Skip to main content

Advertisement

SpringerLink
Log in

Artificial Intelligence and Machine Learning for HIV Prevention: Emerging Approaches to Ending the Epidemic

  • The Science of Prevention (JD Stekler and JM Baeten, Section Editors)
  • Published:
Current HIV/AIDS Reports Aims and scope Submit manuscript

Abstract

Purpose of Review

We review applications of artificial intelligence (AI), including machine learning (ML), in the field of HIV prevention.

Recent Findings

ML approaches have been used to identify potential candidates for preexposure prophylaxis (PrEP) in healthcare settings in the USA and Denmark and in a population-based research setting in Eastern Africa. Although still in the proof-of-concept stage, other applications include ML with smartphone-collected and social media data to promote real-time HIV risk reduction, virtual reality tools to facilitate HIV serodisclosure, and chatbots for HIV education. ML has also been used for causal inference in HIV prevention studies.

Summary

ML has strong potential to improve delivery of PrEP, with this approach moving from development to implementation. Development and evaluation of AI and ML strategies for HIV prevention may benefit from an implementation science approach, including qualitative assessments with end users, and should be developed and evaluated with attention to equity.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

Papers of particular interest, published recently, have been highlighted as: • Of importance •• Of major importance

  1. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44–56.

    Article  CAS  PubMed  Google Scholar 

  2. Yu KH, Beam AL, Kohane IS. Artificial intelligence in healthcare. Nat Biomed Eng. 2018;2(10):719–31.

    Article  PubMed  Google Scholar 

  3. Deo RC. Machine learning in medicine. Circulation. 2015;132(20):1920–30.

    Article  PubMed  PubMed Central  Google Scholar 

  4. Centers for Disease Control and Prevention. HIV in the United States and dependent areas 2019 [updated April 2, 2020. Available from: https://www.cdc.gov/hiv/statistics/overview/ataglance.html]. Accessed 7 Apr 2020.

  5. HIV.gov. Global statistics: the global HIV/AIDS epidemic 2019 [updated July 31, 2019. Available from: https://www.hiv.gov/hiv-basics/overview/data-and-trends/global-statistics]. Accessed 7 Apr 2020.

  6. Fauci AS, Redfield RR, Sigounas G, Weahkee MD, Giroir BP. Ending the HIV epidemic: a plan for the United States. JAMA. 2019;321(9):844–5.

    Article  PubMed  Google Scholar 

  7. • Bi Q, Goodman KE, Kaminsky J, Lessler J. What is machine learning: a primer for the epidemiologist. Am J Epidemiol. 2019;188(12):2222–39. This paper provides an overview of machine learning, including concepts and terminology, commonly used algorithms, and epidemiologic applications in the published literature.

  8. Pearl J. The seven tools of causal inference, with reflections on machine learning. Commun ACM. 2019;62(3):54–60.

    Article  Google Scholar 

  9. Wolpert DH. Stacked generalization. Neural Netw. 1992;5(2):241–59.

    Article  Google Scholar 

  10. Breiman L. Stacked regressions. Mach Learn. 1996;24:49–64.

    Google Scholar 

  11. van der Laan MJ, Polley EC, Hubbard AE. Super learner. Stat Appl Genet Mol Biol. 2007;6:25.

    Google Scholar 

  12. Petersen ML, LeDell E, Schwab J, Sarovar V, Gross R, Reynolds N, 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(1):109–18.

    Article  PubMed  PubMed Central  Google Scholar 

  13. Owens DK, Davidson KW, Krist AH, et al. Preexposure prophylaxis for the prevention of HIV infection: US Preventive Services Task Force recommendation statement. JAMA. 2019;321(22):2203–13.

    Article  PubMed  Google Scholar 

  14. Chou R, Evans C, Hoverman A, Sun C, Dana T, Bougatsos C, et al. Preexposure prophylaxis for the prevention of HIV infection: evidence report and systematic review for the US Preventive Services Task Force. JAMA. 2019;321(22):2214–30.

    Article  PubMed  Google Scholar 

  15. SDET - San Diego early test score. (n.d.) Available from: http://sdet.ucsd.edu/. Accessed 7 Apr 2020.

  16. mysexpro.org. (n.d.) Available from:https://mysexpro.org/en/home/. Accessed 7 Apr 2020.

  17. Ortblad KF, Baeten JM. Electronic health record tools to catalyse PrEP conversations. Lancet HIV. 2019;6(10):e644–e5.

    Article  PubMed  PubMed Central  Google Scholar 

  18. •• Krakower DS, Gruber S, Hsu KK, et al. Development and validation of an automated HIV prediction algorithm to identify candidates for pre-exposure prophylaxis: a modelling study. Lancet HIV. 2019;6(10):e696–704 This study developed and validated an algorithm using EHR data to identify potential PrEP candidates in an ambulatory group practice in Massachusetts. The authors evaluated multiple machine learning algorithms and externally validated their best-performing algorithm in a Boston community health center, finding that predictive performance was slightly lower when applied in a different setting.

    Article  PubMed  PubMed Central  Google Scholar 

  19. Pencina MJ, D'Agostino RB Sr. Evaluating discrimination of risk prediction models: the C statistic. JAMA. 2015;314(10):1063–4.

    Article  CAS  PubMed  Google Scholar 

  20. •• Marcus JL, Hurley LB, Krakower DS, Alexeeff S, Silverberg MJ, Volk JE. Use of electronic health record data and machine learning to identify candidates for HIV pre-exposure prophylaxis: a modelling study. Lancet HIV. 2019;6(10):e688–95 This study developed and validated an algorithm using HER data to identify potential PrEP candidates in a large healthcare system in California. The authors found higher predictive performance with inclusion of multiple EHR data domains compared with simpler algorithms that included only on sexual orientation and STIs, particularly for Black patients.

    Article  PubMed  PubMed Central  Google Scholar 

  21. Ahlstrom MG, Ronit A, Omland LH, Vedel S, Obel N. Algorithmic prediction of HIV status using nation-wide electronic registry data. EClinicalMedicine. 2019 [Epub ahead of print].

  22. • Feller DJ, Zucker J, Yin MT, Gordon P, Elhadad N. Using clinical notes and natural language processing for automated HIV risk assessment. J Acquir Immune Defic Syndr, 2018. 77(2):160–6 This study used machine learning algorithms to predict incident HIV diagnoses in an academic medical center in New York City. The authors found that natural language processing of data from unstructured clinical notes improved predictive performance.

    Article  PubMed  Google Scholar 

  23. Havlir DV, Balzer LB, Charlebois ED, Clark TD, Kwarisiima D, Ayieko J, et al. HIV testing and treatment with the use of a community health approach in rural Africa. N Engl J Med. 2019;381(3):219–29.

    Article  PubMed  PubMed Central  Google Scholar 

  24. •• Balzer L, Havlir DV, Kamya MR, et al. Machine learning to identify persons at high risk of HIV acquisition in rural Kenya and Uganda. Clin Infect Dis. 2019 Nov 7 [Epub ahead of print]. This study used data from a population-based trial of universal HIV testing and treatment to compare three strategies, including a machine learning risk score, for identifying people likely to benefit from enhanced PrEP outreach. The authors found substantial advantages for machine learning compared with a risk group or model-based approach to predicting HIV risk.

  25. Chamie G, Clark TD, Kabami J, Kadede K, Ssemmondo E, Steinfeld R, et al. A hybrid mobile approach for population-wide HIV testing in rural East Africa: an observational study. Lancet HIV. 2016;3(3):e111–9.

    Article  PubMed  PubMed Central  Google Scholar 

  26. Balkus JE, Brown E, Palanee T, Nair G, Gafoor Z, Zhang J, et al. An empiric HIV risk scoring tool to predict HIV-1 acquisition in African Women. J Acquir Immune Defic Syndr. 2016;72(3):333–43.

    Article  PubMed  PubMed Central  Google Scholar 

  27. Romero-Brufau S, Huddleston JM, Escobar GJ, Liebow M. Why the C-statistic is not informative to evaluate early warning scores and what metrics to use. Crit Care. 2015;19:285.

    Article  PubMed  PubMed Central  Google Scholar 

  28. Wray TB, Luo X, Ke J, Perez AE, Carr DJ, Monti PM. Using smartphone survey data and machine learning to identify situational and contextual risk factors for HIV risk behavior among men who have sex with men who are not on PrEP. Prev Sci. 2019;20(6):904–13.

    Article  PubMed  Google Scholar 

  29. Young SD, Yu W, Wang W. Toward automating HIV identification: machine learning for rapid identification of HIV-related social media data. J Acquir Immune Defic Syndr. 2017;74(2):S128–S31.

    Article  PubMed  PubMed Central  Google Scholar 

  30. Muessig KE, Knudtson KA, Soni K, Larsen MA, Traum D, Dong W, et al. "I Didn't tell you sooner because I didn't know how to handle it myself." Developing a Virtual Reality Program to Support Hiv-Status Disclosure Decisions. Digit Cult Educ. 2018;10:22–48.

    PubMed  PubMed Central  Google Scholar 

  31. NIH Research Portfolio Online Reporting Tools (RePORT). Project Information: 5R44MH104102–05. 2019 [Available from: https://projectreporter.nih.gov/project_info_description.cfm?aid=9707883&icde=47043229&ddparam=&ddvalue=&ddsub=&cr=1&csb=default&cs=ASC&pball=]. Accessed 7 Apr 2020.

  32. HIV.gov. Chatbots and HIV communications: what you need to know 2017 [updated October 17, 2017. Available from: https://www.hiv.gov/blog/chatbots-and-hiv-communications-what-you-need-know]. Accessed 7 Apr 2020.

  33. Brixey J, Hoegen R, Lan W, et al. SHIHbot: A Facebook chatbot for sexual health information on HIV/AIDS. Saarbrucken, Germany: SIGDIAL 2017 Conference; 2017.

    Google Scholar 

  34. HIV.gov. 3 Lessons learned from HIV.gov's chatbot pilot 2018 [updated August 28, 2018. Available from: https://www.hiv.gov/blog/3-lessons-learned-hivgov-s-chatbot-pilot]. Accessed 7 Apr 2020.

  35. Zheng W, Balzer L, van der Laan M, Petersen M, Collaboration S. Constrained binary classification using ensemble learning: an application to cost-efficient targeted PrEP strategies. Stat Med. 2018;37(2):261–79.

    Article  PubMed  Google Scholar 

  36. Hernan MA, Hsu J, Healy B. A second chance to get causal inference right: a classification of data science tasks. Chance. 2019;32(1):42–9.

    Article  Google Scholar 

  37. Petersen, M. and Balzer, L (n.d.) Introduction to causal inference [Available from: https://www.ucbbiostat.com/]. Accessed 7 Apr 2020.

  38. Subbaswamy A, Saria S. From development to deployment: dataset shift, causality, and shift-stable models in health AI. Biostatistics 2020;21(2):345–52.

  39. Diaz I, van der Laan MJ. Assessing the causal effect of policies: an example using stochastic interventions. Int J Biostat. 2013;9(2):161–74.

    PubMed  Google Scholar 

  40. Shalit U. Can we learn individual-level treatment policies from clinical data? Biostatistics. 2020;21(2):359–62..

  41. Hayes RJ, Donnell D, Floyd S, et al. Effect of universal testing and treatment on HIV incidence - HPTN 071 (PopART). N Engl J Med. 2019;381(3):207–18.

    Article  PubMed  PubMed Central  Google Scholar 

  42. Makhema J, Wirth KE, Pretorius Holme M, Gaolathe T, Mmalane M, Kadima E, et al. Universal testing, expanded treatment, and incidence of HIV infection in Botswana. N Engl J Med. 2019;381(3):230–42.

    Article  PubMed  PubMed Central  Google Scholar 

  43. Tran L, Yiannoutsos CT, Musick BS, et al. Evaluating the impact of a HIV low-risk express care task-shifting program: a case study of the targeted learning roadmap. Epidemiol Methods. 2016;5(1):69–91.

    Article  PubMed  PubMed Central  Google Scholar 

  44. Balzer LB, Ayieko J, Kwarisiima D, et al. Far from MCAR: obtaining population-level estimates of HIV viral suppression. medRxiv. 2019 [Available from: https://doi.org/10.1101/19012781v1]. Accessed 7 Apr 2020.

  45. Van den Berg P, Powell VE, Wilson IB, Klompas M, Krakower DS. Primary care providers’ perspectives on using automated HIV risk prediction algorithms as clinical decision-support to identify potential candidates for PrEP. 13th International Conference on HIV Treatment and Prevention Adherence; Miami, FL. 2018.

  46. Gilkey MB, Marcus JL, Garrell JM, Powell VE, Maloney KM, Krakower DS. Using HIV risk prediction tools to identify candidates for preexposure prophylaxis: perspectives from patients and primary care providers. AIDS Patient Care STDs. 2019;33(8):372–8.

    Article  PubMed  PubMed Central  Google Scholar 

  47. Palanica A, Flaschner P, Thommandram A, Li M, Fossat Y. Physicians' perceptions of Chatbots in health care: cross-sectional web-based survey. J Med Internet Res. 2019;21(4):e12887.

    Article  PubMed  PubMed Central  Google Scholar 

  48. Nadarzynski T, Miles O, Cowie A, Ridge D. Acceptability of artificial intelligence (AI)-led chatbot services in healthcare: a mixed-methods study. Digit Health. 2019;5:2055207619871808.

    PubMed  PubMed Central  Google Scholar 

  49. Char DS, Shah NH, Magnus D. Implementing machine learning in health care - addressing ethical challenges. N Engl J Med. 2018;378(11):981–3.

    Article  PubMed  PubMed Central  Google Scholar 

  50. Gianfrancesco MA, Tamang S, Yazdany J, Schmajuk G. Potential biases in machine learning algorithms using electronic health record data. JAMA Intern Med. 2018;178(11):1544–7.

    Article  PubMed  PubMed Central  Google Scholar 

  51. • Rajkomar A, Hardt M, Howell MD, Corrado G, Chin MH. Ensuring fairness in machine learning to advance health equity. Ann Intern Med. 2018;169(12):866–72 This paper outlines strategies for promoting fairness at each stage of the machine learning algorithm development and implementation process, including engagement of diverse stakeholders, measurement of algorithm performance across groups, and monitoring of patient outcomes throughout deployment.

    Article  PubMed  PubMed Central  Google Scholar 

  52. Chouldechova A. Fair prediction with disparate impact: a study of Bias in recidivism prediction instruments. Big Data. 2017;5(2):153–63.

    Article  PubMed  Google Scholar 

  53. Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science. 2019;366(6464):447–53.

    Article  CAS  PubMed  Google Scholar 

  54. Huang YA, Zhu W, Smith DK, Harris N, Hoover KW. HIV Preexposure prophylaxis, by race and ethnicity - United States, 2014-2016. MMWR Morb Mortal Wkly Rep. 2018;67(41):1147–50.

    Article  PubMed  PubMed Central  Google Scholar 

  55. Marcus JL, Hurley LB, Hare CB, Silverberg MJ, Volk JE. Disparities in uptake of HIV preexposure prophylaxis in a large integrated healthcare system. Am J Public Health. 2016;106(10):e2–3.

    Article  PubMed  PubMed Central  Google Scholar 

  56. UNAIDS. Miles to go: closing gaps, breaking barriers, righting injustices. 2018 [Available from: https://www.unaids.org/sites/default/files/media_asset/miles-to-go_en.pdf]. Accessed 7 Apr 2020.

  57. Robinson WR, Renson A, Naimi AI. Teaching yourself about structural racism will improve your machine learning. Biostatistics. 2020;21(2):339–44.

  58. Lancki N, Almirol E, Alon L, McNulty M, Schneider JA. Preexposure prophylaxis guidelines have low sensitivity for identifying seroconverters in a sample of young black MSM in Chicago. AIDS. 2018;32(3):383–92.

    Article  PubMed  Google Scholar 

  59. Jones J, Hoenigl M, Siegler AJ, Sullivan PS, Little S, Rosenberg E. Assessing the performance of 3 human immunodeficiency virus incidence risk scores in a cohort of black and white men who have sex with men in the south. Sex Transm Dis. 2017;44(5):297–302.

    Article  PubMed  PubMed Central  Google Scholar 

  60. Eaton LA, Driffin DD, Kegler C, Smith H, Conway-Washington C, White D, et al. The role of stigma and medical mistrust in the routine health care engagement of black men who have sex with men. Am J Public Health. 2015;105(2):e75–82.

    Article  PubMed  PubMed Central  Google Scholar 

  61. Ashton CM, Haidet P, Paterniti DA, Collins TC, Gordon HS, O'Malley K, et al. Racial and ethnic disparities in the use of health services: bias, preferences, or poor communication? J Gen Intern Med. 2003;18(2):146–52.

    Article  PubMed  PubMed Central  Google Scholar 

  62. Nelson A. Unequal treatment: confronting racial and ethnic disparities in health care. J Natl Med Assoc. 2002;94(8):666–8.

    PubMed  PubMed Central  Google Scholar 

  63. NIH Research Portfolio Online Reporting Tools (RePORT). Project Information: 3R01MD013565-02S1. 2019 [Available from: https://projectreporter.nih.gov/project_info_description.cfm?aid=9990158&icde=47042480&ddparam=&ddvalue=&ddsub=&cr=1&csb=default&cs=ASC&pball=]. Accessed 7 Apr 2020.

  64. Pintye J, Drake AL, Kinuthia J, Unger JA, Matemo D, Heffron RA, et al. A risk assessment tool for identifying pregnant and postpartum women who may benefit from Preexposure prophylaxis. Clin Infect Dis. 2017;64(6):751–8.

    PubMed  Google Scholar 

  65. Liu X, Faes L, Kale AU, et al. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digital Health. 2019;1(6):PE271–97.

    Article  Google Scholar 

  66. Chan S, Siegel EL. Will machine learning end the viability of radiology as a thriving medical specialty? Br J Radiol. 2019;92(1094):20180416.

    Article  PubMed  Google Scholar 

  67. Peterson ED. Machine learning, predictive analytics, and clinical practice: can the past inform the present? JAMA. 2019 Nov 22. [Epub ahead of print].

  68. •• Koss CA, Ayieko J, Mwangwa F, et al. Early adopters of human immunodeficiency virus preexposure prophylaxis in a population-based combination prevention study in rural Kenya and Uganda. Clin Infect Dis. 2018;67(12):1853–60 This study used machine learning with data collected on tablets to help identify candidates for PrEP in the SEARCH study in rural Kenya and Uganda. This study provides one of the first examples of implementation of a machine learning approach to identifying PrEP candidates in real time.

    Article  PubMed  PubMed Central  Google Scholar 

  69. Koss C, Charlebois ED, Ayieko J, et al. Uptake, engagement, and adherence to pre-exposure prophylaxis offered after population HIV testing in rural Kenya and Uganda: 72 week interim observational data from the SEARCH trial. Lancet HIV 2020;7(4):e249–61.

Download references

Funding

This work was supported in part by the National Institute of Allergy and Infectious Diseases (K01 AI122853, U01 AI099959, and UM1AI068636) and the President’s Emergency Plan for AIDS Relief (PEPFAR).

Author information

Author notes

  1. Laura B. Balzer and Douglas S. Krakower contributed equally to this work.

Authors and Affiliations

  1. Harvard Medical School and Harvard Pilgrim Health Care Institute, 401 Park Dr, Ste 401, Boston, MA, 02215, USA

    Julia L. Marcus & Whitney C. Sewell

  2. University of Massachusetts Amherst, 715 North Pleasant St, Amherst, MA, 01003, USA

    Laura B. Balzer

  3. Beth Israel Deaconess Medical Center, Division of Infectious Diseases, 110 Francis St., W/LMOB Suite GB, Boston, MA, 02215, USA

    Douglas S. Krakower

Authors
  1. Julia L. Marcus
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Whitney C. Sewell
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Laura B. Balzer
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Douglas S. Krakower
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Julia L. Marcus.

Ethics declarations

Conflict of Interest

Julia Marcus has consulted for Kaiser Permanente Northern California on a research grant from Gilead Sciences. Douglas Krakower has conducted research with project support from Gilead Sciences; has received honoraria for authoring or presenting continuing medical education content for Medscape, MED-IQ, and DKBMed; and has received royalties for authoring content for Uptodate, Inc. Laura Balzer and Whitney Sewell declare no conflicts.

Human and Animal Rights and Informed Consent

All reported studies with human subjects performed by the authors have been previously published and complied with all applicable ethical standards (including the Helsinki declaration and its amendments, institutional/national research committee standards, and international/national/institutional guidelines).

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article is part of the Topical Collection on The Science of Prevention

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Marcus, J.L., Sewell, W.C., Balzer, L.B. et al. Artificial Intelligence and Machine Learning for HIV Prevention: Emerging Approaches to Ending the Epidemic. Curr HIV/AIDS Rep 17, 171–179 (2020). https://doi.org/10.1007/s11904-020-00490-6

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11904-020-00490-6

Keywords

Search

Navigation