Comparative evaluation of ChatGPT-4, Claude 3.5 Sonnet, and Gemini 1.5 Advanced for patient education on chronic obstructive pulmonary disease (COPD): a global expert assessment of artificial intelligence (AI)-generated responses
Bibliographic record
Abstract
Background: AI models like ChatGPT-4, Claude 3.5 Sonnet, and Gemini 1.5 Advanced are increasingly used to generate information, but their effectiveness in delivering accurate and reliable health content related to COPD remains insufficiently explored. Objective: To evaluate and compare the response quality of AI-generated answers to frequently asked questions about COPD. Methods: 30 COPD-related questions, based on the 2024 Global Initiative for Chronic Obstructive Lung Disease strategy document, were input into three AI platforms in September 2024. The 90 responses were evaluated by expert pulmonologists from six continents, blinded to the AI platform, and assessed on a Likert scale (1–5) across five criteria: completeness, accuracy, terminology, accessibility, and safety. Group differences were assessed using the Kruskal–Wallis test, followed by Dunn’s test with Bonferroni correction for multiple comparisons. Results: 61 experienced pulmonologists assessed the survey. Statistical analysis showed that Gemini outperformed the others in response completeness (p < 0.01–0.03), while Claude achieved higher accuracy in information delivery and medical terminology (p = 0.002–0.05). No differences were found for accessibility or safety (all p > 0.05). Conclusions: All three AI platforms provided potentially useful information, though performance varied. Caution is advised when using them as COPD guides for patients and families. While AI has the potential to support global respiratory health education, further research is needed to ensure accuracy and validation.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.047 | 0.121 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".