APPLICATION OF MACHINE LEARNING TECHNIQUE FOR THE PREDICTION OF NEONATAL MORTALITY USING MULTIPLE RISK FACTORS

Authors

  • Tasiu Suleiman a:1:{s:5:"en_US";s:5:"FUDMA";}
  • P. O. Odion
  • M. N. Musa
  • M. M. Isa

DOI:

https://doi.org/10.33003/fjs-2020-0403-324

Keywords:

neonatal mortality, risk factors, Mortality, High-risk Birth, SVM, KMeansSMOTE

Abstract

It is a common knowledge that one of the major cause of neonatal mortality is high-risk birth, which can be identified through risk factors. Though, there are many risk factors associated with neonatal mortality (i.eshort birth interval, pre-natal care etc), most interventions of government and other agencies target birth based on a single risk factor (i.e. poverty) even though most neonatal deaths are not from the targeted risk factor,thus, failing to curb the prevalence of early-life mortality. Hence, data from Nigerian Demographic and health Survey was gotten for this study and nine risk factors were used to predict neonatal mortality risk by applying Support Vector Machine algorithm to build a predictive model. KMeansSMOTE was used to solve the problem of class imbalance in the dataset, while model hyper-parameter tuning was appliedto the SVM model to get a better prediction. Neonatal mortality risk was estimated as a function of nine risk factors.  Risk factors chosen for the study were compared with four (4) risk factors from a previous study. The result gave a sensitivity of 78%, specificity of 44% and area under curve of 60% compared to using only four risk factors which has a sensitivity of 63%, specificity of 37% and area under curve of 50%. The result shows that having more risk factorsgives a considerable improvement by predicting more neonatal deaths.This will aid researchers and governments to identify more risk factorscausing neonatal deaths especially in Africa

References

Abolarin, M.S.,Olughoji, O.A. and Ugwkoke, I. C.(2004). Experimental Investigation on Local Refractory Materials for Furnace Construction. Procedure of the 5th Annual Engineering Conference, Federal University of Technology, Minna, Nigeria. Pp 82 – 85.

ASTM D3974(1981). Standard Practices for Extraction of Trace Elements from Sediments. ASTM International Barr Harber Drive, West Conshohocken, United States, PP393-395

Begum,A., Ramaiah, M., Irfanulla, K. and Veena, K.(2009). Analysis of heavy metal concentrations in soil and Litchens from various localities of Hosur Road Bangalore, India. CONDENFCJHAO, E.J.Chem. 6(1); 13-22.

Dauda A (2011). An Introduction to Atomic Absorption Spectrophotometry. Omo-

Ojo Print and Publishers Nig. Coy, Lagos Nigeria. pp.11-24.

Ekundayo, G. (2003). Foundry Technology for Mechanical Students, Bosem Publisher Akure. Pp. 61-64.

Lacatusu., R. (2000)." Appraisal levels of Soil Contamination and Pollution with Heavy Metals

In Soilâ€.European Soil Research Report, No 4 office of official publication of the European Communities, L.uxembourg,pp.393-402.

Lenka, M. and Peter, E. (2010)." End-of-waste Criteria for Aluminum and Aluminum Alloy Scrap", European Commission, Joint Research Centre, Institute for Prospective Technological Studies, pp. 1-59.

Lickens, G.E. (2004). Effluent Monitoring Journal for Shell Petroleum Development Company of Nigeria Ltd East 22, 1-28

Mingqian B.,(2006). Analysis of the Recycling Method for Aluminum Soda Cans . pp.1-68,

Khan, R.H.(2005) “Metal Casting Technology In Nigeria - Present Status and future Prospectsâ€.22 pp.7-13

Patricia, A.P.(2000). Aluminum Recycling in the United States. U. S. Geological Survey Circular 1196-W. PP 1-6

Shuaib-Babata, Y. L. and Olumodeji, J.O.(2014). Analysis of Ilorin Sand Moulding Properties for Foundry Application. International Journal of Engineering Research and Technology(IJERT). 3(1);1520-1526.

Shuaib-Babata, Y. L.,Abegunde, A. J. and Abdul, J.M.(2017). Suitability of Ado-Ekiti(Nigeria)Natural Moulding Sands for use as Foundry Sands in Production of Aluminium Alloy cast. Journal of Production Engineering.20(2): 91-100.

Suciu, I., Cosma, C., Todica, M., Bolbaca, S.D. and Jantschi, L.(2008). Analysis of Soil heavy metal pollution and pattern in central Transylvania. International Journal of Mol. Science. 9: 434-453.

Tan, R.B.H. and Khoo, H.H.(2004). An LCA Study of a primary aluminum supply chain. Journal of clear production. ELSEVIER pp 1-12. doi:10.1016/j.jclepro.

Tokan, A., Adelemoni, E.A. and Datau, S.G.(2004). Mould Characteristics of Azare fioundry Sand. Journal of raw materials research. (JORMAR). 1(1): 67-78

WHO (2008). World Health Organisation, Guidelines for drinking water quality, World health organisationgeneva. pp. 113-154

Published

2020-09-30

How to Cite

Suleiman, T., Odion, P. O., Musa, M. N., & Isa, M. M. (2020). APPLICATION OF MACHINE LEARNING TECHNIQUE FOR THE PREDICTION OF NEONATAL MORTALITY USING MULTIPLE RISK FACTORS. FUDMA JOURNAL OF SCIENCES, 4(3), 576 - 582. https://doi.org/10.33003/fjs-2020-0403-324