Neurosymbolic framework builds planning models from clinical narratives

Researchers have developed NSPIN, a novel neurosymbolic framework designed to construct planning domain models from unstructured clinical narratives. This approach leverages large language models (LLMs) to extract and structure event sequences from raw text, subsequently inducing a PPDDL model. The framework refines preconditions with LLM-proposed revisions, validated empirically. Evaluations on a dataset of 2,660 laparoscopic appendectomy notes demonstrated that NSPIN generates models capable of generalizing to unseen notes and aligning with surgical practice. AI

IMPACT This research could improve decision support systems in complex medical procedures by enabling better workflow formalization from clinical text.

RANK_REASON The cluster contains a research paper detailing a new methodology and framework. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Laparoscopic appendectomy
• large-language models
• NSPIN
• PPDDL

• paper
• model release

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