Document Type : Full Research Paper


1 Ph.D Student, Bioelectric Department, Biomedical Engineering Faculty, Amirkabir University of Technology, Tehran, Iran

2 Professor, Bioelectric Department, Biomedical Engineering Faculty, Amirkabir University of Technology, Tehran, Iran


Babies are born under 2,500 g., defined as low birth weight (LBW) babies. They are exposed to the higher risks of mortality, congenital malformations, mental retardation, and other physical and neurological impairments. 15.5 % of births around the world are LBW. Reduction of the rate of LBW births to one-third is one of the aims of United Nations Children’s Fund program. Prognosis of LBW births can play a critical role in the reduction of these cases. Also, it helps clinicians to make timely and efficient clinical decisions to save these babies' life. In this study, a hybrid framework called fuzzy evidential network with a good ability to manage different aspects of uncertainty is a selected as the LBW prognosis model. The accuracy of prognosis and the performance of the fuzzy evidential network in the management of missing values of the clinical database were investigated and compared with well-known prognosis models of LBW. The results showed that the fuzzy evidential network has higher prognosis accuracy (84.8%) than other prognosis models. On the other hand, the fusion of naïve Bayes and the fuzzy evidential network outputs resulted in higher prognosis accuracy (85.2%). In addition, the fuzzy evidential network performance in the management of uncertainty induced by imputation method, was better than other prognosis models of this study. The performance loss of this framework as the results of the missing data increment, is less than other models.


Main Subjects

[1]     Sclowitz IKT, Santos IS, Domingues MR, Matijasevich A, Barros AJ. Prognostic factors for low birthweight repetition in successive pregnancies: a cohort study. BMC pregnancy and childbirth. 2013;13:20.
[2]     Pourahmad S, Hamdami E, Vaziri F, Bazrafshan K. A Comparison of the Effective Factors of Preterm Birth Versus Low Birth Weight in Southern Iran Using Artificial Neural Network. International Journal of Women's Health and Reproduction Sciences. 2017;5:55-59.
[3]     Hange U, Selvaraj R, Galani M, Letsholo K. A Data-Mining Model for Predicting Low Birth Weight with a High AUC.  Computer and Information Science: Springer; 2018. p. 109-121.
[4]     Whitmore G, Su Y. Modeling low birth weights using threshold regression: results for US birth data. Lifetime Data Analysis. 2007;13:161-190.
[5]     Firouzi Jahantigh F, Nazarnejad R, Firouzi Jahantigh M. Investigating the Risk Factors for Low Birth Weight Using Data Mining: A Case Study of Imam Ali Hospital, Zahedan, Iran. Journal of Mazandaran University of Medical Sciences. 2016;25:171-188.
[6]     Senthilkumar D, Paulraj S. Prediction of low birth weight infants and its risk factors using data mining techniques.  Proceedings of the 2015 International Conference on Industrial Engineering and Operations Management2015. p. 186-194.
[7]     Blockley D. Analysing uncertainties: Towards comparing Bayesian and interval probabilities'. Mechanical Systems and Signal Processing. 2013;37:30-42.
[8]     He Y, Mirzargar M, Kirby RM. Mixed aleatory and epistemic uncertainty quantification using fuzzy set theory. International Journal of Approximate Reasoning. 2015;66:1-15.
[9]     Aguirre F, Sallak M, Schön W, Qiu S. On the distinction between aleatory and epistemic uncertainty and its implications on reliability and risk analysis.  European Safety and Reliability Conference, ESREL 2013.
[10] Khatibi V, Montazer GA. A fuzzy-evidential hybrid inference engine for coronary heart disease risk assessment. Expert Systems with Applications. 2010;37:8536-8542.
[11] Dutta P. Uncertainty Modeling in Risk Assessment Based on Dempster–Shafer Theory of Evidence with Generalized Fuzzy Focal Elements. Fuzzy Information and Engineering. 2015;7:15-30.
[12] Tang H. A novel fuzzy soft set approach in decision making based on grey relational analysis and Dempster–Shafer theory of evidence. Applied Soft Computing. 2015;31:317-325.
[13] Straszecka E. Combining uncertainty and imprecision in models of medical diagnosis. Information Sciences. 2006;176:3026-3059.
[14] Di Tomaso E, Baldwin JF. An approach to hybrid probabilistic models. International Journal of Approximate Reasoning. 2008;47:202-218.
[15] Liu W-Y, Yue K, Su J-Y, Yao Y. Probabilistic representation and approximate inference of type-2 fuzzy events in Bayesian networks with interval probability parameters. Expert Systems with Applications. 2009;36:8076-8083.
[16] Liao Q, Qiu Z, Zeng J. Fuzzy Bayesian Networks and its application in pressure equipment's security alerts. In: Ding Y, Wang H, Xiong N, Hao K, Wang L, editors. ICNC: IEEE; 2011. p. 1507-1511.
[17] Sakellaropoulos Gc Fau - Nikiforidis GC, Nikiforidis GC. Development of a Bayesian Network for the prognosis of head injuries using graphical model selection techniques. Methods of Information in Medicine. 1999;38:37–42.
[18] Verduijn M, Rosseel PMJ, Peek N, de Jonge E, de Mol BAJM. Prognostic Bayesian networks: II: An application in the domain of cardiac surgery. Journal of Biomedical Informatics. 2007;40:619-630.
[19] van Gerven MAJ, Taal BG, Lucas PJF. Dynamic Bayesian networks as prognostic models for clinical patient management. Journal of Biomedical Informatics. 2008;41:515-529.
[20] Peelen L, de Keizer NF, Jonge Ed, Bosman R-J, Abu-Hanna A, Peek N. Using hierarchical dynamic Bayesian networks to investigate dynamics of organ failure in patients in the Intensive Care Unit. Journal of Biomedical Informatics. 2010;43:273-286.
[21] Benavoli A, Ristic B, Farina A, Oxenham M, Chisci L. An Application of Evidential Networks to Threat Assessment. Aerospace and Electronic Systems, IEEE Transactions on. 2009;45:620-639
[22]  Janghorbani A, Moradi MH. Fuzzy Evidential Network and Its Application as Medical Prognosis and Diagnosis Models. Journal of Biomedical Informatics. 2017;72:96-107.
[23] Laâmari W, Ben Yaghlane B, Simon C. On the Complexity of the Graphical Representation and the Belief Inference in the Dynamic Directed Evidential Networks with Conditional Belief Functions. In: Hüllermeier E, Link S, Fober T, Seeger B, editors. Scalable Uncertainty Management: Springer Berlin Heidelberg; 2012. p. 206-218.
[24] Tsai C-F, Chang F-Y. Combining instance selection for better missing value imputation. Journal of Systems and Software. 2016;122:63-71.
[25]  شیما طباطبایی , مرادی محمد‌حسن. تعیین عوامل خطر پیش بینی کننده کم وزنی هنگام تولد نوزادان متولد تهران در سال 1386. نشریه علمی پژوهشی دانشکده پرستاری و مامایی. 1389;20:29-35
[26] Aguirre F, Sallak M, Vanderhaegen F, Berdjag D. An evidential network approach to support uncertain multiviewpoint abductive reasoning. Information Sciences. 2013;253:110-125.
[27] Shenoy PP. Binary join trees for computing marginals in the Shenoy-Shafer architecture. International Journal of Approximate Reasoning. 1997;17:239-263.
[28] Simon C, Weber P. Evidential Networks for Reliability Analysis and Performance Evaluation of Systems With Imprecise Knowledge. Reliability, IEEE Transactions on. 2009;58:69-87.
[29] Shahpari A, Seyedin SA. Using Mutual Aggregate Uncertainty Measures in a Threat Assessment Problem Constructed by Dempster&Shafer Network. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2015;45:877-886.
[30] Liu Z-g, Pan Q, Dezert J, Martin A. Adaptive imputation of missing values for incomplete pattern classification. Pattern Recognition. 2016;52:85-95.