Osteoporosis

Application of neural network and nomogram for the prediction of risk factors for bone mineral density abnormalities: A cross-sectional NHANES-based survey

“…Although osteoporosis and osteopenia greatly increase bone fragility [ 13 ], they do not cause any evident symptoms in the early stage; therefore, they are not diagnosed until complications such as spinal or limb fractures occur [ 14 ], which seriously affect patients' health condition and quality of life, necessitating the importance of timely diagnosis and treatment of osteoporosis and osteopenia in the early stage [ 15 ]. Many studies have applied algorithms and evaluation tools based on public awareness of osteoporosis and osteopenia risk factors such as age, sex, family history of patients’ fractures, use of glucocorticoids and vitamin D, blood calcium, and other indicators [ 16 ] such as fracture risk assessment tool in the clinical setting [ 17 , 18 ], which indeed provides a reference to assess the risk of bone mineral density abnormalities in a certain population [ 19 ], but the evidence is not comprehensive. Taking the American population as an example, this study included the intake of carbohydrates, dietary fiber, coffee, and other dietary components, as well as the levels of electrolytes such as blood phosphorus, blood potassium, and blood sodium, which may be deficient in abnormalities, as research factors; next, the neural network and nomogram were integrated to establish a prediction model to provide a reference for people who are accustomed to consuming carbohydrates, dietary fiber, coffee, and other dietary components.…”