ArticleProceedings of the National Academy of Sciences of the United States of America2025
Transforming literature screening: The emerging role of large language models in systematic reviews.
Article in Proceedings of the National Academy of Sciences of the United States of America, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 23 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
23 citing papers in PubMed.
- AI-assisted scoping review of code sharing in clinical prediction model research.Nature medicine · 2026Article
- Reproducible study identification and selection in systematic reviews: barriers and paths forward.BMJ open · 2026Article
- High-Recall Biomedical Language Models for Radiation Oncology Evidence Synthesis: An Integrated Systematic Review of Prediction Models for Radiotherapy-Induced Complications in Nasopharyngeal Carcinoma.Life (Basel, Switzerland) · 2026Review
- Performance of Two AI Approaches in ASReview Compared With Manual Screening for Dementia Care Literature Screening: Comparative Analysis.JMIR formative research · 2026Article
- MacAma: Multi-AI Agent as a Co-Scientist for Automated Meta-Analysis.Smart medicine · 2026Article
- Leveraging generative artificial intelligence for the development of non-interventional research study protocols: a proof-of-concept feasibility study.BMC medical research methodology · 2026Article
- Automated full-text screening and accelerated reviews using large language models with context-aware agents: an exploratory analysis in biomarker research.European heart journal. Digital health · 2026Article
- From reviews to real-time: dynamic evidence in dentistry.Evidence-based dentistry · 2026Article
- Automating data extraction in meta-research: A multi-model benchmark in network psychometrics papers.Behavior research methods · 2026Article
- Artificial Intelligence Tools for Automating Evidence Synthesis: Scoping Review.Journal of medical Internet research · 2026Article
- Cybersecurity in Radio Frequency Technologies: A Scientometric and Systematic Review with Implications for IoT and Wireless Applications.Sensors (Basel, Switzerland) · 2026Review
- An auditable pipeline for fuzzy full-text screening in systematic reviews: integrating contrastive semantic highlighting and LLM judgment.Artificial intelligence review · 2026Article
- Transparent Reporting of AI in Systematic Literature Reviews: Development of the PRISMA-trAIce Checklist.JMIR AI · 2025Article
- From Research to Practice in Days, not Decades: Why Leaders Must Act now.Journal of medical systems · 2025Article
- WHO global research priorities for traditional, complementary, and integrative (TCI) medicine: an international consensus and comparisons with LLMs.Journal of global health · 2025Article
- Enhancing Evidence Synthesis Efficiency: Leveraging Large Language Models and Agentic Workflows for Optimized Literature Screening.Cochrane evidence synthesis and methods · 2025Article
- A large language model-based tool for identifying relationships to industry in research on the carcinogenicity of benzene, cobalt, and aspartame.Environmental health : a global access science source · 2025Article
- The current landscape and emerging challenges of benchmarking single-cell methods.Briefings in bioinformatics · 2025Review
- Artificial intelligence for the science of evidence synthesis: how good are AI-powered tools for automatic literature screening?BMC medical research methodology · 2025Article
- Testing the utility of GPT for title and abstract screening in environmental systematic evidence synthesis.Environmental evidence · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
8 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Systematic reviews (SR) synthesize evidence-based medical literature, but they involve labor-intensive manual article screening. Large language models (LLMs) can select relevant literature, but their quality and efficacy are still being determined compared to humans. We evaluated the overlap between title- and abstract-based selected articles of 18 different LLMs and human-selected articles for three SR. In the three SRs, 185/4,662, 122/1,741, and 45/66 articles have been selected and considered for full-text screening by two independent reviewers. Due to technical variations and the inability of the LLMs to classify all records, the LLM's considered sample sizes were smaller. However, on average, the 18 LLMs classified 4,294 (min 4,130; max 4,329), 1,539 (min 1,449; max 1,574), and 27 (min 22; max 37) of the titles and abstracts correctly as either included or excluded for the three SRs, respectively. Additional analysis revealed that the definitions of the inclusion criteria and conceptual designs significantly influenced the LLM performances. In conclusion, LLMs can reduce one reviewer´s workload between 33% and 93% during title and abstract screening. However, the exact formulation of the inclusion and exclusion criteria should be refined beforehand for ideal support of the LLMs.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.