Healthc Inform Res.  2017 Oct;23(4):271-276. 10.4258/hir.2017.23.4.271.

Machine Learning to Improve the Effectiveness of ANRS in Predicting HIV Drug Resistance

• Singh Y

• KMID: 2396418
• DOI: http://doi.org/10.4258/hir.2017.23.4.271

Abstract

OBJECTIVES
Human immunodeficiency virus infection and acquired immune deficiency syndrome (HIV/AIDS) is one of the major burdens of disease in developing countries, and the standard-of-care treatment includes prescribing antiretroviral drugs. However, antiretroviral drug resistance is inevitable due to selective pressure associated with the high mutation rate of HIV. Determining antiretroviral resistance can be done by phenotypic laboratory tests or by computer-based interpretation algorithms. Computer-based algorithms have been shown to have many advantages over laboratory tests. The ANRS (Agence Nationale de Recherches sur le SIDA) is regarded as a gold standard in interpreting HIV drug resistance using mutations in genomes. The aim of this study was to improve the prediction of the ANRS gold standard in predicting HIV drug resistance.
METHODS
A genome sequence and HIV drug resistance measures were obtained from the Stanford HIV database (http://hivdb.stanford.edu/). Feature selection was used to determine the most important mutations associated with resistance prediction. These mutations were added to the ANRS rules, and the difference in the prediction ability was measured.
RESULTS
This study uncovered important mutations that were not associated with the original ANRS rules. On average, the ANRS algorithm was improved by 79% ± 6.6%. The positive predictive value improved by 28%, and the negative predicative value improved by 10%.
CONCLUSIONS
The study shows that there is a significant improvement in the prediction ability of ANRS gold standard.

Keyword

Medical Informatics; Health Informatics; Computational Biology; Artificial Intelligence; Clinical Informatics; Machine Learning

MeSH Terms

Acquired Immunodeficiency Syndrome
Artificial Intelligence
Computational Biology
Developing Countries
Drug Resistance*
Genome
HIV*
Machine Learning*
Medical Informatics
Mutation Rate

Reference

1. Lv Z, Zhu H. Health care expenditure and GDP in African countries: evidence from semiparametric estimation with panel data. ScientificWorldJournal. 2014; 2014:905747.

2. Yashik S, Maurice M. Predicting a single HIV drug resistance measure from three international interpretation gold standards. Asian Pac J Trop Med. 2012; 5(7):566–572.

3. Actuarial Society of South Africa. ASSA2008 model [Internet]. Cape Town, South Africa: Actuarial Society of South Africa;2011. cited at 2017 Oct 15. Available from: http://www.actuarialsociety.org.za/committees/demography-epidemiology-committee/aids-models/.

4. Shisana O, Rehle T, Simbayi LC, Zuma K, Jooste S, Zungu N, et al. South African National HIV Prevalence, Incidence and Behaviour Survey, 2012. Pretoria, South Africa: Human Sciences Research Council;2014. cited at 2107 Oct 15. Available from: http://www.hsrc.ac.za/en/research-data/view/6871.

5. Central Intelligence Agency. The World Factbook: HIV/AIDS - adult prevalence rate [Internet]. Washington (DC): Central Intelligence Agency;2012. cited at 2017 Oct 15. Available from: https://www.cia.gov/library/Publications/the-world-factbook/fields/2155.html.

6. Health Systems Trust. Percentage of deaths due to AIDS Health Indicators [Internet]. Durban, South Africa: Health Systems Trust;2011. cited at 2017 Oct 15. Available from: http://www.hst.org.za/.

7. Richman D, Staszewski S. HIV drug resistance and its implications for antiretroviral treatment strategies. London: International Medical Press;1997.

8. EuroGuidelines Group for HIV Resistance. Clinical and laboratory guidelines for the use of HIV-1 drug resistance testing as part of treatment management: recommendations for the European setting. AIDS. 2001; 15(3):309–320.

9. Meynard JL, Vray M, Morand-Joubert L, Race E, Descamps D, Peytavin G, et al. Phenotypic or genotypic resistance testing for choosing antiretroviral therapy after treatment failure: a randomized trial. AIDS. 2002; 16(5):727–736.

10. Bartlett JC, Gallant JE. Medical Management of HIV infection. Baltimore (MD): John Hopkins University AIDS Service;2004.

11. Toor JS, Sharma A, Kumar R, Gupta P, Garg P, Arora SK. Prediction of drug-resistance in HIV-1 subtype C based on protease sequences from ART naive and first-line treatment failures in North India using genotypic and docking analysis. Antiviral Res. 2011; 92(2):213–218.

12. Liu TF, Shafer RW. Web resources for HIV type 1 genotypic-resistance test interpretation. Clin Infect Dis. 2006; 42(11):1608–1618.

13. Katlama C, Clotet B, Plettenberg A, Jost J, Arasteh K, Bernasconi E, et al. The role of abacavir (ABC, 1592) in antiretroviral therapy-experienced patients: results from a randomized, double-blind, trial. CNA3002 European Study Team. AIDS. 2000; 14(7):781–789.

14. Masquelier B, Assoumou KL, Descamps D, Bocket L, Cottalorda J, Ruffault A, et al. Clinically validated mutation scores for HIV-1 resistance to fosamprenavir/ritonavir. J Antimicrob Chemother. 2008; 61(6):1362–1368.

15. Rajkumar A, Reena GS. Diagnosis of heart disease using datamining algorithm. Glob J Comput Sci Technol. 2010; 10(10):38–43.