Communications on Applied Electronics |
Foundation of Computer Science (FCS), NY, USA |
Volume 5 - Number 8 |
Year of Publication: 2016 |
Authors: Olayemi Olufunke C., Olasehinde Olayemi O., Agbelusi O. |
10.5120/cae2016652349 |
Olayemi Olufunke C., Olasehinde Olayemi O., Agbelusi O. . Predictive Model of Pediatric HIV/AIDS Survival in Nigeria using Support Vector Machine. Communications on Applied Electronics. 5, 8 ( Aug 2016), 29-36. DOI=10.5120/cae2016652349
This paper is focused on the development of a predictive model for the classification of HIV/AIDS survival among Nigerian pediatric patients located in south-western Nigeria using supervised machine learning. Following the identification of the risk factors of HIV/AIDS survival from the review of literature and expert medical physicians, the case files of patients were used to collect information about the distribution of the risk factors and the HIV/AIDS survival status of pediatric patients selected at two hospitals in south-western Nigeria. The predictive model was formulated using the sequential minimal optimization (SMO) algorithm implemented by the support vector machine (SVM) – a binary classification algorithm based on the information collected. The predictive model was simulated using the Waikato Environment for Knowledge Analysis (WEKA) using the 10-fold cross validation technique for model training and testing. The SVM classifier performed well in the classification of the survival of pediatric HIV/AIDS patients with an accuracy of 97.7%. The predictive model developed can be useful to medical practitioners especially in the area of decision support regarding the survival of HIV/AIDS pediatric patients in Nigeria.