Barriers and facilitators to engagement with artificial intelligence (AI)-based chatbots for sexual and reproductive health advice: a qualitative analysis

Sexual health in the era of artificial intelligence: a scoping review of the literature

INTRODUCTION

Artificial Intelligence (AI) has witnessed significant growth in the field of medicine, leveraging machine learning, artificial neuron networks, and large language models. These technologies are effective in disease diagnosis, education, and prevention, while raising ethical concerns and potential challenges. However, their utility in sexual medicine remains relatively unexplored.

OBJECTIVE

We aim to provide a comprehensive summary of the status of AI in the field of sexual medicine.

METHODS

A comprehensive search was conducted using MeSH keywords, including "artificial intelligence," "sexual medicine," "sexual health," and "machine learning." Two investigators screened articles for eligibility within the PubMed and MEDLINE databases, with conflicts resolved by a third reviewer. Articles in English language that reported on AI in sexual medicine and health were included. A total of 69 full-text articles were systematically analyzed based on predefined inclusion criteria. Data extraction included information on article characteristics, study design, assessment methods, and outcomes.

RESULTS

The initial search yielded 905 articles relevant to AI in sexual medicine. Upon assessing the full texts of 121 articles for eligibility, 52 studies unrelated to AI in sexual health were excluded, resulting in 69 articles for systematic review. The analysis revealed AI's accuracy in preventing, diagnosing, and decision-making in sexually transmitted diseases. AI also demonstrated the ability to diagnose and offer precise treatment plans for male and female sexual dysfunction and infertility, accurately predict sex from bone and teeth imaging, and correctly predict and diagnose sexual orientation and relationship issues. AI emerged as a promising modality with significant implications for the future of sexual medicine.

CONCLUSIONS

Further research is essential to unlock the potential of AI in sexual medicine. AI presents advantages such as accessibility, user-friendliness, confidentiality, and a preferred source of sexual health information. However, it still lags human healthcare providers in terms of compassion and clinical expertise.

Collecting initial accounts using ChatCharlie chatbot improves eyewitness memory in later investigative interviews

Initial account interviews (IAi) offer eyewitnesses more immediate opportunities to answer a series of brief questions about their experiences prior to an in-depth, more formal investigative interview. An IAi is typically elicited in-person near/at the scene of a crime using broadly systematic questioning. Retrieval practice can improve subsequent recall in some contexts, but there is a dearth of research centred on the potential costs and benefits of a quick IAi. Furthermore, where an in-person IAi is impossible, no alternative quick provision exists. Given the systematic nature of the IAi protocol, we developed a conversational chatbot as a potential alternative. Using a mock-witness paradigm, we investigated the memory performance of adults from the general population during in-depth in-person interviews one week after having provided an IAi 10 min post event either (1) in person, (2) via the ChatCharlie chatbot, or (3) no IAi (control). IAi conditions leveraged significantly improved event recall during later investigative interviews versus the Control. Accounts were more accurate and complete, and more correct information was remembered without increased errors indicating the potential of digital agents for IAi purposes Findings concur with predictions from theoretical understanding of episodic memory consolidation and the empirical eyewitness literature regarding the benefits of practice in some contexts.

Investigating Whether AI Will Replace Human Physicians and Understanding the Interplay of the Source of Consultation, Health-Related Stigma, and Explanations of Diagnoses on Patients' Evaluations of Medical Consultations: Randomized Factorial Experiment

BACKGROUND

The increasing use of artificial intelligence (AI) in medical diagnosis and consultation promises benefits such as greater accuracy and efficiency. However, there is little evidence to systematically test whether the ideal technological promises translate into an improved evaluation of the medical consultation from the patient's perspective. This perspective is significant because AI as a technological solution does not necessarily improve patient confidence in diagnosis and adherence to treatment at the functional level, create meaningful interactions between the medical agent and the patient at the relational level, evoke positive emotions, or reduce the patient's pessimism at the emotional level.

OBJECTIVE

This study aims to investigate, from a patient-centered perspective, whether AI or human-involved AI can replace the role of human physicians in diagnosis at the functional, relational, and emotional levels as well as how some health-related differences between human-AI and human-human interactions affect patients' evaluations of the medical consultation.

METHODS

A 3 (consultation source: AI vs human-involved AI vs human) × 2 (health-related stigma: low vs high) × 2 (diagnosis explanation: without vs with explanation) factorial experiment was conducted with 249 participants. The main effects and interaction effects of the variables were examined on individuals' functional, relational, and emotional evaluations of the medical consultation.

RESULTS

Functionally, people trusted the diagnosis of the human physician (mean 4.78-4.85, SD 0.06-0.07) more than medical AI (mean 4.34-4.55, SD 0.06-0.07) or human-involved AI (mean 4.39-4.56, SD 0.06-0.07; P<.001), but at the relational and emotional levels, there was no significant difference between human-AI and human-human interactions (P>.05). Health-related stigma had no significant effect on how people evaluated the medical consultation or contributed to preferring AI-powered systems over humans (P>.05); however, providing explanations of the diagnosis significantly improved the functional (P<.001), relational (P<.05), and emotional (P<.05) evaluations of the consultation for all 3 medical agents.

CONCLUSIONS

The findings imply that at the current stage of AI development, people trust human expertise more than accurate AI, especially for decisions traditionally made by humans, such as medical diagnosis, supporting the algorithm aversion theory. Surprisingly, even for highly stigmatized diseases such as AIDS, where we assume anonymity and privacy are preferred in medical consultations, the dehumanization of AI does not contribute significantly to the preference for AI-powered medical agents over humans, suggesting that instrumental needs of diagnosis override patient privacy concerns. Furthermore, explaining the diagnosis effectively improves treatment adherence, strengthens the physician-patient relationship, and fosters positive emotions during the consultation. This provides insights for the design of AI medical agents, which have long been criticized for lacking transparency while making highly consequential decisions. This study concludes by outlining theoretical contributions to research on health communication and human-AI interaction and discusses the implications for the design and application of medical AI.

Current Landscape and Future Directions for Mental Health Conversational Agents for Youth: Scoping Review

BACKGROUND

Conversational agents (CAs; chatbots) are systems with the ability to interact with users using natural human dialogue. They are increasingly used to support interactive knowledge discovery of sensitive topics such as mental health topics. While much of the research on CAs for mental health has focused on adult populations, the insights from such research may not apply to CAs for youth.

OBJECTIVE

This study aimed to comprehensively evaluate the state-of-the-art research on mental health CAs for youth.

METHODS

Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, we identified 39 peer-reviewed studies specific to mental health CAs designed for youth across 4 databases, including ProQuest, Scopus, Web of Science, and PubMed. We conducted a scoping review of the literature to evaluate the characteristics of research on mental health CAs designed for youth, the design and computational considerations of mental health CAs for youth, and the evaluation outcomes reported in the research on mental health CAs for youth.

RESULTS

We found that many mental health CAs (11/39, 28%) were designed as older peers to provide therapeutic or educational content to promote youth mental well-being. All CAs were designed based on expert knowledge, with a few that incorporated inputs from youth. The technical maturity of CAs was in its infancy, focusing on building prototypes with rule-based models to deliver prewritten content, with limited safety features to respond to imminent risk. Research findings suggest that while youth appreciate the 24/7 availability of friendly or empathetic conversation on sensitive topics with CAs, they found the content provided by CAs to be limited. Finally, we found that most (35/39, 90%) of the reviewed studies did not address the ethical aspects of mental health CAs, while youth were concerned about the privacy and confidentiality of their sensitive conversation data.

CONCLUSIONS

Our study highlights the need for researchers to continue to work together to align evidence-based research on mental health CAs for youth with lessons learned on how to best deliver these technologies to youth. Our review brings to light mental health CAs needing further development and evaluation. The new trend of large language model-based CAs can make such technologies more feasible. However, the privacy and safety of the systems should be prioritized. Although preliminary evidence shows positive trends in mental health CAs, long-term evaluative research with larger sample sizes and robust research designs is needed to validate their efficacy. More importantly, collaboration between youth and clinical experts is essential from the early design stages through to the final evaluation to develop safe, effective, and youth-centered mental health chatbots. Finally, best practices for risk mitigation and ethical development of CAs with and for youth are needed to promote their mental well-being.

Opening the digital doorway to sexual healthcare: Recommendations from a behaviour change wheel analysis of barriers and facilitators to seeking online sexual health information and support among underserved populations

BACKGROUND

The ability to access and navigate online sexual health information and support is increasingly needed in order to engage with wider sexual healthcare. However, people from underserved populations may struggle to pass though this "digital doorway". Therefore, using a behavioural science approach, we first aimed to identify barriers and facilitators to i) seeking online sexual health information and ii) seeking online sexual health support. Subsequently, we aimed to generate theory-informed recommendations to improve these access points.

METHODS

The PROGRESSPlus framework guided purposive recruitment (15.10.21-18.03.22) of 35 UK participants from diverse backgrounds, including 51% from the most deprived areas and 26% from minoritised ethnic groups. Using semi-structured interviews and thematic analysis, we identified barriers and facilitators to seeking online sexual health information and support. A Behaviour Change Wheel (BCW) analysis then identified recommendations to better meet the needs of underserved populations.

RESULTS

We found diverse barriers and facilitators. Barriers included low awareness of and familiarity with online information and support; perceptions that online information and support were unlikely to meet the needs of underserved populations; overwhelming volume of information sources; lack of personal relevancy; chatbots/automated responses; and response wait times. Facilitators included clarity about credibility and quality; inclusive content; and in-person assistance. Recommendations included: Education and Persuasion e.g., online and offline promotion and endorsement by healthcare professionals and peers; Training and Modelling e.g., accessible training to enhance searching skills and credibility appraisal; and Environmental Restructuring and Enablement e.g., modifications to ensure online information and support are simple and easy to use, including video/audio options for content.

CONCLUSIONS

Given that access to many sexual health services is now digital, our analyses produced recommendations pivotal to increasing access to wider sexual healthcare among underserved populations. Implementing these recommendations could reduce inequalities associated with accessing and using online sexual health service.

The impact of Chatbot-Assisted Self Assessment (CASA) on intentions for sexual health screening in people from minoritised ethnic groups at risk of sexually transmitted infections

Background Sexually transmitted infections (STIs) present a significant global public health issue, with disparities in STI rates often observed across ethnic groups. The study investigates the impact of Chatbot-Assisted Self Assessment (CASA) on the intentions for sexual health screening within minoritised ethnic groups (MEGs) at risk of STIs as well as the subsequent use of a chatbot for booking STI screening. Methods A simulation within-subject design was utilised to evaluate the effect of CASA on intentions for STI/HIV screening, concern about STIs, and attitudes towards STI screening. Screening intentions served as the dependent variable, while demographic and behavioural factors related to STI/HIV risk were the independent variables. ANCOVA tests were conducted to measure the impact of CASA on these perceptions. Results Involving 548 participants (54% women, 66% black, average age=30years), the study found that CASA positively influenced screening intentions t (547)=-10.3, P t (544)=-4.96, P t (543)=-4.36, P Conclusion CASA increased motivations for STI screening intentions among ethnically diverse communities. The intervention's non-judgemental nature and the chatbot's ability to emulate sexual history-taking were critical in fostering an environment conducive to behavioural intention change. The study's high acceptability indicates the potential for broader application in digital health interventions. However, the limitation of not tracking actual post-intervention behaviour warrants further investigation into CASA's real-world efficacy.

Chatbots That Deliver Contraceptive Support: Systematic Review

BACKGROUND

A chatbot is a computer program that is designed to simulate conversation with humans. Chatbots may offer rapid, responsive, and private contraceptive information; counseling; and linkages to products and services, which could improve contraceptive knowledge, attitudes, and behaviors.

OBJECTIVE

This review aimed to systematically collate and interpret evidence to determine whether and how chatbots improve contraceptive knowledge, attitudes, and behaviors. Contraceptive knowledge, attitudes, and behaviors include access to contraceptive information, understanding of contraceptive information, access to contraceptive services, contraceptive uptake, contraceptive continuation, and contraceptive communication or negotiation skills. A secondary aim of the review is to identify and summarize best practice recommendations for chatbot development to improve contraceptive outcomes, including the cost-effectiveness of chatbots where evidence is available.

METHODS

We systematically searched peer-reviewed and gray literature (2010-2022) for papers that evaluated chatbots offering contraceptive information and services. Sources were included if they featured a chatbot and addressed an element of contraception, for example, uptake of hormonal contraceptives. Literature was assessed for methodological quality using appropriate quality assessment tools. Data were extracted from the included sources using a data extraction framework. A narrative synthesis approach was used to collate qualitative evidence as quantitative evidence was too sparse for a quantitative synthesis to be carried out.

RESULTS

We identified 15 sources, including 8 original research papers and 7 gray literature papers. These sources included 16 unique chatbots. This review found the following evidence on the impact and efficacy of chatbots: a large, robust randomized controlled trial suggests that chatbots have no effect on intention to use contraception; a small, uncontrolled cohort study suggests increased uptake of contraception among adolescent girls; and a development report, using poor-quality methods, suggests no impact on improved access to services. There is also poor-quality evidence to suggest increased contraceptive knowledge from interacting with chatbot content. User engagement was mixed, with some chatbots reaching wide audiences and others reaching very small audiences. User feedback suggests that chatbots may be experienced as acceptable, convenient, anonymous, and private, but also as incompetent, inconvenient, and unsympathetic. The best practice guidance on the development of chatbots to improve contraceptive knowledge, attitudes, and behaviors is consistent with that in the literature on chatbots in other health care fields.

CONCLUSIONS

We found limited and conflicting evidence on chatbots to improve contraceptive knowledge, attitudes, and behaviors. Further research that examines the impact of chatbot interventions in comparison with alternative technologies, acknowledges the varied and changing nature of chatbot interventions, and seeks to identify key features associated with improved contraceptive outcomes is needed. The limitations of this review include the limited evidence available on this topic, the lack of formal evaluation of chatbots in this field, and the lack of standardized definition of what a chatbot is.

Evaluation framework for conversational agents with artificial intelligence in health interventions: a systematic scoping review

OBJECTIVES

Conversational agents (CAs) with emerging artificial intelligence present new opportunities to assist in health interventions but are difficult to evaluate, deterring their applications in the real world. We aimed to synthesize existing evidence and knowledge and outline an evaluation framework for CA interventions.

MATERIALS AND METHODS

We conducted a systematic scoping review to investigate designs and outcome measures used in the studies that evaluated CAs for health interventions. We then nested the results into an overarching digital health framework proposed by the World Health Organization (WHO).

RESULTS

The review included 81 studies evaluating CAs in experimental (n = 59), observational (n = 15) trials, and other research designs (n = 7). Most studies (n = 72, 89%) were published in the past 5 years. The proposed CA-evaluation framework includes 4 evaluation stages: (1) feasibility/usability, (2) efficacy, (3) effectiveness, and (4) implementation, aligning with WHO's stepwise evaluation strategy. Across these stages, this article presents the essential evidence of different study designs (n = 8), sample sizes, and main evaluation categories (n = 7) with subcategories (n = 40). The main evaluation categories included (1) functionality, (2) safety and information quality, (3) user experience, (4) clinical and health outcomes, (5) costs and cost benefits, (6) usage, adherence, and uptake, and (7) user characteristics for implementation research. Furthermore, the framework highlighted the essential evaluation areas (potential primary outcomes) and gaps across the evaluation stages.

DISCUSSION AND CONCLUSION

This review presents a new framework with practical design details to support the evaluation of CA interventions in healthcare research.

PROTOCOL REGISTRATION

The Open Science Framework (https://osf.io/9hq2v) on March 22, 2021.

User experiences of an AI application for predicting risk of sexually transmitted infections

Objective

Awareness of one's individual risk of sexually transmitted infections (STIs) and human immunodeficiency virus (HIV) is a necessary precursor to engagement with prevention strategies and sexual health care. Web-based sexual health applications may improve engagement in sexual health prevention and care by providing individualised and evidence-based sexual health information. The STARTOnline (Supporting Timely and Appropriate Review and Treatment Online) study sought the views of sexual health service users on three web-based sexual health applications to better understand their usefulness, acceptability and accessibility. This paper reports the views and experiences of users of one of the applications called MySTIRisk. MySTIRisk estimates the risk of three common STIs and HIV using data from attendees of a metropolitan sexual health service.

Methods

This study used a bespoke qualitative design, informed by a developmental evaluation approach. Melbourne Sexual Health Centre clinic attendees' views were sought using semi-structured interviews conducted between October 2023 and January 2024 via videoconferencing, telephone and on site at the clinic. Data was analysed using qualitative data analysis methods.

Results

A diverse group of 14 participants described an ideal pathway to better sexual health outcomes that might be facilitated by use of the MySTIRisk application, particularly for individuals with limited sexual health knowledge, or affected by stigma and geographical barriers. This pathway was described as: 1) being concerned about my sexual health; 2) checking my STI risk easily and privately; 3) understanding and trusting the result; and 4) deciding how to look after my health. Factors that might influence this pathway were also described, including areas for improvement in accessibility and acceptability.

Conclusion

These findings support the role of web-based sexual health applications in facilitating access to sexual health education and behavioural change and underscore the importance of codesign approaches in improving their uptake and impact.

Women's perspectives on the use of artificial intelligence (AI)-based technologies in mental healthcare

This study aimed to evaluate women's attitudes towards artificial intelligence (AI)-based technologies used in mental health care. We conducted a cross-sectional, online survey of U.S. adults reporting female sex at birth focused on bioethical considerations for AI-based technologies in mental healthcare, stratifying by previous pregnancy. Survey respondents (n = 258) were open to AI-based technologies in mental healthcare but concerned about medical harm and inappropriate data sharing. They held clinicians, developers, healthcare systems, and the government responsible for harm. Most reported it was "very important" for them to understand AI output. More previously pregnant respondents reported being told AI played a small role in mental healthcare was "very important" versus those not previously pregnant (P = .03). We conclude that protections against harm, transparency around data use, preservation of the patient-clinician relationship, and patient comprehension of AI predictions may facilitate trust in AI-based technologies for mental healthcare among women.

"But can chatbots understand sex?" Attitudes towards artificial intelligence chatbots amongst sexual and reproductive health professionals: An exploratory mixed-methods study

BACKGROUND

Artificial Intelligence (AI)-enabled chatbots can offer anonymous education about sexual and reproductive health (SRH). Understanding chatbot acceptability and feasibility allows the identification of barriers to the design and implementation.

METHODS

In 2020, we conducted an online survey and qualitative interviews with SRH professionals recruited online to explore the views on AI, automation and chatbots. Qualitative data were analysed thematically.

RESULTS

Amongst 150 respondents (48% specialist doctor/consultant), only 22% perceived chatbots as effective and 24% saw them as ineffective for SRH advice [Mean = 2.91, SD = 0.98, range: 1-5]. Overall, there were mixed attitudes towards SRH chatbots [Mean = 4.03, SD = 0.87, range: 1-7]. Chatbots were most acceptable for appointment booking, general sexual health advice and signposting, but not acceptable for safeguarding, virtual diagnosis, and emotional support. Three themes were identified: "Moving towards a 'digital' age'", "AI improving access and service efficacy", and "Hesitancy towards AI".

CONCLUSIONS

Half of SRH professionals were hesitant about the use of chatbots in SRH services, attributed to concerns about patient safety, and lack of familiarity with this technology. Future studies should explore the role of AI chatbots as supplementary tools for SRH promotion. Chatbot designers need to address the concerns of health professionals to increase acceptability and engagement with AI-enabled services.

Factors Influencing the Acceptability, Acceptance, and Adoption of Conversational Agents in Health Care: Integrative Review

BACKGROUND

Conversational agents (CAs), also known as chatbots, are digital dialog systems that enable people to have a text-based, speech-based, or nonverbal conversation with a computer or another machine based on natural language via an interface. The use of CAs offers new opportunities and various benefits for health care. However, they are not yet ubiquitous in daily practice. Nevertheless, research regarding the implementation of CAs in health care has grown tremendously in recent years.

OBJECTIVE

This review aims to present a synthesis of the factors that facilitate or hinder the implementation of CAs from the perspectives of patients and health care professionals. Specifically, it focuses on the early implementation outcomes of acceptability, acceptance, and adoption as cornerstones of later implementation success.

METHODS

We performed an integrative review. To identify relevant literature, a broad literature search was conducted in June 2021 with no date limits and using all fields in PubMed, Cochrane Library, Web of Science, LIVIVO, and PsycINFO. To keep the review current, another search was conducted in March 2022. To identify as many eligible primary sources as possible, we used a snowballing approach by searching reference lists and conducted a hand search. Factors influencing the acceptability, acceptance, and adoption of CAs in health care were coded through parallel deductive and inductive approaches, which were informed by current technology acceptance and adoption models. Finally, the factors were synthesized in a thematic map.

RESULTS

Overall, 76 studies were included in this review. We identified influencing factors related to 4 core Unified Theory of Acceptance and Use of Technology (UTAUT) and Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) factors (performance expectancy, effort expectancy, facilitating conditions, and hedonic motivation), with most studies underlining the relevance of performance and effort expectancy. To meet the particularities of the health care context, we redefined the UTAUT2 factors social influence, habit, and price value. We identified 6 other influencing factors: perceived risk, trust, anthropomorphism, health issue, working alliance, and user characteristics. Overall, we identified 10 factors influencing acceptability, acceptance, and adoption among health care professionals (performance expectancy, effort expectancy, facilitating conditions, social influence, price value, perceived risk, trust, anthropomorphism, working alliance, and user characteristics) and 13 factors influencing acceptability, acceptance, and adoption among patients (additionally hedonic motivation, habit, and health issue).

CONCLUSIONS

This review shows manifold factors influencing the acceptability, acceptance, and adoption of CAs in health care. Knowledge of these factors is fundamental for implementation planning. Therefore, the findings of this review can serve as a basis for future studies to develop appropriate implementation strategies. Furthermore, this review provides an empirical test of current technology acceptance and adoption models and identifies areas where additional research is necessary.

TRIAL REGISTRATION

PROSPERO CRD42022343690; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=343690.

Chatbots to Improve Sexual and Reproductive Health: Realist Synthesis

BACKGROUND

Digital technologies may improve sexual and reproductive health (SRH) across diverse settings. Chatbots are computer programs designed to simulate human conversation, and there is a growing interest in the potential for chatbots to provide responsive and accurate information, counseling, linkages to products and services, or a companion on an SRH journey.

OBJECTIVE

This review aimed to identify assumptions about the value of chatbots for SRH and collate the evidence to support them.

METHODS

We used a realist approach that starts with an initial program theory and generates causal explanations in the form of context, mechanism, and outcome configurations to test and develop that theory. We generated our program theory, drawing on the expertise of the research team, and then searched the literature to add depth and develop this theory with evidence.

RESULTS

The evidence supports our program theory, which suggests that chatbots are a promising intervention for SRH information and service delivery. This is because chatbots offer anonymous and nonjudgmental interactions that encourage disclosure of personal information, provide complex information in a responsive and conversational tone that increases understanding, link to SRH conversations within web-based and offline social networks, provide immediate support or service provision 24/7 by automating some tasks, and provide the potential to develop long-term relationships with users who return over time. However, chatbots may be less valuable where people find any conversation about SRH (even with a chatbot) stigmatizing, for those who lack confidential access to digital devices, where conversations do not feel natural, and where chatbots are developed as stand-alone interventions without reference to service contexts.

CONCLUSIONS

Chatbots in SRH could be developed further to automate simple tasks and support service delivery. They should prioritize achieving an authentic conversational tone, which could be developed to facilitate content sharing in social networks, should support long-term relationship building with their users, and should be integrated into wider service networks.

Increasing Participation in a TelePrEP Program for Sexual and Gender Minority Adolescents and Young Adults in Louisiana: Protocol for an SMS Text Messaging-Based Chatbot

BACKGROUND

Sexual and gender minority (SGM) adolescents and young adults (AYAs) are at increased risk of HIV infection, particularly in the Southern United States. Despite the availability of effective biomedical prevention strategies, such as pre-exposure prophylaxis (PrEP), access and uptake remain low among SGM AYAs. In response, the Louisiana Department of Health initiated the LA TelePrEP Program, which leverages the power of telemedicine to connect Louisiana residents to PrEP. A virtual TelePrEP Navigator guides users through the enrollment process, answers questions, schedules appointments, and facilitates lab testing and medication delivery. To increase the participation of SGM AYAs in the program, the TelePrEP program partnered with researchers to develop a chatbot that would facilitate access to the program and support navigator functions. Chatbots are capable of carrying out many functions that reduce employee workload, and despite their successful use in health care and public health, they are relatively new to HIV prevention.

OBJECTIVE

In this paper, we describe the iterative and community-engaged process that we used to develop an SMS text messaging-based chatbot tailored to SGM AYAs that would support navigator functions and disseminate PrEP-related information.

METHODS

Our process was comprised of 2 phases: conceptualization and development. In the conceptualization phase, aspects of navigator responsibilities, program logistics, and user interactions to prioritize in chatbot programming (eg, scheduling appointments and answering questions) were identified. We also selected a commercially available chatbot platform that could execute these functions and could be programmed with minimal coding experience. In the development phase, we engaged Department of Health staff and SGM AYAs within our professional and personal networks. Five different rounds of testing were conducted with various groups to evaluate each iteration of the chatbot. After each iteration of the testing process, the research team met to discuss feedback, guide the programmer on incorporating modifications, and re-evaluate the chatbot's functionality.

RESULTS

Through our highly collaborative and community-engaged process, a rule-based chatbot with artificial intelligence components was successfully created. We gained important knowledge that could advance future chatbot development efforts for HIV prevention. Key to the PrEPBot's success was resolving issues that hampered the user experience, like asking unnecessary questions, responding too quickly, and misunderstanding user input.

CONCLUSIONS

HIV prevention researchers can feasibly and efficiently program a rule-based chatbot with the assistance of commercially available tools. Our iterative process of engaging researchers, program personnel, and different subgroups of SGM AYAs to obtain input was key to successful chatbot development. If the results of this pilot trial show that the chatbot is feasible and acceptable to SGM AYAs, future HIV researchers and practitioners could consider incorporating chatbots as part of their programs.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/42983.