Evaluating ChatGPT’s ability to simplify scientific abstracts for clinicians and the public
Bibliographic record
Abstract
This study evaluated ChatGPT's ability to simplify scientific abstracts for both public and clinician use. Ten questions were developed to assess ChatGPT's ability to simplify scientific abstracts and improve their readability for both the public and clinicians. These questions were applied to 43 abstracts. The abstracts were selected through a convenience sample from Google Scholar by four interdisciplinary reviewers from physiotherapy, occupational therapy, and nursing backgrounds. Each abstract was summarized by ChatGPT on two separate occasions. These summaries were then reviewed independently by two different reviewers. Flesch Reading Ease scores were calculated for each summary and original abstract. A subgroup analysis explored differences in accuracy, clarity, and consistency across various study designs. ChatGPT's summaries scored higher on the Flesch Reading Ease test than the original abstracts in 31 out of 43 papers, showing a significant improvement in readability (p = 0.005). Systematic reviews and meta-analyses consistently received higher scores for accuracy, clarity, and consistency, while clinical trials scored lower across these parameters. Despite its strengths, ChatGPT showed limitations in "Hallucination presence" and "Technical terms usage," scoring below 7 out of 10. Hallucination rates varied by study type, with case reports having the lowest scores. Reviewer agreement across parameters demonstrated consistency in evaluations. ChatGPT shows promise for translating knowledge in clinical settings, helping to make scientific research more accessible to non-experts. However, its tendency toward hallucinations and technical jargon requires careful review by clinicians, patients, and caregivers. Further research is needed to assess its reliability and safety for broader use in healthcare communication.
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 | 0.218 | 0.656 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.006 |
| Bibliometrics | 0.017 | 0.008 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.007 | 0.008 |
| Open science | 0.003 | 0.010 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.007 | 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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.
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".