An Automatic and End-to-End System for Rare Disease Knowledge Graph Construction Based on Ontology-Enhanced Large Language Models: Development Study
Lang Cao, Jimeng Sun, Adam Cross, Alexandre Castonguay · 2024
Read An Automatic and End-to-End System for Rare Disease Knowledge Graph Construction Based on Ontology-Enhanced Large Language Models: Development Study by Lang Cao, Jimeng Sun, Adam Cross, Alexandre Castonguay (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11683654.txt.
Description
Lang Cao and co-authors build AutoRD in this 2024 study, a system that mines rare disease facts from medical text and assembles them into a knowledge graph. Rare diseases affect millions in total, yet each one draws little research. Many lack standard diagnosis codes, so patients are hard to find in records. Language models can extract facts, but they lack deep rare-disease knowledge.
AutoRD pairs a large language model with two medical ontologies covering traits and rare diseases. Its pipeline cleans text, pulls out entities and their links, checks them, and builds the graph. On a curated test set, it beat the plain model by a wide margin on entity extraction. Rare disease mentions were caught with high precision and recall. The authors offer the system for trial recruitment and research support.
Catalog record
| CREATOR | Lang Cao, Jimeng Sun, Adam Cross, Alexandre Castonguay |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |