Vertebral Fractures among Patients Referred for Bone Densitometry Screening in Dubai Primary Health Care Facilities

Osteoporotic hip and vertebral fractures in the Arab region: a systematic review

Asia is projected to account for the largest proportion of the rising burden of osteoporotic fractures worldwide. Data from the Middle East is scarce. We performed a systematic review on the epidemiology of vertebral and hip osteoporotic fractures in 22 Arab League countries, using Scopus, PubMed, and Embase. We identified 67 relevant publications, 28 on hip and 39 on vertebral fractures. The mean age of patients was 70-74 years, female to male ratio 1.2:2.1. Age-standardized incidence rates, to the UN 2010 population, were 236 to 290/100,000 for women from Kuwait and Lebanon, lower in Morocco. Risk factors for hip fractures included lower BMD or BMI, taller stature, anxiolytics, and sleeping pills. Most patients were not tested nor treated. Mortality derived from retrospective studies ranged between 10 and 20% at 1 year, and between 25 and 30% at 2-3 years. Among 39 studies on vertebral fractures, 18 described prevalence of morphometric fractures. Excluding grade 1 fractures, 13.3-20.2% of women, mean age 58-74 years, had prevalent vertebral fractures, as did 10-14% of men, mean age 62-74 years. Risk factors included age, gender, smoking, multiparity, years since menopause, low BMD, bone markers, high sclerostin, low IgF1, hypovitaminosis D, abdominal aortic calcification score, and VDR polymorphisms. Vertebral fracture incidence in women from Saudi Arabia, mean age 61, was 6.2% at 5 years, including grade 1 fractures. Prospective population-based fracture registries, prevalence studies, predictive models, fracture outcomes, and fracture liaison services from Arab countries are still lacking today. They are the pillars to closing the care gap of this morbid disease.

Artificial intelligence for the detection of vertebral fractures on plain spinal radiography

Vertebral fractures (VFs) cause serious problems, such as substantial functional loss and a high mortality rate, and a delayed diagnosis may further worsen the prognosis. Plain thoracolumbar radiography (PTLR) is an essential method for the evaluation of VFs. Therefore, minimizing the diagnostic errors of VFs on PTLR is crucial. Image identification based on a deep convolutional neural network (DCNN) has been recognized to be potentially effective as a diagnostic strategy; however, the accuracy for detecting VFs has not been fully investigated. A DCNN was trained with PTLR images of 300 patients (150 patients with and 150 without VFs). The accuracy, sensitivity, and specificity of diagnosis of the model were calculated and compared with those of orthopedic residents, orthopedic surgeons, and spine surgeons. The DCNN achieved accuracy, sensitivity, and specificity rates of 86.0% [95% confidence interval (CI) 82.0-90.0%], 84.7% (95% CI 78.8-90.5%), and 87.3% (95% CI 81.9-92.7%), respectively. Both the accuracy and sensitivity of the model were suggested to be noninferior to those of orthopedic surgeons. The DCNN can assist clinicians in the early identification of VFs and in managing patients, to prevent further invasive interventions and a decreased quality of life.