Evaluating an Innovative HIV Self-Testing Service With Web-Based, Real-Time Counseling Provided by an Artificial Intelligence Chatbot (HIVST-Chatbot) in Increasing HIV Self-Testing Use Among Chinese Men Who Have Sex With Men: Protocol for a Noninferiority Randomized Controlled Trial
Bibliographic record
Abstract
BACKGROUND: Counseling support for HIV self-testing (HIVST) users is essential to ensure support and linkage to care among men who have sex with men (MSM). An HIVST service with web-based real-time instruction, pretest, and posttest counseling provided by trained administrators (HIVST-OIC) was developed by previous projects. Although the HIVST-OIC was highly effective in increasing HIVST uptake and the proportion of HIVST users receiving counseling along with testing, it required intensive resources to implement and sustain. The service capacity of HIVST-OIC cannot meet the increasing demands of HIVST. OBJECTIVE: This randomized controlled trial primarily aims to establish whether HIVST-chatbot, an innovative HIVST service with web-based real-time instruction and counseling provided by a fully automated chatbot, would produce effects that are similar to HIVST-OIC in increasing HIVST uptake and the proportion of HIVST users receiving counseling alongside testing among MSM within a 6-month follow-up period. METHODS: A parallel-group, noninferiority randomized controlled trial will be conducted with Chinese-speaking MSM aged ≥18 years with access to live-chat applications. A total of 528 participants will be recruited through multiple sources, including outreach in gay venues, web-based advertisement, and peer referral. After completing the baseline telephone survey, participants will be randomized evenly into the intervention or control groups. Intervention group participants will watch a web-based video promoting HIVST-chatbot and receive a free HIVST kit. The chatbot will contact the participant to implement HIVST and provide standard-of-care, real-time pretest and posttest counseling and instructions on how to use the HIVST kit through WhatsApp. Control group participants will watch a web-based video promoting HIVST-OIC and receive a free HIVST kit in the same manner. Upon appointment, a trained testing administrator will implement HIVST and provide standard-of-care, real-time pretest and posttest counseling and instructions on how to use the HIVST kit through live-chat applications. All participants will complete a telephone follow-up survey 6 months after the baseline. The primary outcomes are HIVST uptake and the proportion of HIVST users receiving counseling support along with testing in the past 6 months, measured at month 6. Secondary outcomes include sexual risk behaviors and uptake of HIV testing other than HIVST during the follow-up period. Intention-to-treat analysis will be used. RESULTS: Recruitment and enrollment of participants started in April 2023. CONCLUSIONS: This study will generate important research and policy implications regarding chatbot use in HIVST services. If HIVST-chatbot is proven noninferior to HIVST-OIC, it can be easily integrated into existing HIVST services in Hong Kong, given its relatively low resource requirements for implementation and maintenance. HIVST-chatbot can potentially overcome the barriers to using HIVST. Therefore, the coverage of HIV testing, the level of support, and the linkage to care for MSM HIVST users will be increased. TRIAL REGISTRATION: ClinicalTrial.gov NCT05796622; https://clinicaltrials.gov/ct2/show/NCT05796622. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/48447.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.047 | 0.026 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.000 |
| Bibliometrics | 0.002 | 0.006 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; both teacher heads agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".