Faculdade de Medicina Preventiva, Universidade de São Paulo, São Paulo, Brazil.
Unité Mixte de Recherche 1296 Radiations: défense, santé et environnements, Lyon 2 University, Lyon, France.
J Med Internet Res. 2023 Jun 23;25:e41881. doi: 10.2196/41881.
HIV incidence rates have increased in adolescent men who have sex with men (AMSM) and adolescent transgender women (ATGW). Thus, it is essential to promote access to HIV prevention, including pre-exposure prophylaxis (PrEP), among these groups. Moreover, using artificial intelligence and online social platforms to create demand and access to health care services are essential tools for adolescents and youth.
This study aims to describe the participative process of developing a chatbot using artificial intelligence to create demand for PrEP use among AMSM and ATGW in Brazil. Furthermore, it analyzes the chatbot's acceptability, functionality, and usability and its results on the demand creation for PrEP.
The chatbot Amanda Selfie integrates the demand creation strategies based on social networks (DCSSNs) of the PrEP1519 study. She was conceived as a Black transgender woman and to function as a virtual peer educator. The development process occurred in 3 phases (conception, trial, and final version) and lasted 21 months. A mixed methodology was used for the evaluations. Qualitative approaches, such as in-depth adolescent interviews, were used to analyze acceptability and usability, while quantitative methods were used to analyze the functionality and result of the demand creation for PrEP based on interactions with Amanda and information from health care services about using PrEP. To evaluate Amanda's result on the demand creation for PrEP, we analyzed sociodemographic profiles of adolescents who interacted at least once with her and developed a cascade model containing the number of people at various stages between the first interaction and initiation of PrEP (PrEP uptake). These indicators were compared with other DCSs developed in the PrEP1519 study using chi-square tests and residual analysis (P=.05).
Amanda Selfie was well accepted as a peer educator, clearly and objectively communicating on topics such as gender identity, sexual experiences, HIV, and PrEP. The chatbot proved appropriate for answering questions in an agile and confidential manner, using the language used by AMSM and ATGW and with a greater sense of security and less judgment. The interactions with Amanda Selfie combined with a health professional were well evaluated and improved the appointment scheduling. The chatbot interacted with most people (757/1239, 61.1%) reached by the DCSSNs. However, when compared with the other DCSSNs, Amanda was not efficient in identifying AMSM/ATGW (359/482, 74.5% vs 130/757, 17.2% of total interactions, respectively) and in PrEP uptake (90/359, 25.1% vs 19/130, 14.6%). The following profiles were associated (P<.001) with Amanda Selfie's demand creation, when compared with other DCS: ATGW and adolescents with higher levels of schooling and White skin color.
Using a chatbot to create PrEP demand among AMSM and ATGW was well accepted, especially for ATGW with higher levels of schooling. A complimentary dialog with a health professional increased PrEP uptake, although it remained lower than the results of the other DCSSNs.
艾滋病毒发病率在与男性发生性关系的男青少年(AMSM)和跨性别女性青少年(ATGW)中有所增加。因此,必须促进这些群体获得艾滋病毒预防措施,包括暴露前预防(PrEP)。此外,利用人工智能和在线社交平台创造需求并获得医疗服务是青少年和青年的重要工具。
本研究旨在描述使用人工智能为巴西 AMSM 和 ATGW 创建 PrEP 使用需求的聊天机器人的参与式开发过程。此外,还分析了聊天机器人的可接受性、功能和可用性及其在 PrEP 需求创造方面的结果。
聊天机器人 Amanda Selfie 集成了 PrEP1519 研究中的基于社交网络的需求创造策略(DCSSNs)。她被构想为一名黑人跨性别女性,并作为虚拟同伴教育者发挥作用。开发过程分为 3 个阶段(构思、试验和最终版本),历时 21 个月。采用混合方法进行评估。使用深入的青少年访谈等定性方法来分析可接受性和可用性,而使用定量方法来分析基于与 Amanda 的交互以及医疗保健服务提供的有关使用 PrEP 的信息的 PrEP 功能和创建需求的结果。为了评估 Amanda 在 PrEP 需求创造方面的效果,我们分析了至少与她互动过一次的青少年的社会人口统计学特征,并开发了一个包含从第一次互动到开始使用 PrEP(PrEP 使用率)各个阶段人数的级联模型。使用卡方检验和残差分析(P=.05)将这些指标与 PrEP1519 研究中的其他 DCS 进行比较。
Amanda Selfie 作为同伴教育者被很好地接受,能够清晰客观地就性别认同、性经历、艾滋病毒和 PrEP 等主题进行交流。该聊天机器人在以 AMSM 和 ATGW 使用的语言敏捷且机密地回答问题方面表现出色,并且具有更高的安全感和更少的判断力。与 Amanda Selfie 的互动结合医疗专业人员的互动,得到了很好的评价,并改善了预约安排。该聊天机器人与 DCSSNs 联系到的大多数人(757/1239,61.1%)进行了互动。然而,与其他 DCSSNs 相比,Amanda 在识别 AMSM/ATGW 方面效率不高(359/482,74.5% 与 130/757,分别为总互动的 17.2%),在 PrEP 使用率方面也不高(90/359,25.1% 与 19/130,14.6%)。与其他 DCS 相比,以下特征与 Amanda Selfie 的需求创造相关(P<.001):跨性别女性和受教育程度较高的青少年以及白皮肤。
在 AMSM 和 ATGW 中使用聊天机器人来创造 PrEP 需求的方法得到了很好的接受,特别是对受教育程度较高的跨性别女性。与医疗保健专业人员进行补充对话增加了 PrEP 的使用率,尽管仍低于其他 DCS 的结果。