Systematic Review with LLMs

This study investigates the feasibility of using Large Language Models (LLMs) to automate systematic reviews. Based on a published systematic review on COVID-19 prognostic scores, it pursues two main objectives: first, to compare the results of an LLM-based replication, including inclusion decision and data extraction, with human reference data. Second, an LLM-based framework will be developed in accordance with established guidelines to facilitate access and use of LLMs for researchers. The study aims to demonstrate  that LLMs obtain the potential of to reduce manual effort and improve the efficiency of systematic reviews.