The Prediction of Paediatric HIV/AIDS Patient Survival: A Data Mining Approach

Authors

  • Idowu Peter Adebayo Department Computer Science and Engineering Peadiatric Department Obafemi Awolowo University, Ile-Ife Wesley Hospital Osun State
  • Agbelusi Olutola Department of Computer Science, Rufus Giwa Polytechnic, Owo
  • Aladekomo T. A. Peadiatric Department Obafemi Awolowo University, Ile-Ife Wesley Hospital Osun State

Abstract

This research requires the development of predictive model for determining the survival of Paediatric HIV/AIDS patients who are receiving antiretroviral drugs in the South-western Nigeria. The WEKA software was used in developing the predictive model using Naïve Bayes’ Classifier. Naïve Bayes’ Classifier was used to predict the length of survival of HIV/AIDS patients based on variables like CD4 count, viral load, opportunistic infection and nutritional status. The result shows that Naïve Bayes’ Classification can predict the survival of paediatrics HIV/AIDS patient with an accuracy of 60% to 100% based on selected dependent variables.

 

References

Eric et al, 2012: Human Immunodeficiency Virus Management

P.A Idowu, N. Okonronkwo and E.R Adagunodo(2009): Spatial Predictive Models for Malaria in Nigeria, journal of Health Informatics in Developing Countries, 3(3): pp 9-17. New Zealand.

Kononenko (2001) Machine learning for medical diagnosis: History, state of the art and perspective, Invited paper, Artificial Intelligence in Medicine - ISSN 0933-3657, vol. 23, no. 1, pp. 89-109.

Matthias & Margaret (2010): New models predict short-term survival of HIV patients starting antiretroviral therapy in sub-Saharan Africa.

Med News 2012: The management of Human Immunodeficiency Virus

Moore et al (2006) “CD4 percentage is an independent predictor of survival in patients starting antiretroviral therapy with absolute CD4 cell counts between 200 and 350 cells/microL†in the Journal of HIV Medical Vol 7, pp 383-8.

Puthanakit et al (2012) “Early versus deferred antiretroviral therapy for children older than 1 year infected with HIV (PREDICT): a multicentre, randomised, open-label trial†in Lancet infectious Diseases Journal; 12(12):933-41. doi: 10.1016/S1473- 3099(12)70242-6.

Rosma et al (2012) “The prediction of AIDS survival: A Data Mining Approach†in proceeding of the WSEAS international Conference on Multivariate Analysis and its application in Science and Engineering.

Sam Mateo (2012):

Downloads

Published

2016-06-15

How to Cite

Adebayo, I. P., Olutola, A., & T. A., A. (2016). The Prediction of Paediatric HIV/AIDS Patient Survival: A Data Mining Approach. Asian Journal of Computer and Information Systems, 4(3). Retrieved from https://www.ajouronline.com/index.php/AJCIS/article/view/930

Issue

Section

Articles