MetaSyn benchmark shows LLM pipelines recover at most 52.7% of ground-truth included studies due to screening failures on PI/ECO eligibility, despite 90.9% retrieval recall at K=200.
Using text mining for study identification in systematic reviews: a systematic review of current approaches
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Registry analysis shows marked growth in AI-related clinical trials led by China and the US, with moderate human-AI agreement on interaction classification in a 100-record sample.
citing papers explorer
-
Benchmarking LLM Agents on Meta-Analysis Articles from Nature Portfolio
MetaSyn benchmark shows LLM pipelines recover at most 52.7% of ground-truth included studies due to screening failures on PI/ECO eligibility, despite 90.9% retrieval recall at K=200.
-
Trends in AI and Human-AI Interaction in Clinical Trials -- A Hybrid Human-AI Exploration
Registry analysis shows marked growth in AI-related clinical trials led by China and the US, with moderate human-AI agreement on interaction classification in a 100-record sample.