Comparison of particle swarm and bacterial foraging optimization algorithms for therapy planning in HIV/AIDS patients

Abstract

In HIV/AIDS patients, antiretroviral therapy (ART) is used for reducing the viral load and helps in increasing the life span of the individual. However, severe side effects are associated with the use of antiretroviral drugs. Hence, a treatment schedule, using minimal amount of drugs, is required for maintaining a low viral load and a healthy immune system. The objective of this work is to compute the optimal dosage of antiretroviral drugs for therapy planning in HIV/AIDS patients, using intelligent optimization techniques. In this work, two computational swarm intelligence techniques known as the particle swarm optimization (PSO) and bacterial foraging optimization (BFO) in conjunction with the three-dimensional mathematical model of HIV/AIDS have been used for estimating the optimal drug dosage for administering therapy by minimization of viral load as well as the total drug concentration. Results demonstrate that, using the proposed method, it is possible to achieve minimal viral load and an improved immune system, with the estimated drug dosage. Further, it was observed that the efficiency of BFO (CD4 cells [Formula: see text][Formula: see text]cells/mm3 at seventh year of infection) for estimation of optimal drug dosage is higher than the PSO method (CD4 cells [Formula: see text][Formula: see text]cells/mm3 at seventh year of infection). This work seems to be of high clinical relevance since, at present, ART is the widely used procedure for treatment of HIV infected patients.