ChatGPT for Systematic and Scoping Reviews in Public Health Research: An Applicable Approach
Bibliographic record
Abstract
Abstract Background The Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) is a well-defined framework that guides researchers in compiling knowledge from a domain and presenting it with clarity, objectivity, and relevant information to their peers. PRISMA has been widely used in public health research to conduct systematic and scoping reviews and contribute to the body of knowledge. However, with the ever-increasing production of new studies, a valid sample of the number of papers available may not be represented by any systematic review in the future. Methods In this work, we propose the utilization of technologies such as chat-GPT as a tool to automate parts of the PRISMA process and increase the proportional representation that one systematic review can provide. We present an unguided exploratory experiment with chat-GPT that retro-fed information about PRISMA until chat-GPT created a data structure suitable to be used by crawlers to conduct PRISMA data collection. We also used the created data structure as input to chat-GPT in an attempt to summarize the information contained in the document in the format of a systematic review. Results The created data structure was also used to help do a systematic review summary using chat-GPT.Also, results indicate that this approach has the potential to increase the efficiency and scalability of systematic reviews. Conclusions The proposed approach has the potential to enhance the effectiveness of systematic and scoping reviews and increase the proportional representation of the number of papers available. While further research is necessary to assess the feasibility and scalability of using chat-GPT in this context, this study highlights the promise of leveraging new technologies to improve the quality and efficiency of systematic reviews in public health research. Key messages • PRISMA is a systematic review framework that is both effective and intricate, requiring significant time and effort to execute. • The utilization of chat-GPT can automate parts of the PRISMA process and increase proportional representation in systematic reviews.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.583 | 0.021 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.005 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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; both teacher heads 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".