Will ChatGPT-4 improve the quality of medical abstracts?
Bibliographic record
Abstract
Background: ChatGPT received attention for medical writing. Our objective was to evaluate whether ChatGPT 4.0 could improve the quality of abstracts submitted to a medical conference by clinical researchers. Methods: This was an experimental study involving 24 international researchers (the participants) who provided one original abstract intended for submission at the 2024 Pediatric Academic Society (PAS) conference. We asked ChatGPT-4 to improve the quality of the abstract while adhering to PAS submission guidelines. Participants received the revised version and were tasked with creating a final abstract. The quality of each version (original, ChatGPT and final) was evaluated by the participants themselves using a numeric scale (0-100). Additionally, three co-investigators assessed abstracts blinded to the version. The primary analysis focused on the mean difference in scores between the final and original abstracts. Results: Abstract quality varied between the three versions with mean scores of 82, 65 and 90 for the original, ChatGPT and final versions, respectively. Overall, the final version displayed significantly improved quality compared to the original (mean difference 8.0 points; 95% CI: 5.6-10.3). Independent ratings by the co-investigators confirmed statistically significant improvements (mean difference 1.10 points; 95% CI: 0.54-1.66). Participants identified minor (n = 10) and major (n = 3) factual errors in ChatGPT's abstracts. Conclusion: ChatGPT 4.0 does not produce abstracts of better quality than the one crafted by researchers but it offers suggestions to help them improve their abstracts. It may be more useful for researchers encountering challenges in abstract generation due to limited experience or language barriers.
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 | 0.170 | 0.475 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.004 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.005 | 0.004 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.015 | 0.003 |
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".