Machine Learning Algorithms Using Routinely Collected Data Do Not Adequately Predict Viremia to Inform Targeted Services in Postpartum Women Living With HIV.
Adult
Algorithms
Anti-HIV Agents
/ therapeutic use
Anti-Retroviral Agents
/ therapeutic use
Female
HIV Infections
/ diagnosis
Humans
Infectious Disease Transmission, Vertical
/ prevention & control
Machine Learning
Postpartum Period
Pregnancy
Pregnancy Complications, Infectious
/ diagnosis
Routinely Collected Health Data
Viral Load
Viremia
/ diagnosis
Journal
Journal of acquired immune deficiency syndromes (1999)
ISSN: 1944-7884
Titre abrégé: J Acquir Immune Defic Syndr
Pays: United States
ID NLM: 100892005
Informations de publication
Date de publication:
15 12 2021
15 12 2021
Historique:
received:
05
05
2021
accepted:
18
08
2021
pubmed:
15
9
2021
medline:
27
1
2022
entrez:
14
9
2021
Statut:
ppublish
Résumé
Adherence to antiretroviral treatment (ART) among postpartum women with HIV is essential for optimal health and prevention of perinatal transmission. However, suboptimal adherence with subsequent viremia is common, and adherence challenges are often underreported. We aimed to predict viremia to facilitate targeted adherence support in sub-Saharan Africa during this critical period. Data are from PROMISE 1077BF/FF, which enrolled perinatal women between 2011 and 2014. This analysis includes postpartum women receiving ART per study randomization or country-specific criteria to continue from pregnancy. We aimed to predict viremia (single and confirmed events) after 3 months on ART at >50, >400, and >1000 copies/mL within 6-month intervals through 24 months. We built models with routine clinical and demographic data using the least absolute shrinkage and selection operator and SuperLearner (which incorporates multiple algorithms). Among 1321 women included, the median age was 26 years and 96% were in WHO stage 1. Between 0 and 24 months postpartum, 42%, 31%, and 28% of women experienced viremia >50, >400, and >1000 copies/mL, respectively, at least once. Across models, the cross-validated area under the receiver operating curve ranged from 0.74 [95% confidence interval (CI): 0.72 to 0.76] to 0.78 (95% CI: 0.76 to 0.80). To achieve 90% sensitivity predicting confirmed viremia >50 copies/mL, 64% of women would be classified as high risk. Using routinely collected data to predict viremia in >1300 postpartum women with HIV, we achieved moderate model discrimination, but insufficient to inform targeted adherence support. Psychosocial characteristics or objective adherence metrics may be required for improved prediction of viremia in this population.
Sections du résumé
BACKGROUND
Adherence to antiretroviral treatment (ART) among postpartum women with HIV is essential for optimal health and prevention of perinatal transmission. However, suboptimal adherence with subsequent viremia is common, and adherence challenges are often underreported. We aimed to predict viremia to facilitate targeted adherence support in sub-Saharan Africa during this critical period.
METHODS
Data are from PROMISE 1077BF/FF, which enrolled perinatal women between 2011 and 2014. This analysis includes postpartum women receiving ART per study randomization or country-specific criteria to continue from pregnancy. We aimed to predict viremia (single and confirmed events) after 3 months on ART at >50, >400, and >1000 copies/mL within 6-month intervals through 24 months. We built models with routine clinical and demographic data using the least absolute shrinkage and selection operator and SuperLearner (which incorporates multiple algorithms).
RESULTS
Among 1321 women included, the median age was 26 years and 96% were in WHO stage 1. Between 0 and 24 months postpartum, 42%, 31%, and 28% of women experienced viremia >50, >400, and >1000 copies/mL, respectively, at least once. Across models, the cross-validated area under the receiver operating curve ranged from 0.74 [95% confidence interval (CI): 0.72 to 0.76] to 0.78 (95% CI: 0.76 to 0.80). To achieve 90% sensitivity predicting confirmed viremia >50 copies/mL, 64% of women would be classified as high risk.
CONCLUSIONS
Using routinely collected data to predict viremia in >1300 postpartum women with HIV, we achieved moderate model discrimination, but insufficient to inform targeted adherence support. Psychosocial characteristics or objective adherence metrics may be required for improved prediction of viremia in this population.
Identifiants
pubmed: 34520443
doi: 10.1097/QAI.0000000000002800
pii: 00126334-202112150-00003
pmc: PMC8585692
mid: NIHMS1739613
doi:
Substances chimiques
Anti-HIV Agents
0
Anti-Retroviral Agents
0
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Langues
eng
Sous-ensembles de citation
IM
Pagination
439-447Subventions
Organisme : NIAID NIH HHS
ID : UM1 AI069423
Pays : United States
Organisme : NIMH NIH HHS
ID : K01 MH119910
Pays : United States
Organisme : NIAID NIH HHS
ID : UM1 AI069518
Pays : United States
Organisme : NIAID NIH HHS
ID : UM1 AI069536
Pays : United States
Organisme : NIAID NIH HHS
ID : UM1 AI069469
Pays : United States
Organisme : NIAID NIH HHS
ID : UM1 AI069530
Pays : United States
Informations de copyright
Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.
Déclaration de conflit d'intérêts
The authors have no conflicts of interest to disclose.
Références
UNAIDS. Start Free, Stay Free, AIDS Free: Final Report on 2020 Targets. Geneva, Switzerland: Joint United Nations Programme on HIV/AIDS (UNAIDS), 2021.
Currier JS, Britto P, Hoffman RM, et al. Randomized trial of stopping or continuing ART among postpartum women with pre-ART CD4 >/= 400 cells/mm3. PLoS One. 2017;12:e0176009.
Fowler MG, Qin M, Fiscus SA, et al. Benefits and risks of antiretroviral therapy for perinatal HIV prevention. N Engl J Med. 2016;375:1726–1737.
Jamieson DJ, Chasela CS, Hudgens MG, et al. Maternal and infant antiretroviral regimens to prevent postnatal HIV-1 transmission: 48-week follow-up of the BAN randomised controlled trial. Lancet. 2012;379:2449–2458.
Flynn PM, Taha TE, Cababasay M, et al. Prevention of HIV-1 transmission through breastfeeding: efficacy and safety of maternal antiretroviral therapy versus infant nevirapine prophylaxis for duration of breastfeeding in HIV-1-infected women with high CD4 cell count (IMPAACT PROMISE): a randomized, open-label, clinical trial. J Acquir Immune Defic Syndr. 2018;77:383–392.
Donnell D, Baeten JM, Kiarie J, et al. Heterosexual HIV-1 transmission after initiation of antiretroviral therapy: a prospective cohort analysis. Lancet. 2010;375:2092–2098.
Cohen MS, Chen YQ, McCauley M, et al. Prevention of HIV-1 infection with early antiretroviral therapy. N Engl J Med. 2011;365:493–505.
Rodger AJ, Cambiano V, Bruun T, et al. Sexual activity without condoms and risk of HIV transmission in serodifferent couples when the HIV-positive partner is using suppressive antiretroviral therapy. JAMA. 2016;316:171–181.
Centers for Disease Control and Prevention. Evidence of HIV Treatment and Viral Suppression in Preventing the Sexual Transmission of HIV. Atlanta, GA: Centers for Disease Control and Prevention, 2017.
Chetty T, Newell ML, Thorne C, et al. Viraemia before, during and after pregnancy in HIV-infected women on antiretroviral therapy in rural KwaZulu-Natal-South Africa, 2010-2015. Trop Med Int Health. 2018;23:79–91.
Hosseinipour M, Nelson JAE, Trapence C, et al. Viral suppression and HIV drug resistance at 6 months among women in Malawi's Option B+ Program: results from the PURE Malawi Study. J Acquir Immune Defic Syndr. 2017;75:S149–S155.
Ruperez M, Noguera-Julian M, Gonzalez R, et al. HIV drug resistance patterns in pregnant women using next generation sequence in Mozambique. PLoS One. 2018;13:e0196451.
Myer L, Redd AD, Mukonda E, et al. Antiretroviral adherence, elevated viral load and drug resistant mutations in HIV-infected women initiating treatment in pregnancy: a nested case-control study. Clin Infect Dis. 2020;70:501–508.
Hoffman RM, Warshaw MG, Amico KR, et al. Predictors of viremia in postpartum women on antiretroviral therapy. J Acquir Immune Defic Syndr. 2020;83:72–80.
Yotebieng M, Mpody C, Ravelomanana NL, et al. HIV viral suppression among pregnant and breastfeeding women in routine care in the Kinshasa province: a baseline evaluation of participants in CQI-PMTCT study. J Int AIDS Soc. 2019;22:e25376.
Sam-Agudu NA, Ramadhani HO, Isah C, et al. The impact of structured mentor mother programs on 6-month postpartum retention and viral suppression among HIV-positive women in rural Nigeria: a prospective paired cohort study. J Acquir Immune Defic Syndr. 2017;75(suppl 2):S173–S181.
Mills EJ, Lester R, Thorlund K, et al. Interventions to promote adherence to antiretroviral therapy in Africa: a network meta-analysis. Lancet HIV. 2014;1:e104-111.
Bonner K, Mezochow A, Roberts T, et al. Viral load monitoring as a tool to reinforce adherence: a systematic review. J Acquir Immune Defic Syndr. 2013;64:74–78.
Berg KM, Arnsten JH. Practical and conceptual challenges in measuring antiretroviral adherence. J Acquir Immune Defic Syndr. 2006;43(suppl 1):S79–S87.
Kagee A, Nel A. Assessing the association between self-report items for HIV pill adherence and biological measures. AIDS Care. 2012;24:1448–1452.
Beyrer C, Pozniak A. HIV drug resistance—an emerging threat to epidemic control. N Engl J Med. 2017;377:1605–1607.
The Global Fund. A New Toolkit for Differentiated Care in HIV and TB Programs. Geneva, Switzerland: Global Fund to Fight AIDS, Tuberculosis and Malaria. Available at: https://www.theglobalfund.org/en/news/2015-12-04-new-toolkit-for-differentiated-care-in-hiv-and-tb-programs/ . Accessed March 14, 2018.
McNairy ML, Abrams EJ, Rabkin M, et al. Clinical decision tools are needed to identify HIV-positive patients at high risk for poor outcomes after initiation of antiretroviral therapy. Plos Med. 2017;14:e1002278.
Srivastava M, Sullivan D, Phelps BR, et al. Boosting ART uptake and retention among HIV-infected pregnant and breastfeeding women and their infants: the promise of innovative service delivery models. J Int AIDS Soc. 2018;21:1–6.
Mungwira RG, Divala TH, Nyirenda OM, et al. A targeted approach for routine viral load monitoring in Malawian adults on antiretroviral therapy. Trop Med Int Health. 2018;23:526–532..
Phan V, Thai S, Koole O, et al. Validation of a clinical prediction score to target viral load testing in adults with suspected first-line treatment failure in resource-constrained settings. J Acquir Immune Defic Syndr. 2013;62:509–516.
van Griensven J, Phan V, Thai S, et al. Simplified clinical prediction scores to target viral load testing in adults with suspected first line treatment failure in Phnom Penh, Cambodia. PLoS One. 2014;9:e87879.
Meya D, Spacek LA, Tibenderana H, et al. Development and evaluation of a clinical algorithm to monitor patients on antiretrovirals in resource-limited settings using adherence, clinical and CD4 cell count criteria. J Int AIDS Soc. 2009;12:3.
Petersen ML, LeDell E, Schwab J, et al. Super Learner analysis of electronic adherence data improves viral prediction and may provide strategies for selective HIV RNA monitoring. J Acquir Immune Defic Syndr. 2015;69:109–118.
Robbins GK, Johnson KL, Chang Y, et al. Predicting virologic failure in an HIV clinic. Clin Infect Dis. 2010;50:779–786.
Taha TE, Brummel S, Angelidou K, et al. PROMISE trial: results of continued vs discontinued ART after end of breastfeeding [139]. Conference on Retroviruses and Opportunistic Infections; March 4–7, 2018; Boston, MA.
World Health Organization. Consolidated Guideline on the Use of Antiretroviral Drugs for Treating and Preventing HIV Infection: Recommendations for a Public Health Approach. Geneva, Switzerland: World Health Organization; 2016.
World Health Organization. WHO Case Definitions of HIV for Surveillance and Revised Clinical Staging and Immunological Classification of HIV-Related Disease in Adults and Children. Geneva, Switzerland: World Health Organization; 2007.
INSIGHT START Study Group, Lundgren JD, Babiker AG, et al. Initiation of antiretroviral therapy in early asymptomatic HIV infection. N Engl J Med. 2015;373:795–807.
Davis NL, Miller WC, Hudgens MG, et al. Maternal and breastmilk viral load: impacts of adherence on peripartum HIV infections averted-The Breastfeeding, Antiretrovirals, and Nutrition Study. J Acquir Immune Defic Syndr. 2016;73:572–580.
Waitt C, Low N, Van de Perre P, et al. Does U=U for breastfeeding mothers and infants? Breastfeeding by mothers on effective treatment for HIV infection in high-income settings. Lancet HIV. 2018;5:e531-e536.
Flynn P, Taha T, Cababasay M, et al. Association of Maternal Viral Load and CD4 Count with Perinatal HIV-1 Transmission Risk during Breastfeeding in the PROMISE Postpartum Component [THPEB115]. 22nd International AIDS Conference; 2018; Amsterdam, Netherlands.
Bernal E, Gomez JM, Jarrin I, et al. Low-level viremia Is associated with clinical progression in HIV-infected patients receiving antiretroviral treatment. J Acquir Immune Defic Syndr. 2018;78:329–337.
Hosmer DW, Lemeshow S, Sturdivant RX. Model-building strategies and methods for logistic regression. In: Applied Logistic Regression . Hoboken, NJ: Wiley; 2013:89–151.
Tibshirani R. Regression shrinkage and selection via the lasso. J R Stat Soc Ser B. 1996;58:267–288.
van der Laan MJ, Polley EC, Hubbard AE. Super learner. Stat Appl Genet Mol Biol. 2007;6:Article25.
James G, Witten D, Hastie T, et al. An Introduction to Statistical Learning with Applications in R . New York, NY: Springer; 2013.
Harrell FE Jr, Lee KL, Mark DB. Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Stat Med. 1996;15:361–387.
Altman DG, Royston P. What do we mean by validating a prognostic model? Stat Med. 2000;19:453–473.
Gonzalez JS, Batchelder AW, Psaros C, et al. Depression and HIV/AIDS treatment nonadherence: a review and meta-analysis. J Acquir Immune Defic Syndr. 2011;58:181–187.
Tuthill EL, Pellowski JA, Young SL, et al. Perinatal depression among HIV-infected women in KwaZulu-natal South Africa: prenatal depression predicts lower rates of exclusive breastfeeding. AIDS Behav. 2017;21:1691–1698.
Phillips TK, Clouse K, Zerbe A, et al. Linkage to care, mobility and retention of HIV-positive postpartum women in antiretroviral therapy services in South Africa. J Int AIDS Soc. 2018;21(suppl 4):e25114.
Kanters S, Vitoria M, Zoratti M, et al. Comparative efficacy, tolerability and safety of dolutegravir and efavirenz 400mg among antiretroviral therapies for first-line HIV treatment: a systematic literature review and network meta-analysis. EClinicalMedicine. 2020;28:100573.