![[2602.20324] An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.20324] An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models
Summary
This article presents RARE-PHENIX, an AI framework designed for end-to-end phenotyping of rare diseases from clinical notes, utilizing large language models for improved accuracy and efficiency.
Why It Matters
The manual curation of phenotypes from clinical notes is labor-intensive, making it difficult to scale. RARE-PHENIX addresses this challenge by automating the extraction and standardization of phenotypes, potentially enhancing diagnostic processes for rare diseases and improving patient outcomes.
Key Takeaways
- RARE-PHENIX integrates phenotype extraction, standardization, and ranking into a single workflow.
- The framework outperformed existing models like PhenoBERT in precision and recall metrics.
- Ablation studies indicate that each module in RARE-PHENIX contributes to its overall performance.
- The approach aligns phenotyping with clinical workflows, enhancing its applicability in real-world settings.
- RARE-PHENIX has the potential to support human-in-the-loop diagnosis for rare diseases.
Computer Science > Artificial Intelligence arXiv:2602.20324 (cs) [Submitted on 23 Feb 2026] Title:An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models Authors:Cathy Shyr, Yan Hu, Rory J. Tinker, Thomas A. Cassini, Kevin W. Byram, Rizwan Hamid, Daniel V. Fabbri, Adam Wright, Josh F. Peterson, Lisa Bastarache, Hua Xu View a PDF of the paper titled An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models, by Cathy Shyr and 10 other authors View PDF HTML (experimental) Abstract:Phenotyping is fundamental to rare disease diagnosis, but manual curation of structured phenotypes from clinical notes is labor-intensive and difficult to scale. Existing artificial intelligence approaches typically optimize individual components of phenotyping but do not operationalize the full clinical workflow of extracting features from clinical text, standardizing them to Human Phenotype Ontology (HPO) terms, and prioritizing diagnostically informative HPO terms. We developed RARE-PHENIX, an end-to-end AI framework for rare disease phenotyping that integrates large language model-based phenotype extraction, ontology-grounded standardization to HPO terms, and supervised ranking of diagnostically informative phenotypes. We trained RARE-PHENIX using data from 2,671 patients across 11 Undiagnosed Diseases Network clinical sites, and externally validated it on 16,35...
