Applying machine learning to laboratory data: predicting suppression of next HIV viral load in South Africa

By  Dr Mhairi Maskew  Crompton T, Sharpey-Schafer K, De Voux L  Jacob Bor  Rennick M, Pisa P,  Jacqui Miot  |  | 

With more than seven million HIV-infected people 1, South Africa is home to more people living with HIV than any other country in the world,2 and their national ART program is the world’s largest.3 South Africa adopted a “treat all” policy to provide ART to all HIV-positive people, regardless of CD4 cell count, in September 2016.3 Expanded ART availability has dramatically altered the health and quality of life of people living with HIV/AIDS, with an estimated life expectancy gain of 11.3 years between 2003 and 2011 due to ART4 and a 77% decrease in HIV transmission in stable serodiscordant couples.5 However, the rapid scale-up of the national ART program has put tremendous pressure on the limited resources of a public health sector. By expanding eligibility, UTT has eliminated “pre-ART” care for most patients.6 It has also led to faster ART initiation with fewer required clinic visits prior to dispensing drugs. These changes have compressed the care cascade, likely leading to greater ART uptake. At the same time, retention of new patients may have suffered. The problem of patient loss to follow-up (LTFU) within the public sector in South Africa has been well documented.7 The potential for improved health through expanded ART availability will only be realized if individuals sustain engagement in HIV care.

Publication details