Dataset Information

Automated bone mineral density prediction and fracture risk assessment using plain radiographs via deep learning.

ABSTRACT: Dual-energy X-ray absorptiometry (DXA) is underutilized to measure bone mineral density (BMD) and evaluate fracture risk. We present an automated tool to identify fractures, predict BMD, and evaluate fracture risk using plain radiographs. The tool performance is evaluated on 5164 and 18175 patients with pelvis/lumbar spine radiographs and Hologic DXA. The model is well calibrated with minimal bias in the hip (slope = 0.982, calibration-in-the-large = -0.003) and the lumbar spine BMD (slope = 0.978, calibration-in-the-large = 0.003). The area under the precision-recall curve and accuracy are 0.89 and 91.7% for hip osteoporosis, 0.89 and 86.2% for spine osteoporosis, 0.83 and 95.0% for high 10-year major fracture risk, and 0.96 and 90.0% for high hip fracture risk. The tool classifies 5206 (84.8%) patients with 95% positive or negative predictive value for osteoporosis, compared to 3008 DXA conducted at the same study period. This automated tool may help identify high-risk patients for osteoporosis.

SUBMITTER: Hsieh CI

PROVIDER: S-EPMC8446034 | biostudies-literature | 2021 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated bone mineral density prediction and fracture risk assessment using plain radiographs via deep learning.

Hsieh Chen-I CI Zheng Kang K Lin Chihung C Mei Ling L Lu Le L Li Weijian W Chen Fang-Ping FP Wang Yirui Y Zhou Xiaoyun X Wang Fakai F Xie Guotong G Xiao Jing J Miao Shun S Kuo Chang-Fu CF

Nature communications 20210916 1

Dual-energy X-ray absorptiometry (DXA) is underutilized to measure bone mineral density (BMD) and evaluate fracture risk. We present an automated tool to identify fractures, predict BMD, and evaluate fracture risk using plain radiographs. The tool performance is evaluated on 5164 and 18175 patients with pelvis/lumbar spine radiographs and Hologic DXA. The model is well calibrated with minimal bias in the hip (slope = 0.982, calibration-in-the-large = -0.003) and the lumbar spine BMD (slope = 0.9 ...[more]

PMID: 34531406

Similar Datasets

Project description:ImportanceScreening for osteoporosis with bone mineral density (BMD) is recommended for older adults. It is unclear whether repeating a BMD screening test improves fracture risk assessment.ObjectivesTo determine whether changes in BMD after 4 years provide additional information on fracture risk beyond baseline BMD and to quantify the change in fracture risk classification after a second BMD measure.Design, setting, and participantsPopulation-based cohort study involving 310 men and 492 women from the Framingham Osteoporosis Study with 2 measures of femoral neck BMD taken from 1987 through 1999.Main outcomes and measuresRisk of hip or major osteoporotic fracture through 2009 or 12 years following the second BMD measure.ResultsMean age was 74.8 years. The mean (SD) BMD change was -0.6% per year (1.8%). Throughout a median follow-up of 9.6 years, 76 participants experienced an incident hip fracture and 113 participants experienced a major osteoporotic fracture. Annual percent BMD change per SD decrease was associated with risk of hip fracture (hazard ratio [HR], 1.43 [95% CI, 1.16 to 1.78]) and major osteoporotic fracture (HR, 1.21 [95% CI, 1.01 to 1.45]) after adjusting for baseline BMD. At 10 years' follow-up, 1 SD decrease in annual percent BMD change compared with the mean BMD change was associated with 3.9 excess hip fractures per 100 persons. In receiver operating characteristic (ROC) curve analyses, the addition of BMD change to a model with baseline BMD did not meaningfully improve performance. The area under the curve (AUC) was 0.71 (95% CI, 0.65 to 0.78) for the baseline BMD model compared with 0.68 (95% CI, 0.62 to 0.75) for the BMD percent change model. Moreover, the addition of BMD change to a model with baseline BMD did not meaningfully improve performance (AUC, 0.72 [95% CI, 0.66 to 0.79]). Using the net reclassification index, a second BMD measure increased the proportion of participants reclassified as high risk of hip fracture by 3.9% (95% CI, -2.2% to 9.9%), whereas it decreased the proportion classified as low risk by -2.2% (95% CI, -4.5% to 0.1%).Conclusions and relevanceIn untreated men and women of mean age 75 years, a second BMD measure after 4 years did not meaningfully improve the prediction of hip or major osteoporotic fracture. Repeating a BMD measure within 4 years to improve fracture risk stratification may not be necessary in adults this age untreated for osteoporosis.

Project description:BackgroundDisordered mineral metabolism reverses incompletely after kidney transplantation in numerous patients. Post-transplantation bone disease is a combination of pre-existing chronic kidney disease and mineral disorder and often evolving osteoporosis. These two frequently overlapping conditions increase the risk of post-transplantation fractures.Material and methodsWe studied the prevalence of low bone volume in bone biopsies obtained from kidney transplant recipients who were biopsied primarily due to the clinical suspicion of persistent hyperparathyroidism between 2000 and 2015 at the Hospital District of Helsinki and Uusimaa. Parameters of mineral metabolism, results of dual-energy x-ray absorptiometry scans, and the history of fractures were obtained concurrently. One hundred nine bone biopsies taken at a median of 31 (interquartile range, IQR, 18-70) months after transplantation were included in statistical analysis. Bone turnover was classified as high in 78 (72%) and normal/low in 31 (28%) patients. The prevalence of low bone volume (n = 47, 43%) was higher among patients with low/normal turnover compared to patients with high turnover [18 (58%) vs. 29 (37%), P = 0.05]. Thirty-seven fragility fractures in 23 (21%) transplant recipients corresponding to fracture incidence 15 per 1000 person-years occurred during a median follow-up 9.1 (IQR, 6.3-12.1) years. Trabecular bone volume did not correlate with incident fractures. Accordingly, low bone mineral density at the lumbar spine correlated with low trabecular bone volume, but not with incident fractures. The cumulative corticosteroid dose was an important determinant of low bone volume, but not of incident fractures.ConclusionsDespite the high prevalence of trabecular bone loss among kidney transplant recipients, the number of fractures was limited. The lack of association between trabecular bone volume and fractures suggests that the bone cortical compartment and quality are important determinants of bone strength and post-transplantation fracture.

Project description:In adult hypophosphatasia (HPP) patients, elevated lumbar spine dual X-ray absorptiometry (DXA) values are associated with markers of disease severity and disease-specific fracture risk while femoral bone mineral density (BMD), being largely unaffected by the disease severity, may still be useful to monitor other causes of increased fracture risk due to low BMD.IntroductionHypophosphatasia (HPP) is a rare inherited metabolic disorder due to deficient activity of the tissue-nonspecific alkaline phosphatase (TNAP). Clinical manifestation in adult HPP patients is manifold including an increased risk for fractures, but data regarding clinical significance of DXA measurement and associations with fracture risk and disease severity is scarce.MethodsRetrospective single-center analysis of DXA scans in patients with confirmed HPP (documented mutation, clinical symptoms, low alkaline phosphatase activity). Further data evaluation included disease-related fractures, laboratory results (alkaline phosphatase, pyridoxalphosphate, phosphoethanolamine), and medical history.ResultsAnalysis included 110 patients (84 female, mean age of 46.2 years) of whom 37.3% (n = 41) were harboring two mutations. Average T-Score level at the lumbar spine was - 0.1 (SD 1.9), and mean total hip T-Score was - 1.07 (SD 0.15). Both lower ALP activity and higher substrate levels (pyridoxalphosphate and phosphoethanolamine) were significantly correlated with increased lumbar spine T-Score levels (p < 0.001) while BMD at the hip was not affected by indicators of disease severity. Increased lumbar spine BMD was significantly associated with an increased risk for HPP-related fractures, prevalent in 22 (20%) patients (p < 0.001) with 21 of them having biallelic mutations.ConclusionBMD in adult HPP patients is not systematically reduced. Conversely, increased lumbar spine BMD appears to be associated with severely compromised mineralization and increased risk for HPP-related fractures while BMD at the hip appears unaffected by indicators of disease severity, suggesting suitability of this anatomic location for assessing and discerning disorders with increased fracture risk owing to reduced BMD like osteoporosis.Trial registration numberGerman register for clinical studies (DRKS00014022) DATE OF REGISTRATION: 02/10/2018 - retrospectively registered.

Dataset Information

Automated bone mineral density prediction and fracture risk assessment using plain radiographs via deep learning.

Publications

Automated bone mineral density prediction and fracture risk assessment using plain radiographs via deep learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets