Artificial neural networks became an attractive alternative for modeling and simulation of com- plex biological systems. In the present work, a blood plasma model based on artificial neural networks was proposed in or...Artificial neural networks became an attractive alternative for modeling and simulation of com- plex biological systems. In the present work, a blood plasma model based on artificial neural networks was proposed in order to evaluate the relationship between the magnesium ion pre-sent in the blood plasma and systolic blood pressure and glucose. Experimental and simu- lated data were used to construct and validate the model. It performed the analysis consider-ing the systolic blood pressure and glucose as a function of magnesium ion concentration at a fixed temperature (37oC). Predictions of these relationships through the proposed model produced errors, on average, below 1% com-pared against experimental data not presented in the training step. The proposed methodology revealed quantitative results and correctly pre-dicted behaviors and trends towards the asso-ciation between magnesium concentrations and systolic blood pressure, and glucose in far agreement with experimental results from lit-erature. These results indicated that artificial neural networks can successfully learn the complexity of the relationships among bio-logical parameters of distinct groups and can be used as a complementary tool to assist studies in which the role of magnesium in systolic blood pressure and glucose are con-sidered.展开更多
文摘Artificial neural networks became an attractive alternative for modeling and simulation of com- plex biological systems. In the present work, a blood plasma model based on artificial neural networks was proposed in order to evaluate the relationship between the magnesium ion pre-sent in the blood plasma and systolic blood pressure and glucose. Experimental and simu- lated data were used to construct and validate the model. It performed the analysis consider-ing the systolic blood pressure and glucose as a function of magnesium ion concentration at a fixed temperature (37oC). Predictions of these relationships through the proposed model produced errors, on average, below 1% com-pared against experimental data not presented in the training step. The proposed methodology revealed quantitative results and correctly pre-dicted behaviors and trends towards the asso-ciation between magnesium concentrations and systolic blood pressure, and glucose in far agreement with experimental results from lit-erature. These results indicated that artificial neural networks can successfully learn the complexity of the relationships among bio-logical parameters of distinct groups and can be used as a complementary tool to assist studies in which the role of magnesium in systolic blood pressure and glucose are con-sidered.
