Article

Sensitivity, specificity and avoidable workload of using a large language models for title and abstract screening in systematic reviews and meta-analyses

2023-12-17

Abstract excerpt

<h4>Importance</h4> Systematic reviews are time-consuming and are still performed predominately manually by researchers despite the exponential growth of scientific literature. <h4>Objective</h4> To investigate the sensitivity, specificity and estimate the avoidable workload when using an AI-based large language model (LLM) (Generative Pre-trained Transformer [GPT] version 3.5-Turbo from OpenAI) to perform title...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 17a0c915-cf63-5dc3-9229-0ae475eb922f
DOI: 10.1101/2023.12.15.23300018

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Sensitivity, specificity and avoidable workload of using a large language models for title and abstract screening in systematic reviews and meta-analysesDOI 10.1101/2023.12.15.23300018Read

Development of meta-prompts for Large Language Models to screen titles and abstracts for diagnostic test accuracy reviewsSemantic proximity Read

Validation of Generative AI Models to Expedite Title and Abstract Screening in Systematic ReviewsSemantic proximity Read

Will generative AI help solve systematic literature reviews? Evidence from a 2-year research programmeSemantic proximity Read

Automation of Systematic Reviews with Large Language ModelsSemantic proximity Read

Fully Automated Systematic Review Generation via Large Language Models: Quality Assessment and Implications for Scientific PublishingSemantic proximity Read

JARVIS, should this study be selected for full-text screening? Performance of a Joint AI-ReViewer Interactive Screening tool for systematic reviewsSemantic proximity Read

Artificial intelligence resources for the screening of titles and abstracts in systematic reviews: a scoping reviewSemantic proximity Read

Human Researchers are Superior to Large Language Models in Writing a Systematic Review in a Comparative Multitask AssessmentSemantic proximity Read

Assessing the feasibility and acceptability of a bespoke large language model pipeline to extract data from different study designs for public health evidence reviewsSemantic proximity Read

Making Broad Evidence Synthesis Feasible: An LLM Screening Agent for Meta-Analyses Applied To Suicide PreventionSemantic proximity Read

Collaborative Large Language Models for Automated Data Extraction in Living Systematic ReviewsSemantic proximity Read

The use of a large language models to create plain language summaries of evidence reviews in healthcare: a feasibility studySemantic proximity Read