Use of ChatGPT in HIV Infection Counselling and Literacy

Authors

  • José Ganicho Infectious Diseases Department. Hospital de Curry Cabral. Unidade Local de Saúde de São José. Lisbon. Portugal.
  • Maria Carlos Infectious Diseases Department. Hospital de Curry Cabral. Unidade Local de Saúde de São José. Lisbon. Portugal.
  • Gonçalo Cristóvão Infectious Diseases Department. Hospital de Curry Cabral. Unidade Local de Saúde de São José. Lisbon. Portugal.
  • Claudina Cruz Infectious Diseases Department. Hospital de Curry Cabral. Unidade Local de Saúde de São José. Lisbon. Portugal.
  • Marta Leal Infectious Diseases Department. Hospital de Curry Cabral. Unidade Local de Saúde de São José. Lisbon. Portugal.
  • Ana Raquel Garrote Infectious Diseases Department. Hospital de Curry Cabral. Unidade Local de Saúde de São José. Lisbon. Portugal.
  • Diogo Bento Infectious Diseases Department. Hospital de Curry Cabral. Unidade Local de Saúde de São José. Lisbon. Portugal.
  • Diana Seixas Infectious Diseases Department. Hospital de Curry Cabral. Unidade Local de Saúde de São José. Lisbon. Portugal.
  • Maria José Manata Infectious Diseases Department. Hospital de Curry Cabral. Unidade Local de Saúde de São José. Lisbon. Portugal.
  • Fernando Maltez Infectious Diseases Department. Hospital de Curry Cabral. Unidade Local de Saúde de São José. Lisbon. Portugal; Environmental Health Institute. Faculdade de Medicina. Universidade de Lisboa. Lisbon. Portugal.

DOI:

https://doi.org/10.20344/amp.22805

Keywords:

Artificial Intelligence, Health Literacy, HIV Infections/prevention & control, Pre-Exposure Prophylaxis

Abstract

Introduction: Artificial intelligence is an area that has been transforming various sectors of society. One of these tools is ChatGPT (chat generative pre-trained transformer), a large language model-based platform developed to understand language patterns and generate answers. The accessibility, answers in real-time, and privacy make ChatGPT a platform with enormous potential in health counseling. The aim of this study was to explore the potential of ChatGPT in health counseling and literacy regarding HIV infection and pre-exposure prophylaxis (PrEP).
Methods: A team of five experts in infectious diseases was consulted regarding the five most frequently asked questions by patients regarding initial HIV diagnosis and PrEP. The questions were submitted to the ChatGPT-4 version and the quality of the answers was reviewed based on a Likert scale from 1 to 5 (from ‘strongly disagree’ to ‘strongly agree’). The evaluation of the expert’s team followed a set of eight criteria: accuracy, clarity, relevance, depth, objectivity, conciseness, timeliness, and suitability for the target audience.
Results: The five most frequently asked questions by patients regarding HIV infection and the mean evaluation of the answers were: “What does it mean to have HIV? Will I die sooner?” (4.25), “Does HIV infection have a cure? Will I ever be able to stop taking medication?” (4.35), “Can I transmit my infection to other people? How to avoid it?” (4.03), “What are the adverse effects of the antiretroviral treatment?” (3.53), “Can I have unprotected sexual relationships? What are the risks?” (4.53). Regarding PrEP, the more frequently asked questions were: “I want to start pre-exposure prophylaxis. Is it safe?” (4.58), “What are the different regimens of pre-exposure prophylaxis?” (4.63), “After I start taking pre-exposure prophylaxis, do I have to take it forever?” (3.95), “What are the adverse effects of pre-exposure prophylaxis?” (4.63), “Does pre-exposure prophylaxis protect against other sexually transmitted infections or do I have to use condoms?” (4.60).
Conclusion: Only two answers received a rating below four on the 1 - 5 Likert scale, highlighting ChatGPT’s potential as a promising tool for health counselling and literacy, provided ethical and legal concerns are effectively addressed.

Downloads

Download data is not yet available.

References

ChatGPT-4. [cited 2023 Aug 25]. Available from: https://openai.com/gpt- 4.

Yang X, Chen A, PourNejatian N, Chang Shin H, Smith KE, Parisien C, et al. A large language model for electronic health records. npj Digit Med. 2022;5:1-9.

Xiaoliang M, RuQiang Z, Ying L, Congjian D, Dequan D. Design of a large language model for improving customer service in telecom operators. Electron Lett. 2024;60:e13218.

Rodkjaer LØ, Storgaard M, Sørensen NT, Schougaard LM. Levels of health literacy among people living with HIV in outpatient care: a crosssectional study from Denmark. AIDS Res Ther. 2023;20:59.

Ríos-Hoyo A, Shan NL, Li A, Pearson AT, Pusztai L, Howard FM. Evaluation of large language models as a diagnostic aid for complex medical cases. Front Med. 2024;11:1380148.

Ray PP. ChatGPT: a comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet Things Cyber-Phys Syst. 2023;3:121-54

Peres F. Health literacy in ChatGPT: exploring the potential of the use of artificial intelligence to produce academic text. Cienc Saude Colet. 2024;29:e02412023.

Osborn CY, Paasche-Orlow MK, Davis TC, Wolf MS. Health literacy: an overlooked factor in understanding HIV health disparities. Am J Prev Med. 2007;33:374-8.

Mgbako O, Conard R, Mellins CA, Dacus J, Remien RH. A systematic review of factors critical for HIV health literacy, ART adherence and retention in care in the U.S. for racial and ethnic minorities. AIDS Behav. 2022;26:3480-93.

Menichetti J, Hillen MA, Papageorgiou A, Pieterse AH. How can ChatGPT be used to support healthcare communication research? Patient Educ Couns. 2023;115:107947.

Meng X, Yan X, Zhang K, Liu D, Cui X, Yang Y, et al. The application of large language models in medicine: a scoping review. iScience. 2024;27:109713.

McDonald M, Shenkman L. Health literacy and health outcomes of adults in the United States: implications for providers. Internet J Allied Health Sci Pract. 2018;16:1-5.

Ferguson LA, Pawlak R. Health literacy: the road to improved health outcomes. J Nurse Pract. 2011;7:123-9.

Fatani B. ChatGPT for future medical and dental research. Cureus. 2023;15: e37285.

Berkman ND, Sheridan SL, Donahue KE, Halpern DJ, Crotty K. Low health literacy and health outcomes: an updated systematic review. Ann Intern Med. 2011;155:97.

Azizi Z, Alipour P, Gomez S, Broadwin C, Islam S, Sarraju A, et al. Evaluating recommendations about atrial fibrillation for patients and clinicians obtained from chat-based artificial intelligence algorithms. Circ Arrhythm Electrophysiol. 2023;16:415-7.

Ayre J, Mac O, McCaffery K, McKay BR, Liu M, Shi Y, et al. New frontiers in health literacy: using ChatGPT to simplify health information for people in the community. J Gen Intern Med. 2024;39:573-7.

Amutah-Onukagha N, Ibeziako N, Tibbitt C, Louis L, Amarnath A. Wisdom matters: honoring the wisdom and assessing the health literacy of black women living with HIV. J Healthc Sci Humanit. 2021;11:204-24.

Downloads

Published

2025-06-02

How to Cite

1.
Ganicho J, Carlos M, Cristóvão G, Cruz C, Leal M, Garrote AR, Bento D, Seixas D, Manata MJ, Maltez F. Use of ChatGPT in HIV Infection Counselling and Literacy. Acta Med Port [Internet]. 2025 Jun. 2 [cited 2025 Dec. 5];38(6-7):385-92. Available from: https://www.actamedicaportuguesa.com/revista/index.php/amp/article/view/22805

Issue

Vol. 38 No. 6-7 (2025): June-July

Section

Original

License

Copyright (c) 2025 Acta Médica Portuguesa

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

All the articles published in the AMP are open access and comply with the requirements of funding agencies or academic institutions. The AMP is governed by the terms of the Creative Commons ‘Attribution – Non-Commercial Use - (CC-BY-NC)’ license, regarding the use by third parties.

It is the author’s responsibility to obtain approval for the reproduction of figures, tables, etc. from other publications.

Upon acceptance of an article for publication, the authors will be asked to complete the ICMJE “Copyright Liability and Copyright Sharing Statement “(http://www.actamedicaportuguesa.com/info/AMP-NormasPublicacao.pdf) and the “Declaration of Potential Conflicts of Interest” (http:// www.icmje.org/conflicts-of-interest). An e-mail will be sent to the corresponding author to acknowledge receipt of the manuscript.

After publication, the authors are authorised to make their articles available in repositories of their institutions of origin, as long as they always mention where they were published and according to the Creative Commons license.

Crossref
Scopus
Google Scholar
Europe PMC