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.

双能 X 射线吸收测定法 (DXA) 在测量骨矿物质密度 (BMD) 和评估骨折风险方面并未得到充分利用。我们提出了一种自动化工具，可以使用平片来识别骨折、预测 BMD 并评估骨折风险。该工具的性能在 5164 名和 18175 名患者的骨盆/腰椎 X 光片和 Hologic DXA 上进行了评估。该模型经过良好校准，髋部（斜率 = 0.982，大校准 = -0.003）和腰椎 BMD（斜率 = 0.978，大校准 = 0.003）偏差最小。髋部骨质疏松的精确回忆曲线下面积和准确度分别为 0.89 和 91.7%，脊柱骨质疏松为 0.89 和 86.2%，10 年重大骨折高风险为 0.83 和 95.0%，髋部骨折高风险为 0.96 和 90.0% 。该工具对 5206 名 (84.8%) 患者进行了分类，骨质疏松症的阳性或阴性预测值为 95%，而同一研究期间进行的 DXA 为 3008 名。这种自动化工具可能有助于识别骨质疏松症的高危患者。