TRV-2026-1882Certified recordPeer-reviewed

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…

Health · The Trace — both readings · certified 2026-10-19 · v1 · article view · machine-readable

Current reading — 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.

Current reading — 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.

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.

Evidence

Reader signal

How should this claim be treated?

Cite this record

Truvace Impact Record TRV-2026-1882, v1: “Pilot study of a ChatGPT-based educational and counselling tool in a specialist HIV and sexual health clinic.” Truvace, 2026-10-19. /record/TRV-2026-1882 (accessed at citation time). sha256 3e5346d56b2dfa02…

Calibration history

Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.

  1. Certifiedv13e5346d56b2d…

    Certified into the record

Verify this record
How to verify without trusting this page

Fetch the canonical text of any version from /api/record/TRV-2026-1882 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.