CONCLUSION

The 2016 SOSORT guidelines were developed based on the current evidence on CTIS. Over the last 5 years, high-quality evidence has started to emerge, particularly in the areas of efficacy of bracing (one large multicentre trial) and PSSE (three single-centre randomized controlled trials). Several grade A recommendations were presented. Despite the growing high-quality evidence, the heterogeneity of the study protocols limits generalizability of the recommendations. There is a need for standardization of research methods of conservative treatment effectiveness, as recognized by SOSORT and the Scoliosis Research Society (SRS) non-operative management Committee.

Replication of Association Between 53 Single-Nucleotide Polymorphisms in a DNA-Based Diagnostic Test and AIS Progression in Chinese Han Population

STUDY DESIGN

A case-only study.

OBJECTIVE

The aim of this study was to evaluate the association of the 53 single-nucleotide polymorphisms (SNPs) in a prognostic test with curve progression in Chinese adolescent idiopathic scoliosis (AIS) patients.

SUMMARY OF BACKGROUND DATA

"ScoliScore" was the first diagnostic kit developed for curve progression of AIS in the white population. To date, there is still a paucity of validation of ScoliScore in Chinese Han population.

METHODS

A total of 670 AIS patients were included in the study, with 313 patients assigned to the nonprogression group and the other 357 patients assigned to the progression group. A panel of 53 SNPs encompassed in ScoliScore were genotyped using the PCR-based Invader assay. The allele frequencies were compared between AIS patients with progressive curve and those with nonprogressive curve.

RESULTS

SNP rs9945359 and rs17044552 are the only 2 SNPs that had significantly different allele frequencies between the 2 groups. Allele A of rs9945359 was significantly higher in the progression group than in the nonprogression group (25.7% vs 19.5%, P = 0.01), and allele A of rs17044552 was significantly lower in the progression group (11.5% vs 16.4%, P = 0.01). The odds ratio (OR) of these 2 SNPs were 1.42 [95% confidence interval (95% CI) 1.09-1.88] and 0.65 (95% CI 0.47-0.91), respectively. As for the allele frequencies of the other 51 SNPs, no significant difference was found between the 2 groups.

CONCLUSION

ScoliScore could not be able to predict the curve progression of AIS in Chinese Han population. However, the role of this test in other populations cannot be totally excluded, and additional replication studies in other ethnic groups are warranted to evaluate the significance of these SNPs.

LEVEL OF EVIDENCE

4.

Predictors of spine deformity progression in adolescent idiopathic scoliosis: A systematic review with meta-analysis

AIM: To evaluate published data on the predictors of progressive adolescent idiopathic scoliosis (AIS) in order to evaluate their efficacy and level of evidence.

METHODS: Selection criteria: (1) study design: randomized controlled clinical trials, prospective cohort studies and case series, retrospective comparative and none comparative studies; (2) participants: adolescents with AIS aged from 10 to 20 years; and (3) treatment: observation, bracing, and other. Search method: Ovid MEDLINE, Embase, the Cochrane Library, PubMed and patent data bases. All years through August 2014 were included. Data were collected that showed an association between the studied characteristics and the progression of AIS or the severity of the spine deformity. Odds ratio (OR), sensitivity, specificity, positive and negative predictive values were also collected. A meta-analysis was performed to evaluate the pooled OR and predictive values, if more than 1 study presented a result. The GRADE approach was applied to evaluate the level of evidence.

RESULTS: The review included 25 studies. All studies showed statistically significant or borderline association between severity or progression of AIS with the following characteristics: (1) An increase of the Cobb angle or axial rotation during brace treatment; (2) decrease of the rib-vertebral angle at the apical level of the convex side during brace treatment; (3) initial Cobb angle severity (> 25^o); (4) osteopenia; (5) patient age < 13 years at diagnosis; (6) premenarche status; (7) skeletal immaturity; (8) thoracic deformity; (9) brain stem vestibular dysfunction; and (10) multiple indices combining radiographic, demographic, and physiologic characteristics. Single nucleotide polymorphisms of the following genes: (1) calmodulin 1; (2) estrogen receptor 1; (3) tryptophan hydroxylase 1; (3) insulin-like growth factor 1; (5) neurotrophin 3; (6) interleukin-17 receptor C; (7) melatonin receptor 1B, and (8) ScoliScore test. Other predictors included: (1) impairment of melatonin signaling in osteoblasts and peripheral blood mononuclear cells (PBMC); (2) G-protein signaling dysfunction in PBMC; and (3) the level of platelet calmodulin. However, predictive values of all these findings were limited, and the levels of evidence were low. The pooled result of brace treatment outcomes demonstrated that around 27% of patents with AIS experienced exacerbation of the spine deformity during or after brace treatment, and 15% required surgical correction. However, the level of evidence is also low due to the limitations of the included studies.

CONCLUSION: This review did not reveal any methods for the prediction of progression in AIS that could be recommended for clinical use as diagnostic criteria.