Identification of asymptomatic vertebral compression fracture using a novel shape-based algorithm

Abstract Background: Vertebral fracture is both common and serious among adults, yet it often goes undiagnosed. The aims of this study were to develop a shape-based algorithm (SBA) for the automatic identification of vertebral fractures. Results: At the person level, the SBA achieved a sensitivity of 100% and specificity of 61% (95% CI, 51-72%). At the vertebral level, the SBA achieved a sensitivity of 84% (95% CI, 72% to 93%), a specificity of 88% (95% CI, 85% to 90%). On average, the SBA took 0.3 seconds to assess one X-ray. Conclusions: The SBA developed here is a fast and efficient tool that can be used to systematically screen for asymptomatic vertebral fractures and reduce the workload of healthcare professionals. Methods: The study included 50participants whose plain thoracolumbar spine X-rays (n = 144) were taken. Clinical diagnosis of vertebral fracture (grade 0 to 3) was made by rheumatologists using Genant's semiquantitative method. The SBA algorithm was developed to determinethe ratio of vertebral body height loss. Based on the ratio, SBA classifies a vertebra into 4 classes: 0=normal, 1=mild fracture, 2=moderate fracture, 3=severe fracture). The concordance between clinical diagnosis and SBA-based classification was assessed at both personal and vertebral levels.