PulseAugur
EN
LIVE 08:34:29

LLM framework automates scientific cohort discovery from literature

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a novel framework that leverages large language models (LLMs) to automate the discovery of scientific cohorts from literature. This system generates PubMed queries based on research questions, screens retrieved titles and abstracts using an LLM, and extracts explicit cohort names. In a use case involving youth aggression genetics, the framework identified 44 eligible cohorts, with 17 not found in established cohort catalogues, demonstrating its potential to complement existing discovery methods. AI

IMPACT Automates and enhances the discovery of scientific cohorts, potentially accelerating multi-study analyses and research.

RANK_REASON The item is an academic paper detailing a new methodology for scientific literature analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.IR (Information Retrieval) →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

LLM framework automates scientific cohort discovery from literature

COVERAGE [2]

  1. arXiv cs.CL TIER_1 English(EN) · Moritz Sturm, Lisa M. Berg, Inken Berg, Harishny Sarma, Jasmin Hartmann, Denissa Girschik, Gemma Roig, Christine M. Freitag, Andreas G. Chiocchetti ·

    Large language model-assisted discovery of cohorts from scientific literature

    arXiv:2608.15909v1 Announce Type: cross Abstract: Background: Planning multi-study analyses requires identifying cohorts with the relevant participants, phenotypes, and data modalities. This process commonly relies on prior knowledge, cohort catalogues, and manual literature sear…

  2. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Andreas G. Chiocchetti ·

    Large language model-assisted discovery of cohorts from scientific literature

    Background: Planning multi-study analyses requires identifying cohorts with the relevant participants, phenotypes, and data modalities. This process commonly relies on prior knowledge, cohort catalogues, and manual literature searches. We developed a complementary question-driven…

RELATED ENTITIES

RELATED TOPICS