Enhancing search strategies for systematic reviews on drug Harms: An evaluation of the utility of ChatGPT in error detection and keyword generation
Bibliographic record
Abstract
Developing search strategies for synthesizing evidence on drug harms requires specialized expertise and knowledge. The aim of this study was to evaluate ChatGPT's ability to enhance search strategies for systematic reviews of drug harms by identifying missing and generating omitted keywords. A literature search in PubMed identified systematic reviews of drug harms from 10 high-impact journals between 1-Nov-2013 to 27-Nov-2023. Sixteen search strategies used in these reviews were selected each with a single error of omission introduced. ChatGPT's (GPT-4) performance was evaluated based on error detection, similarity between the extracted and generated search strategies via strict and semantic keyword matching, and proportion of omitted keywords generated. ChatGPT identified the introduced errors in all search strategies. Under strict matching, the mean Jaccard's similarity measure was 0.17 (range: 0.00–0.52) and with semantic matching this increased to 0.23 (range: 0.00–0.53). Similarly, the mean proportion of keywords recreated by ChatGPT was 49 % using strict matching increasing to 71 % with semantic matching. ChatGPT effectively detected errors and generated relevant keywords, showing potential as a tool for evidence retrieval on drug harms. • ChatGPT was tested on its ability to enhance search strategies for systematic reviews of drug harms. • ChatGPT was able to identify intentional errors introduced into search strategies with high sensitivity. • ChatGPT generated relevant keywords, showing potential to enhance the efficiency and quality of systematic reviews on drug harms.
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 | 0.230 | 0.588 |
| Meta-epidemiology (narrow) | 0.004 | 0.002 |
| Meta-epidemiology (broad) | 0.006 | 0.007 |
| Bibliometrics | 0.023 | 0.016 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.008 |
| Open science | 0.003 | 0.010 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 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; 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".