Despite extensive experimental and animal evidence about the detrimental effects of iron and its overload on bone metabolism, there have been no clinical studies relating iron stores to bone loss, especially in nonpathologic conditions. In the present study, we performed a large longitudinal study to evaluate serum ferritin concentrations in relation to annualized changes in bone mineral density (BMD) in healthy Koreans. A total of 1729 subjects (940 postmenopausal women and 789 middle‐aged men) aged 40 years or older who had undergone comprehensive routine health examinations with an average 3 years of follow‐up were enrolled. BMD in proximal femur sites (ie, the total femur, femur neck, and trochanter) was measured with dual‐energy X‐ray absorptiometry using the same equipment at baseline and follow‐up. The mean age of women and men in this study was 55.8 ± 6.0 years and 55.5 ± 7.8 years, respectively, and serum ferritin levels were significantly higher in men than in women (p < 0.001). The overall mean annualized rates of bone loss in the total femur, femur neck, and trochanter were −1.14%/year, −1.17%/year, and −1.51%/year, respectively, in women, and −0.27%/year, −0.34%/year, and −0.41%/year, respectively, in men. After adjustment for potential confounders, the rates of bone loss in all proximal femur sites in both genders were significantly accelerated in a dose‐response fashion across increasing ferritin quartile categories (p for trend = 0.043 to <0.001). Consistently, compared with subjects in the lowest ferritin quartile category, those in the third and/or highest ferritin quartile category showed significantly faster bone loss in the total femur and femur neck in both genders (p = 0.023 to <0.001). In conclusion, these data provide the first clinical evidence that increased total body iron stores could be an independent risk factor for accelerated bone loss, even in healthy populations. © 2012 American Society for Bone and Mineral Research.

Osteoporosis is a common, but silent disease until it is complicated by fractures that are associated with morbidity and mortality. Over the past few years, although deep learning-based disease diagnosis on chest radiographs has yielded promising results, osteoporosis screening remains unexplored. Paired data with 13,026 chest radiographs and dual-energy X-ray absorptiometry (DXA) results from the Health Screening and Promotion Center of Asan Medical Center, between 2012 and 2019, were used as the primary dataset in this study. For the external test, we additionally used the Asan osteoporosis cohort dataset (1089 chest radiographs, 2010 and 2017). Using a well-performed deep learning model, we trained the OsPor-screen model with labels defined by DXA based diagnosis of osteoporosis (lumbar spine, femoral neck, or total hip T-score ≤ −2.5) in a supervised learning manner. The OsPor-screen model was assessed in the internal and external test sets. We performed substudies for evaluating the effect of various anatomical subregions and image sizes of input images. OsPor-screen model performances including sensitivity, specificity, and area under the curve (AUC) were measured in the internal and external test sets. In addition, visual explanations of the model to predict each class were expressed in gradient-weighted class activation maps (Grad-CAMs). The OsPor-screen model showed promising performances. Osteoporosis screening with the OsPor-screen model achieved an AUC of 0.91 (95% confidence interval [CI], 0.90–0.92) and an AUC of 0.88 (95% CI, 0.85–0.90) in the internal and external test set, respectively. Even though the medical relevance of these average Grad-CAMs is unclear, these results suggest that a deep learning-based model using chest radiographs could have the potential to be used for opportunistic automated screening of patients with osteoporosis in clinical settings. © 2021 American Society for Bone and Mineral Research (ASBMR).