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

Background: The risk of bone mineral density abnormalities is inconsistent between eastern and western regions owing to differences in ethnicity and dietary habits. A diet comprising carbohydrates and dietary fiber is not the common daily diet of the American population. Thus far, no studies have assessed the risk of bone mineral density abnormalities in the American population, and no predictive model has considered the intake of carbohydrates, dietary fiber, and coffee, as well as levels of various electrolytes for assessing bone mineral density abnormalities, especially in the elderly. This study conducted a neural network analysis and established a predictive nomogram considering an unusual diet to determine risk factors for bone mineral density abnormalities in the American population, mainly to provide a reference for the prevention and treatment of related bone mineral density abnormalities. Methods: Overall, 9871 patients who had complete data were selected from the National Health and Nutrition Examination Survey database during 2017-2020 as the research object, and patients' general clinical characteristics were compared. Neural networks and nomograms were analyzed to screen for and quantify risk factors for bone mineral density abnormalities. Finally, the receiver operating characteristic (ROC) curve, calibration curve, decision curve analysis (DCA), and community indifference curve (CIC) were constructed to comprehensively verify the accuracy, differential ability, and clinical practicability of the neural network and nomogram. Results: The important risk factors for bone mineral density abnormalities were caffeine intake, carbohydrate consumption, body mass index (BMI), height, blood sodium, blood calcium, blood phosphorus, blood potassium, dietary fiber, vitamin D, participant age, weight, race, family history, and sex. The nomogram revealed that caffeine intake, carbohydrate consumption, blood potassium, and age were positively correlated with bone mineral density abnormalities, whereas BMI, height, blood phosphate, dietary fiber, and blood sodium were negatively correlated with bone mineral density abnormalities. Women were more prone to these abnormalities than men. The area under the ROC curve values of the neural network and nomogram were 85.8 % and 77.7 %, respectively. The Youden index was 58.04 % and 41.87 %, respectively. The detection sensitivity was 75.73 % and 65.06 %, respectively, and the specificity was 82.31 % and 76.81 %, respectively. Calibration curves of the neural network and nomogram showed better discrimination ability from the standard curve (P > 0.05). DCA and CIC analyses showed that the application of the neural network and nomogram to explore risk factors for bone mineral density abnormalities had certain clinical practicability, and the overall predictive effect of the model was good. Conclusion: The outcomes of the neural network and nomogram analyses suggested that diet structure and electrolyte changes are important significant risk factors for bone mineral density abnormalities, especially with increasing carbohydrate and caffeine intake and decreasing dietary fiber intake. The established model can also provide a reference for future risk prediction.