Use as Directed? A Comparison of Software Tools Intended to Check Rigor and Transparency of Published Work

The causes of the reproducibility crisis include lack of standardization and transparency in scientific reporting. Checklists such as ARRIVE and CONSORT seek to improve transparency, but they are not always followed by authors and peer review often fails to identify missing items. To address these issues, there are several automated tools that have been designed to check different rigor criteria. We have conducted a broad comparison of 11 automated tools across 9 different rigor criteria from the ScreenIT group. We found some criteria, including detecting open data, where the combination of tools showed a clear winner, a tool which performed much better than other tools. In other cases, including detection of inclusion and exclusion criteria, the combination of tools exceeded the performance of any one tool. We also identified key areas where tool developers should focus their effort to make their tool maximally useful. We conclude with a set of insights and recommendations for stakeholders in the development of rigor and transparency detection tools. The code and data for the study is available at https://github.com/PeterEckmann1/tool-comparison.

Exploring the use of a Large Language Model for data extraction in systematic reviews: a rapid feasibility study

This paper describes a rapid feasibility study of using GPT-4, a large language model (LLM), to (semi)automate data extraction in systematic reviews. Despite the recent surge of interest in LLMs there is still a lack of understanding of how to design LLM-based automation tools and how to robustly evaluate their performance. During the 2023 Evidence Synthesis Hackathon we conducted two feasibility studies. Firstly, to automatically extract study characteristics from human clinical, animal, and social science domain studies. We used two studies from each category for prompt-development; and ten for evaluation. Secondly, we used the LLM to predict Participants, Interventions, Controls and Outcomes (PICOs) labelled within 100 abstracts in the EBM-NLP dataset. Overall, results indicated an accuracy of around 80%, with some variability between domains (82% for human clinical, 80% for animal, and 72% for studies of human social sciences). Causal inference methods and study design were the data extraction items with the most errors. In the PICO study, participants and intervention/control showed high accuracy (>80%), outcomes were more challenging. Evaluation was done manually; scoring methods such as BLEU and ROUGE showed limited value. We observed variability in the LLMs predictions and changes in response quality. This paper presents a template for future evaluations of LLMs in the context of data extraction for systematic review automation. Our results show that there might be value in using LLMs, for example as second or third reviewers. However, caution is advised when integrating models such as GPT-4 into tools. Further research on stability and reliability in practical settings is warranted for each type of data that is processed by the LLM.