Methods: In this work, a method for estimating the HIV-1 viral load from CD4 cell counts, using a hybrid artificial intelligence technique is proposed. The coupled bacterial foraging/jumping frogs optimization procedure is a mathematical procedure which combines the decision making capabilities of the E.Coli bacteria and frogs. The coordinates of a bacterium and a frog represents an individual solution of the optimization problem. The final solution is obtained as the set of trial solutions converges towards the optimal solution. The computer program for estimation was developed using Matlab 7.10.1 running on a system with 1.73 GHz processor.
Results: The accuracy in estimation of HIV-1 viral load using the proposed method was found to be 94.58%. Further, the estimation error in the acute stage of the disease was found to be 4.29%, whereas, the estimation error in the chronic phase of the disease was found to be 0.83%. Also, the average correlation value between the actual and estimated HIV-1 viral load was found to be 0.99. The total time for estimation of HIV-1 viral load was 15.22 seconds.
Conclusions: The proposed approach for HIV-1 viral load estimation appears to be efficient and useful as a low cost strategy for VL testing in resource limited settings.