Article

PhenoAgent: agentic LLM framework for phenotyping electronic health records via structured query decomposition and self-correction

2026-06-28

Abstract excerpt

<title>Abstract</title> <p>Most clinical phenotype information is embedded in free-text electronic health records, limiting structured queries for cohort selection and trial recruitment. Here we introduce PhenoAgent, a three-stage agentic large language model (LLM) framework for phenotype retrieval from free text. PhenoAgent decomposes clinical queries into a structured JSON schema, evaluates each record with a s...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 332930f4-6127-52a0-924a-c69ac470e4b0
DOI: 10.21203/rs.3.rs-10026525/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

PhenoAgent: agentic LLM framework for phenotyping electronic health records via structured query decomposition and self-correctionDOI 10.21203/rs.3.rs-10026525/v1Read

Addressing challenges in agentic retrieval of structured data from biomedical databasesSemantic proximity Read

Agentic Authoring of OMOP Concept Sets from Natural LanguageSemantic proximity Read

Systematic benchmarking demonstrates large language models have not reached the diagnostic accuracy of traditional rare-disease decision support toolsSemantic proximity Read

RESCUE: An end-to-end multi-agent LLM system for proactive rare-disease patient screening in the EHRSemantic proximity Read

Large Language Models Facilitate the Generation of Electronic Health Record Phenotyping AlgorithmsSemantic proximity Read

PHO-Agents: A Large Language Model–Powered Multi-Agent System for Predicting Health OutcomesSemantic proximity Read

MRQC-LLM: A Novel Large Language Model Framework for Enhancing Medical Record Quality ControlSemantic proximity Read

Extraction of Human Phenotype Ontology (HPO) Concepts from Clinical Notes Utilizing Large Language Models (LLM) with Model Context Protocol (MCP)Semantic proximity Read

A Systematic Exploration of LLM Behavior for EHR PhenotypingSemantic proximity Read

Large language models facilitate the generation of electronic health record phenotyping algorithms.Semantic proximity Read

HEAL-KGGen: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Genetic Biomarker-Based Medical DiagnosisSemantic proximity Read

The Transformative Potential of Large Language Models in Mining Electronic Health Records DataSemantic proximity Read