LLM-driven framework advances causal discovery for adverse pregnancy outcomes

Researchers have developed a novel neurosymbolic framework to improve causal discovery for adverse pregnancy outcomes (APOs) like preterm birth and gestational diabetes. This method combines the broad knowledge of large language models (LLMs) with empirical data scoring to generate and refine causal hypotheses. The LLM acts as an adaptive proposal distribution, with high-scoring hypotheses guiding subsequent LLM generations. Applied to a clinical dataset, the approach successfully identified expert-validated causal relationships and uncovered new potential risk factors. AI

IMPACT This approach could lead to more accurate identification of risk factors for adverse pregnancy outcomes, enabling targeted interventions.

RANK_REASON The cluster contains an academic paper detailing a new methodology for causal discovery. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• gestational diabetes
• Kavimayil P. Komarasamy
• large language model
• preterm birth

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →