TRV-2026-1911Certified recordPeer-reviewed

Evaluating COPD care assistance: a comparative study of ChatGPT-3.5, ChatGPT-4.0, and ERNIE bot performance

Background: Large language model (LLM) chatbots are increasingly used to provide health information, yet their reliability in addressing chronic obstructive pulmonary disease (COPD) care questions in the Chinese context remains unclear. To evaluate and compare the performance of three publicly available LLM chatbots - ChatGPT-3.5, ChatGPT-4.0 (OpenAI), and ERNIE Bot (Baidu) - in answering chronic obstructive pulmonary disease (COPD) care questions in China. Methods: We performed a cross-sectional comparative eva…

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

Current reading — gain

Most chatbot answers to Chinese-language COPD care questions were rated accurate by respiratory physicians, suggesting a role in basic patient education.

Current reading — problem

Responses from the same chatbots lacked comprehensiveness and concrete, patient-executable steps, so they are unsuitable as standalone clinical advice.

What this doesn’t fix

The evaluation was a cross-sectional test of 40 questions in Chinese, and the ERNIE Bot advantage was described only for this Chinese-language evaluation, so results may not generalise to other languages or real patient use.

Evidence

Reader signal

How should this claim be treated?

Cite this record

Truvace Impact Record TRV-2026-1911, v1: “Evaluating COPD care assistance: a comparative study of ChatGPT-3.5, ChatGPT-4.0, and ERNIE bot performance.” Truvace, 2026-10-19. /record/TRV-2026-1911 (accessed at citation time). sha256 763c90be4545b8a4…

Calibration history

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

  1. Certifiedv1763c90be4545…

    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-2026-1911 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.