Defining "successful" treatment outcomes in adolescent idiopathic scoliosis: a scoping review

Using artificial intelligence to develop a measure of orthopaedic treatment success from clinical notes

Introduction

A readily available outcome measure that reflects the success of a patient's treatment is needed to demonstrate the value of orthopaedic interventions. Patient-reported outcome measures (PROMs) are survey-based instruments that collect joint-specific and general health perceptions on symptoms, functioning, and health-related quality of life. PROMs are considered the gold standard outcome measure in orthopaedic medicine, but their use is limited in real-world practice due to challenges with technology integration, the pace of clinic workflows, and patient compliance. Clinical notes generated during each encounter patients have with their physician contain rich information on current disease symptoms, rehabilitation progress, and unexpected complications. Artificial intelligence (AI) methods can be used to identify phrases of treatment success or failure captured in clinical notes and discern an indicator of treatment success for orthopaedic patients.

Methods

This was a cross-sectional analysis of clinical notes from a sample of patients with an acute shoulder injury. The study included adult patients presenting to a Level-1 Trauma Center and regional health system for an acute Proximal Humerus Fracture (PHF) between January 1, 2019 and December 31, 2021. We used the progress note from the office visit for PHF-related care (ICD10: S42.2XXX) or shoulder pain (ICD10: M45.2XXX) closest to 1-year after the injury date. Clinical notes were reviewed by an orthopaedic resident and labeled as treatment success or failure. A structured comparative analysis of classifiers including both machine and deep learning algorithms was performed.

Results

The final sample included 868 clinical notes from patients treated by 123 physicians across 35 departments within one regional health system. The study sample was stratified into 465 notes labeled as treatment success and 403 labeled as treatment failure. The Bio-ClinicalBERT model had the highest performance of 87% accuracy (AUC = 0.87 ± 0.04) in correctly distinguishing between treatment success and failure notes.

Discussion

Our results suggest that text classifiers applied to clinical notes are capable of differentiating patients with successful treatment outcomes with high levels of accuracy. This finding is encouraging, signaling that routinely collected clinical note content may serve as a data source to develop an outcome measure for orthopaedic patients.

Design and development of an intelligent wearing system for adolescent spinal orthotics

Adolescent idiopathic scoliosis is the deformity of the human spine in three-dimensional space. It is a disease with a long course and difficult to recover in a short time. Currently, spinal orthotic braces are an effective non-surgical treatment for this condition. However, existing spinal orthotic braces are still deficient. For example, existing spinal orthotics braces have no way of knowing how correct, effective, and comfortable a patient is wearing the orthotics. Based on distributed pressure monitoring technology, this paper conducts pressure acquisition and compensation research on spinal orthotics used by adolescent patients. After analyzing the principles of orthopedics and selecting monitoring points, this paper selects appropriate sensors and calibrates them. An intelligent wearable system for adolescent spinal orthotics was developed based on these findings. The experimental results show that the system can effectively monitor the process of patients wearing spinal orthotic braces. In addition, the system can compensate and visualize the pressure in real-time, so that doctors and patients can know the process and make judgments and adjustments.

Higher Baseline Serum Myokine of FSTL1 May Serve as a Potential Predictive Biomarker for Successful Brace Treatment in Girls With Adolescent Idiopathic Scoliosis

STUDY DESIGN

A retrospective case-control study.

OBJECTIVE

This study aimed to investigate whether myokine, which is related to exercise and muscle mass, could serve as a biomarker for predicting bracing outcomes.

SUMMARY OF BACKGROUND DATA

Several risk factors have been documented to be associated with bracing failure in patients with adolescent idiopathic scoliosis (AIS). However, serum biomarkers have not been extensively explored.

PATIENTS AND METHODS

Skeletally immature females with AIS, without previous histories of bracing or surgery, were included. Peripheral blood was collected at the time of the bracing prescription. Baseline serum concentrations of 8 myokines [apelin, fractalkine, brain-derived neurotrophic factor, erythropoietin, osteonectin, fatty-acid-binding protein 3, follistatin-like 1 (FSTL1), and musclin] were measured by multiplex assays. Patients were followed up until weaned from bracing and then designated as a "failure" (defined as Cobb angle progression >5°) or "success." A logistic regression analysis was performed that accounted for serum myokines and skeletal maturity.

RESULTS

We included 117 patients, with 27 in the failure group. Patients in the failure group had lower initial Risser sign and lower baseline serum levels of myokines, including FSTL1 (2217.3 ± 617.0 vs . 1369.3 ± 704.9, P = 0.002), apelin [116.5 (12.0, 335.9) vs . 83.5 (10.5, 221.1), P = 0.016], fractalkine (979.6 ± 457.8 vs . 743.8 ± 456.1, P = 0.020), and musclin [211.3 (16.3, 370.3) vs . 67.8 (15.5, 325.6), P = 0.049]. Following adjusted analysis, serum FSTL1 [odds ratio = 10.460; (2.213-49.453)] was determined to be predictive of bracing effectiveness.

CONCLUSION

Patients who failed AIS bracing had significantly lower mean baseline levels of FSTL1 than those who achieved success. FSTL1 may serve as a biomarker that can inform outcomes after bracing.

Adolescent idiopathic scoliosis is associated with muscle area asymmetries in the lumbar spine

PURPOSE

While the etiopathogenesis of adolescent idiopathic scoliosis (AIS) remains unclear, it is assumed that muscular asymmetries contribute to curve progression. As previous studies have found asymmetries of the thoracic paraspinal muscles in AIS patients, our study's aim was to analyze differences in the erector spinae, multifidus, quadratus lumborum, and psoas muscles of the lumbar spine depending on the curve's radiographic characteristics.

METHODS

We retrospectively included all patients who received posterior reposition spondylodesis for AIS treatment at our institution. Patients were classified according to the Lenke classification. Muscle cross-sectional areas were obtained from magnetic resonance imaging of the lumbar spine. Data were analyzed with the Wilcoxon rank sum test, the Kruskal-Wallis test with post hoc testing, or the Spearman's correlation coefficient.

RESULTS

Seventy-four (14 males and 60 females) AIS patients with a median age of 16 (IQR ± 4) years and a mean Cobb angle of 56.0° (± 18.0°) were included. In curve types Lenke 1 and 2 (n = 45), the erector spinae (p < 0.001) and multifidus (p < 0.001) muscles had a significantly larger cross-sectional area on the convex side, whereas the quadratus lumborum (p = 0.034) and psoas (p < 0.001) muscles each had a significantly larger cross-sectional area on the lumbar contralateral side.

CONCLUSION

Our results show an asymmetry of the lumbar spine's muscles which depends on both the convexity and the extent of the scoliotic curve. While our results cannot prove whether these differences are the deformity's cause or effect, they may contribute to a better understanding of AIS pathogenesis and may allow for more specific preoperative physiotherapy.