Prediction of Human Immunodeficiency Virus-1 Viral Load from CD4 Cell Count Using Artificial Neural Networks

摘要

The spread of HIV/AIDS is a global-problem today and is considered to be the most severe health crisis of modern times. In recent years, soft computing techniques such as artificial neural networks and swarm intelligence techniques have emerged to play an important role in the study of immune response especially in the problem involving HIV infection. Viral load testing is highly important for diagnosis and staging of HIV-1 infection and due to the cost and availability of viral load testing instruments, it is not being performed in many resource limited countries. In this work, an artificial neural networks model has been developed for estimation of HIV-1 viral load from CD4 cell count measurements under the influence of antiretroviral drugs, in the AIDS phase of the disease. Results demonstrate that the developed model is efficient in estimation of HIV-1 viral load. In this paper, the objectives, methods and significant observations are presented in detail.