Modelling of the relationship between systolic blood pressure and glucose with the magnesium ion present in the blood plasma: an approach using artificial neural networks


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.

Share and Cite:

C. D. Conway, J. , N. Lavorato, S. , F. Cunha, V. and C. Belchior, J. (2009) Modelling of the relationship between systolic blood pressure and glucose with the magnesium ion present in the blood plasma: an approach using artificial neural networks. Health, 1, 211-219. doi: 10.4236/health.2009.13036.

Conflicts of Interest

The authors declare no conflicts of interest.


[1] P. Laurant and R. M. Touyz, (2000) Physiological and pathophysiological role of magnesium in the cardiovascular system: implications in hypertension. J. Hypertens., 18, 1177-1191.
[2] C. S. Yajnik, R. F. Smith, T. D. R. Hockaday, and N. I. Ward, (1984) Fasting plasma magnesium concentrations and glucose disposal in diabetes. Br. Med. J., 288, 1032-1034.
[3] J. A. M. Maier, (2003) Low magnesium and atherosclerosis: an evidence-based link. Mol. Aspects Med., 24, 137-146.
[4] S. Sasaki, T. Oshima, H. Matsuura, R. Ozono, Y. Higashi, N. Sasaki, et al., (2000) Abnormal magnesium status in patients with cardiovascular diseases. Clin. Sci., 98, 175-181.
[5] B. Sontia and R. M. Touyz, (2007) Role of magnesium in hypertension. Arch. Biochem. Biophys., 458, 33-39.
[6] N. E. Saris, E. Mervaala, H. Darppanen, J. A. Khawaja and A. Lewenstam, (2000) Magnesium: an update on physiological, clinical and analytical aspects. Clin. Chim. Acta, 294, 1-26.
[7] M. Speich, B. Bousquet and G. Nicolas, (1981) Reference values for ionized, complexed, and protein-bound plasma magnesium in men and women. Clin. Chem., 27, 246-248.
[8] J. Ma, A. R. Folson, S. L. Melnick, J. H. Eckfeldt, A. R. Sharrett, A. A. Nabulsi, et al., (1995) Associations of serum and dietary magnesium with cardiovascular disease, hyper- tension, diabetes, insulin, and carotid arterial wall thickness: The ARIC Study. J. Clin. Epidemiol., 48, 927-940.
[9] L. M. Resnick, O. Bardice, B. T. Altura, M. H. Alderman and B. M. Altura, (1997) Serum ionized magnesium-relation to blood pressure and racial factors. Amer. J. Hypert., 10, 1420-1424.
[10] R. M. Touyz, F. J. Milne, H. C. Seftel, and K. S. Reinach, (1987) Magnesium, calcium, sodium and potassium status in normotensive and hypertensive Johannesburg residents. S. Afr. Med. J.,72, 377-381.
[11] D. D. Perrin, (1965) Multiple equilibria in assemblages of metal ions and complexing species: a model for biological systems. Nature, 206, 170-178.
[12] D. D. Perrin and I. G. Sayce, (1967) Computer calculation of equilibrium concentrations in mixtures of metal ions and complexing species. Talanta, 14, 833-842.
[13] P. M. May, P. W. Linder, and D. R. Williams, (1977) Computer simulation of metal-ion equilibria in biofluids: models for the low-molecular-weight complex distribution of calcium(II), magnesium(II), manganese(II), iron(III), copper(II), zinc(II), and lead(II) ions in human blood plasma. J. Chem. Soc. Dalton, 6, 588-595.
[14] L. S. Nikolaeva and V. V. Chirkov, (2004) Computer modeling of the influence of ethylenediamine-N, N’-bis (methylenephosphonic acid) on metal-ion equilibria in blood plasma. Russ. J. Inorg. Chem., 49, 1547-1552.
[15] J. P. Wang, H. Y. Zhang, K. Y. Yang, and C. J. Niu, (2004) Computer simulation of Gd(III) speciation in human in-terstitial fluid. Biometals, 17, 599-603.
[16] A. Liparini, S. Carvalho, and J. C. Belchior, (2005) Analysis of the applicability of artificial neural networks for studying blood plasma: determination of magnesium ion concentration as a case study. Clin. Chem. Lab. Med., 43, 939-946.
[17] S. R. Bhatikara, C. Degroffb, and R. L. Mahajana, (2005) A classifier based on the artificial neural network ap-proach for cardiologic auscultation in pediatrics. Artif. Intell. Med., 33, 251-260.
[18] I. Inza, M. Merin, N. P. Larra, J. Quiroga, B. Sierra, and M. Girala, (2001) Feature subset selection by genetic algo-rithms–a case study in the survival of cirrhotic patients treated with tips. Artif. Intell. Med., 23, 187-205.
[19] D. Itchhaporia, P. B. Snow, R. J. Almassy, and W. J. Oet-gen, (1996) Artificial neural networks: Current status in cardiovascular medicine. J. Am. Coll. Cardiol., 28, 515-521.
[20] J. D. Martin, E. Soria, G. Campos, A. J. Serrano, J. R. Sepulveda, and V. Gimenez, (2004) Neural networks as effective techniques in clinical management of patients: some case studies. Trans. Inst. Measur. Control, 26, 169-183.
[21] C. Thang, E. W. Cooper, Y. Hoshino, and K. Kamei, (2005) A decision support system for rheumatic evaluation and treatment in oriental medicine using fuzzy logic and neural network. Lect. Note Artif. Intell., 3558, 399-409.
[22] J. Trujillano, J. March, and A. Sorribas, (2004) Methodo-logical approach to the use of artificial neural networks for predicting results in medicine. Med. Clin., 122, 59-67.
[23] R. Poli, S. Cagnoni, R. Livi, G. Coppini, and G. Valli, (1991) A neural network expert system for diagnosing and treating hypertension. Computer, 24, 64-71.
[24] A. M. Zhai, B. Q. Sun, Y. J. Feng, and H. Q. Wang, (2003) A study on diagnosis of hypertension by intelligent medical diagnostic system. Dyn. Cont. Discr. Imp. Syst. Ser. B, Suppl.S, 478-480.
[25] M. Beksac, M. S. Beksac, V. B. Tipi, H. A. Duru, M. U. Karakas, and A. N. Cakar, (1997), An artificial intelligent diagnostic system on differential recognition of hemato-poietic cells from microscopic images. Cytometric, 30, 145-150.
[26] F. Viazzi, G. Leoncini, G. Sacchi, D. Parodi, E. Ratto, V. Falqui, et al., (2006) Predicting cardiovascular risk using creatinine clearance and an artificial neural network in primary hypertension. J. Hypertens., 24, 1281-1286.
[27] J. C. D. Conway, A. Liparini, J. R. Oliveira Júnior, and J. C. Belchior, (2007) Analyses of the temperature and pH effects on the complexation of the magnesium and cal-cium in human blood plasma: an approach using artificial neural networks. Anal. Bioanal. Chem., 30, 1585-1594.
[28] W. S. McCulloc and W. Pitts, (1943) A logical calculus of the ideas immanent in nervous activity. Bull. Math. Bio-phys., 5, 115-133.
[29] S. Haykin, (1999) Neural networks: A comprehensive foundation. Prentice Hall.
[30] D. W. Marquardt, (1963) An algorithm for least-squares estimation of nonlinear parameters. J. Soc. Indust. Appl. Math., 11, 431-441.
[31] O. D. Williams, (1989) The atherosclerosis risk in commu-nities (ARIC) study: design and objectives. Amer. J. Epidemiol., 129, 687-702.
[32] A. A. Freitas, (2002) Data mining and knowledge dis-covery with evolutionary algorithms. Springer.
[33] H. J. Milionis, G. E. Alexandrides, E. N. Liberopoulos, E. T. Bairaktari, J. Goudevenos, and M. S. Elisaf, (2002) Hypomagnesemia and concurrent acid-base and electro-lyte abnormalities in patients with congestive heart failure. Eur. J. Heart Fail., 4, 167-173.
[34] H. Eison, R. A. Phillips, M. Ardeljan and L. R. Krakoff, (1990) Differences in ambulatory blood pressure between men and women with mild hypertension, J. Hum. Hy-pertens., 4, 400-404.
[35] C. Agyemang, N. Bindraban, G. Mairuhu, G. Van Montfrans, R. Koopmans, and K. Stronks, (2005) Prevalence, awareness, treatment, and control of hypertension among black suri-namese, south Asian surinamese and white dutch in am-sterdam, the netherlands: the sunset study. J. Hypertens., 23, 1971 1977.
[36] J. L. Li, R. M. Canham, W. Vongpatanasin, D. Leonard, R. J. Auchus, and R. G. Victor, (2006) Do allelic variantes in alpha(2A) and alpha(2C) adrenergic receptors predispose to hypertension in blacks?. Hypertension, 47, 1140-1146.
[37] J. P. Fauvel and M. Laville, (2006) Hypertension in blacks. Press. Med., 35, 1067-1071.
[38] P. McNair, M. S. Christensen, and C. Christiansen, (1982) Renal hypomagnesemia in human diabetes mellitus: its re- lation to glucose homeostasis. Eur. J. Clin. Invest., 12, 81-85.
[39] H. M. Mather, G. E. Levin, J. A. Nisbet, L. A. A. Hadley LAA, N. W. Oakley, and T. R. E. Pilkington, (1982) Di-urnal profiles of plasma magnesium and blood glucose in diabetes. Diabetologia, 22, 180-183.
[40] H. Rosolova, O. Mayer, and G. Reaven, (1997) Effect of variations in plasma magnesium concentration on resis-tance to insulin-mediated glucose disposal in nondiabetic subjects. J. Clin. Endocrinol. Metab., 82, 3783-3785.
[41] P. E. Paulev, (1999) Textbook in medical physiology and pathophysiology, essentials and clinical problems. Co-penhagen Medical Plubishers.

Copyright © 2024 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.