Spinal–pelvic parameters are utilized in orthopedics for assessing patients’ curvature and body alignment in diagnosing, treating, and planning surgeries for spinal and pelvic disorders. Segmenting and autodetecting the whole spine from lateral radiographs is challenging. Recent efforts have employed deep learning techniques to automate the segmentation and analysis of whole-spine lateral radiographs. This study aims to develop an artificial intelligence (AI)-based deep learning approach for the automated segmentation, alignment, and measurement of spinal–pelvic parameters through whole-spine lateral radiographs. We conducted the study on 932 annotated images from various spinal pathologies. Using a deep learning (DL) model, anatomical landmarks of the cervical, thoracic, lumbar vertebrae, sacrum, and femoral head were automatically distinguished. The algorithm was designed to measure 13 radiographic alignment and spinal–pelvic parameters from the whole-spine lateral radiographs. Training data comprised 748 digital radiographic (DR) X-ray images, while 90 X-ray images were used for validation. Another set of 90 X-ray images served as the test set. Inter-rater reliability between orthopedic spine specialists, orthopedic residents, and the DL model was evaluated using the intraclass correlation coefficient (ICC). The segmentation accuracy for anatomical landmarks was within an acceptable range (median error: 1.7–4.1 mm). The inter-rater reliability between the proposed DL model and individual experts was fair to good for measurements of spinal curvature characteristics (all ICC values > 0.62). The developed DL model in this study demonstrated good levels of inter-rater reliability for predicting anatomical landmark positions and measuring radiographic alignment and spinal–pelvic parameters. Automated segmentation and analysis of whole-spine lateral radiographs using deep learning offers a promising tool to enhance accuracy and efficiency in orthopedic diagnostics and treatments.

Objective: The world population gradually getting older, age-related sarcopenia is becoming more frequent. Known to be highly prevalent in high income countries, relative data in Africa are still scarce. This review aims to estimate the prevalence of sarcopenia in Africa and its characteristics. Study Design and Setting: A literature search in PubMed, Web of Science, Google Scholar, and Scopus was conducted in October 2022. All studies reporting the prevalence of sarcopenia in Africa within 15 years were included, and we did an assessment of bias with Hoy et al’s risk bias assessment tool. The estimated prevalence of sarcopenia was the outcome and we performed secondary analyses by age, gender, and diagnostic criteria. The random effect model was used for the prevalence estimation. The prevalence of sarcopenia and 95% confidence interval (95% CI) were calculated using the inverse-variance method. Results: A total of 17 studies met our eligibility criteria, for a study population of 12,690 participants with 44.3% males and 55.7% females. The overall prevalence of sarcopenia was 25% (95% CI: 19– 30%). The prevalence of sarcopenia among 50 years old and older was 23% (95% CI: 17– 29%). We had a higher prevalence of sarcopenia among males (30%, %95 IC: 20– 39%) than females (29%, %95 IC: 21– 36%). The prevalence of sarcopenia was different depending on the diagnosis criteria used. Conclusion: The prevalence of sarcopenia in Africa was relatively high. However, the fact that the majority of included studies were hospital-based studies shows the necessity of further community-based studies in order to have a more accurate representation of the situation in the general population.

Purpose: Studies on the incidence and mortality of refractures after primary osteoporotic fracture are limited by the relatively rare incidence of such refractures and small sample sizes. The objectives of this research were: 1) to determine the incidence of osteoporotic refractures and fracture locations and 2) to assess mortality rates associated with osteoporotic refracture over a median follow up of 3 years using nationwide claim database. Materials and Methods: Patients over 50 years of age who had an osteoporotic fracture that was confirmed operationally were enrolled. Refracture was defined as that after 6 months of an untreated period. Mortality rate was calculated using the Charlson comorbidity index and was analyzed using Cox proportional hazards regression analysis. Results: A total of 18956 first-time instances of osteoporotic fracture were reported between 2007 and 2012 after a median follow up of 3.1 years (range, 1 to 7 years). Among 18956 patients, 2941 (15.50%) experienced refracture. After follow up for 1 year, cumulative mortality rates for re-fracture and non-refracture groups were 9.1% and 7.2%, respectively. After adjusting for covriates, mortality rate was 1.2 times greater in patients with re-fracture than in patients without re-fracture over a median follow up of 3 years (hazard ratio: 1.20, 95% confidence interval: 1.08-1.34, p<0.001). Conclusion: The incidence of osteoporotic re-fracture in this nationwide study was 15.5%, and the mortality rate of re-fracture patients was 1.2 times higher than that of non-refracture patients over a median follow up of 3 years.

Background: Dual energy X-ray absorptiometry (DXA) is a preferred modality for screening or diagnosis of osteoporosis and can predict the risk of hip fracture. However, the DXA test is difficult to implement easily in some developing countries, and fractures have been observed before patients underwent DXA. The purpose of this systematic review is to search for studies that predict the risk of hip fracture using artificial intelligence (AI) or machine learning, organize the results of each study, and analyze the usefulness of this technology.Methods: The PubMed, OVID Medline, Cochrane Collaboration Library, Web of Science, EMBASE, and AHRQ databases were searched including “hip fractures” AND “artificial intelligence”.Results: A total of 7 studies are included in this study. The total number of subjects included in the 7 studies was 330,099. There were 3 studies that included only women, and 4 studies included both men and women. One study conducted AI training after 1:1 matching between fractured and non-fractured patients. The area under the curve of AI prediction model for hip fracture risk was 0.39 to 0.96. The accuracy of AI prediction model for hip fracture risk was 70.26% to 90%.Conclusions: We believe that predicting the risk of hip fracture by the AI model will help select patients with high fracture risk among osteoporosis patients. However, to apply the AI model to the prediction of hip fracture risk in clinical situations, it is necessary to identify the characteristics of the dataset and AI model and use it after performing appropriate validation.

The aim of this study was to evaluate the associations of frailty with perceived neighborhood walkability and environmental pollution among community-dwelling older adults in rural areas. The participants were 808 community-dwelling men and women aged 65 years and older in 2 rural towns. Comprehensive information, including demographics, socioeconomic status, grip strength, polypharmacy, perceived neighborhood environment (specifically, walkability and environmental pollution), and frailty, was collected from participants using face-to-face interviews conducted between June and August 2018. Perceived neighborhood walkability was measured using 20 items that were selected and revised from the Neighborhood Environment Walkability Scale, the Neighborhood Walkability Checklist from the National Heart Foundation of Australia, and the Physical Activity Neighborhood Environment Survey. The Kaigo-Yobo Checklist was used to assess participants' frailty. The overall prevalence of frailty in this community-dwelling population was 35.5%. Sex, age, cohabitation status, educational attainment, employment status, grip strength, and polypharmacy were significantly associated with frailty. In the logistic regression analysis, frailty was associated with low perceived neighborhood walkability (adjusted odds ratio [aOR], 0.881; 95% confidence interval [CI], 0.833 to 0.932; p<0.001) and severe perceived neighborhood environmental pollution (aOR, 1.052; 95% CI, 1.017 to 1.087; p=0.003) after adjusting for sex, age, cohabitation status, educational attainment, employment status, monthly income, grip strength, and polypharmacy. More studies are warranted to establish causal relationships between walkability and environmental pollution and frailty.

Park SH, et al. Yonsei Med J. 2022 Sep;63(9):873-880. https://doi.org/10.3349/ymj.2022.63.9.873