KG-RAG for Rare Disease Diagnosis
What it is
A Retrieval Augmented Generation (RAG) framework that utilizes the PrimeKG database to improve LLM accuracy in identifying rare diseases. It supports two modes: generating disease symptom descriptions and generating differential diagnoses from lists of symptoms.
The problem it solves
LLM hallucinations and lack of specialized medical knowledge when diagnosing rare diseases.
What you could use it for
- Generating descriptions of symptoms for specific rare diseases.
- Generating differential diagnoses based on a list of patient symptoms.
- Reducing LLM hallucinations in medical contexts by grounding responses in a knowledge graph.
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.