Your Cart

Your cart is empty

Home  >  Volume 27 (July 2014)

16. Comparison Between Artificial Neural Network Models and Multiple Regression Models In the Tracking of CD4 Cell Counts of HIV Patients. A Case Study of Anambra State by Nwosu C. A. Volume 27,(July 2014), pp 129 – 132
Sale price: $5.00


Artificial Neural Network models are relatively new computational tools which their inherent ability to learn and recognize highly non-linear and complex relationships make them ideally suited in solving a wide range of complex real-world problems.  In this research, the Artificial Neural Network model is compared with the multiple Regression Model (MRM) in the tracking of CD4 cell counts of HIV positive patients. Modeling is performed based on 250 datasets of HIV positive patients from a cohort study with follow-up collected from the continuous quality improvement HIV care of Nnamdi Azikiwe University Teaching Hospital (NAUTH) Nnewi. The predictive results of the CD4 cell counts from the two models from the historical data and their mean absolute error (MAE) were analysed and compared. The results indicated that the Artificial Neural Network model gave the most accurate prediction of the CD4 cell counts. The artificial neural network model outperformed the multiple regression model.

Keywords: Artificial Neural Network model, CD4 cell counts, multiple regression model, prediction, HIV.