Application of neural networks to the study of the influence of diet and lifestyle on the value of bone mineral density in post-menopausal women

Abstract

a b s t r a c tOsteoporosis is characterized by low bone mineral density (BMD). This illness has a highcost impact in all developed countries. The aim of this article is the development of a mathematical method able to predict the BMD of post-menopausal women, taking into account only certain nutritional variables. This research applies neural networks for the study of the influence of diet and lifestyle on the value of bone mineral density in postmenopausal women.A questionnaire on nutritional habits and lifestyle was drawn up. The variables obtained from this, together with the BMD of the patients calculated by densitometry, were processed using genetic algorithms in order to reduce the number of input variables. Finally, a neural network model using only those variables considered important was applied.It has been proved to be possible to build a neural network model able to forecast the BMD of post-menopausal women according to their responses to the questionnaire. This model can be used to determine which women should take a densitometry in order to verify their bone quality and thus prevent some risks associated with osteoporosis.

Artificial intelligence on the identification of risk groups for osteoporosis, a general review

“…Considering somatic factors, in 2010, Cos Juez et al [ 25 ], developed a mathematical method to identify postmenopausal women with osteoporosis, considering only nutritional factors and lifestyle as influential factors in their diagnosis. The variables obtained through a questionnaire, together with the BMD of the patients calculated by densitometry, were processed using genetic algorithms to identify the most relevant factors in the identification.…”

Application of artificial neural networks to detect bone remodeling changes in diabetes mellitus

“…Много слойный перс епт рон (MLP) -это модель искусственной нейронной сети с прямой связью, которая отображает наборы входных данных в набор соответствующих выходных данных [3,4,5,7]. Многослойный персептрон состоит из линейной функции Применение искусственных нейронных сетей для выявления изменений костного ремоделирования при сахарном диабете С. С. Сафарова, к. м. н, доцент Азербайджанский медицинский университет, г. Баку, Азербайджан…”

Prediction of Neutron Yield of IR-IECF Facility in High Voltages Using Artificial Neural Network

“…What makes a multilayer perceptron a different tool to predict the nonlinear unknown-response systems is that each neuron uses a nonlinear activation function (such as tangent sigmoid), which was developed to model Figure 4: Architecture for the proposed MLP model. the frequency of action potentials, or firing, of biological neurons in the brain [18,19]. The proposed MLP model is shown in Figure 4, where the inputs are discharge current (mA) and voltage (kV) and the output is NPR (n/s).…”