Truace
Subscribe

ChatGPT-based counselling chatbot in a Singapore HIV and sexual health clinic

Source article: Pilot study of a ChatGPT-based educational and counselling tool in a specialist HIV and sexual health clinic

Objectives: Real-world implementation of large language models such as ChatGPT to enhance patient education remains limited. We evaluated the feasibility, acceptability and attitudes towards a ChatGPT-based counselling tool among patients and healthcare workers (HCWs) in a specialist infectious diseases clinic. Methods: We conducted a prospective clinical implementation study in a specialist HIV and sexual health clinic in Singapore from Jan 2025 to December 2025. Patients interacted with a custom ChatGPT-based…

By the Truvace desk2 min read1 sourcePeer-reviewedTRV-2026-1882· cite & verify
Pilot study of a ChatGPT-based educational and counselling tool in a specialist HIV and sexual health clinic
"Chatbots linked" by Ashhstarr is licensed under CC BY-SA 4.0. To view a copy of this license, visit https://creativecommons.org/licenses/by-sa/4.0/.
Trace impact readingNegative state
P 74The P score combines the specificity and measured human impact of the grounded problem claim with the strength of this Trace’s cited sources.

Both sides are scored from claims and sources, not community votes.

G 69The G score combines the specificity and measured human impact of the grounded gain claim with the strength of this Trace’s cited sources.

In brief

Researchers ran a prospective implementation study in a specialist HIV and sexual health clinic in Singapore during 2025. Patients used a custom ChatGPT-based chatbot before routine counselling with a physician or pharmacist, and the responses were then reviewed together in the consultation.

The findings suggest large language models could support patient education in sensitive clinical settings, but the evidence is early. Patients and staff accepted the tool, yet worries about accuracy and missing nuance remain, and clinical effectiveness has not been tested.

Main points

  1. The chatbot was used most often for counselling on starting or switching antiretroviral therapy and for sexual health advice.
  2. The analysis covered 35 patient assessments and 35 healthcare worker assessments.
  3. Patients scored lower on the perceived risk measure than HCWs (median 13 vs 18), while anxiety scores were similar.
  4. Technology/social influence scores were high in both groups, with an overall median of 20, and most participants were willing to use the tool again.

The gain

Patients and staff at a Singapore HIV clinic found a chatbot-assisted pre-counselling step feasible and generally acceptable, with feedback citing better patient understanding and more focused consultations.

The problem

The same pilot participants raised concerns about the chatbot's lack of contextual nuance and occasional inaccuracies, and patients reported greater perceived risk than staff.

The rundown

The study ran from January to December 2025 in a specialist infectious diseases clinic. Patients interacted with the chatbot before seeing a physician or pharmacist, who then reviewed the chatbot's responses with them during the consultation.

After the interaction, patients and healthcare workers completed structured surveys drawn from a validated tool, covering perceived risk, anxiety, technology/social influence and intention for future use.

Qualitative feedback pointed to better patient understanding and more focused consultations. Participants also reported lack of contextual nuance and occasional inaccuracies, and the authors call for studies of accuracy and clinical effectiveness before wider rollout.

What this doesn’t fix

This was a small pilot with 35 patient and 35 healthcare worker assessments at a single clinic, and accuracy and clinical effectiveness were not evaluated.

Sources

  1. Peer-reviewedHIV Medicine2026-10-18

The debate