Volume 5, Issue 3, September 2019, Page: 159-169
A Classification Model for Severity of Neonatal Jaundice Using Deep Learning
Ngozi Chidozie Egejuru, Department of Computer Science, Hallmark University, Ijebu-Itele, Nigeria
Adanze Onyenonachi Asinobi, Department of Pediatrics, College of Medicine, University of Ibadan, Ibadan, Nigeria
Oluwasina Adewunmi, Tai Solarin University of Education, Ijebu Ode, Nigeria
Temilade Aderounmu, Department of Pediatrics and Child Health Care, Obafemi Awolowo University Teaching Hospital Complex, Ile-Ife, Nigeria
Samuel Ademola Adegoke, Department of Pediatrics and Child Health Care, Obafemi Awolowo University, Ile-Ife, Nigeria
Peter Adebayo Idowu, Department of Computer Science and Engineering, Obafemi Awolowo University, Ile-Ife, Nigeria
Received: Jul. 14, 2019;       Accepted: Aug. 5, 2019;       Published: Aug. 28, 2019
DOI: 10.11648/j.ajp.20190503.24      View  49      Downloads  20
Abstract
Neonatal jaundice is a yellowish discoloration of the white part of the eyes and skin in a newborn baby due to high bilirubin levels. An early diagnosis of the severity of neonatal jaundice using machine learning will decrease neonates’ likelihood of developing complications. The study elicited knowledge on the variables that are associated with the severity of neonatal jaundice and collected relevant data from a tertiary hospital in south-western Nigeria. The study formulated the predictive model for the severity of neonatal jaundice based on the variables identified using deep learning with multi-layer perceptron (MLP) classifier for varying number of epochs. The results of the study showed that using the deep learning with MLP classifier and 5 epochs had the lowest error rate however with the highest build time and provided a better model compared to the use of the other number of epochs. The study concluded that the using deep learning with MLP classifier and 5 epochs, the development of the classification model for the severity of neonatal jaundice patients receiving treatment was more effective due to its ability to understand the relationship between the attributes and their respective target class labels.
Keywords
Neonatal Jaundice, Fuzzy Model, Risk Classification, Risk Factors
To cite this article
Ngozi Chidozie Egejuru, Adanze Onyenonachi Asinobi, Oluwasina Adewunmi, Temilade Aderounmu, Samuel Ademola Adegoke, Peter Adebayo Idowu, A Classification Model for Severity of Neonatal Jaundice Using Deep Learning, American Journal of Pediatrics. Vol. 5, No. 3, 2019, pp. 159-169. doi: 10.11648/j.ajp.20190503.24
Copyright
Copyright © 2019 Authors retain the copyright of this article.
This article is an open access article distributed under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Reference
[1]
Ferreira, D., Oliviera, A. & Freitas, A. (2012). Applying Data Mining Techniques to improve Diagnosis in Neonatal Jaundice. BMC Medical Informatics and Decision Making 12 (143): 1-6.
[2]
Egube, B. A., Ofili, A. N. and Onakewhor, J. U. (2013). Neonatal Jaundice and its management: Knowledge, attitude, and practice among expectant mothers attending antenatal clinic at University of Benin teaching Hospital, Benin City, Nigeria. Nigerian Journal of Clinical Practice 16 (2): 188-194.
[3]
Coleman, R. (2011). Newborn Jaundice and Vitamin D. Retrieved from http://www.livestrong.com/article/532575-newbornjaundice-vitamin-d/#ixzz2a3FMIuBl on March 21, 2017.
[4]
Rennie, J., Burman-Roy, S. & Murphy, M. S. (2010). Neonatal jaundice: summary of NICE guidance. BMJ 340: 1-13.
[5]
De Luca D. (2010). NICE Guidelines on Neonatal Jaundice: at Risk of Being Too Nice. Lancet. 376 (9743): 771.
[6]
Besser, I., Perry, Z. H., Mesner, O., Zmora, E. & Toker, A. (2010). Yield of recommended blood tests for neonates requiring phototherapy for hyperbilirubinemia. Israeli Medical Association Journal 12 (4): 220-224.
[7]
Randev, S. & Grover, N. (2010). Predicting neonatal hyperbilirubinemia using first day serum Bilirubin levels. Indian Journal of Pediatrics 77 (2): 147–150.
[8]
Bhutani, V. K., Vilms, R. J. & Hamerman-Johnson, L. (2010). Universal Bilirubin screening for severe neonatal hyperbilirubinemia. Journal of Perinatology 30 (supplementary): S6–S15.
[9]
Burke, B. L., Robbins, J. M., Bird, T. M., Hobbs, C. A., Nesmith, C. & Tilford, J. M. (2009) Trends in hospitalizations for neonatal jaundice and kernicterus in the united states, 1988–2005. Journal of Pediatrics 123 (2): 523–532.
[10]
Zupan, J. (2005). Prenatal mortality in developing countries. N Engl J Med 352: 2047-2048.
[11]
Ogunfowora, O. B., Adefuye, P. O. and Fetuga, M. B. (2006). What do expectant mothers know about neonatal jaundice? International Electronic Journal of Health Education 9: 134-140.
[12]
Ezechukwu, C. C., Ugochukwu, E. F., Egbuonu, I. and Chukwuka, J. O. (2004). Risk factors from neonatal mortality in regional tertiary hospital in Nigeria. Niger J Clin Pract 7: 50-52.
[13]
Balogun, J. A., Aderounmu, T., Egejuru, N. C. & Idowu, P. A. (2018). An Ensemble Model of Machine Learning Algorithms for the Severity of Sickle Cell Disease (SCD). Computer Reviews Journal 2: 331-346.
[14]
Idowu, P. A., Aladekomo, T. A., Williams, K. O., Balogun, J. A. (2015). Predictive Model for Likelihood of Survival of Sickle Cell Anaemia (SCA) among Pediatric Patients using Fuzzy Logic. Journal of Transactions on Networks and Communications 3 (1): 31-44.
[15]
Idowu, P. A., Aladekomo, T. A., Williams, K. O., Balogun, J. A. (2015). Breast Cancer Risk Prediction using Data Mining Classification Techniques. Journal of Transactions on Networks and Communications 3 (1): 1-11.
[16]
Idowu, P. A., Aladekomo, T. A., Agbelusi, O., Alaba, O. B. & Balogun, J. A. (2017). Survival Model for Pediatric HIV/AIDS Patient using C4. 5 Decision Tree Algorithm. International Journal of Child Health and Human Development 10 (2): 143-155.
[17]
Chen, H. Y., Chuang, C. H., Yang, Y. J. and Wu, T. P. (2011). Exploring the risk factors of preterm birth using data mining. Expert Syst Appl 38 (5): 5384-5387.
[18]
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Wang, G. (2015). Recent Advances in Convolutional Neural Networks. arXiv, 1–14.
[19]
Najafabadi, M. M., Villanustre, F., Khoshgoftaar, T. M., Seliya, N., Wald, R., & Muharemagic, E. (2015). Deep learning applications and challenges in big data analytics. Journal of Big Data 2 (1): 1-13.
[20]
Idowu, P. A., Aladekomo, T. A., Agbelusi, O., Alaba, O. B. & Balogun, J. A. (2017). Prediction of Pediatric HIV/AIDS Survival in Nigeria using Naïve Bayes’ Approach. International Journal of Child Health and Human Development 10 (2): 131-142.
[21]
Purushothama, S., Meng, C., Che, Z. & Liu, Y. (2017). Benchmark of Deep Learning Models on Large Healthcare MIMIC Datasets. Journal of Biomedical Informatics 23: 1-13.
[22]
Balajee, J. & Sethumadahavi, R. (2017). Big Data Deep Learning in Healthcare for Electronic Health Records. International Scientific Research Organization Journal (ISROJ) 2 (2): 31-35.
Browse journals by subject