FastHPOCR: pragmatic, fast, and accurate concept recognition using the human phenotype ontology

First steps toward building natural history of diseases computationally: Lessons learned from the Noonan syndrome use case

Rare diseases (RDs) are conditions affecting fewer than 1 in 2,000 people, with over 7,000 identified, primarily genetic in nature, and more than half impacting children. Although each RD affects a small population, collectively, between 3.5% and 5.9% of the global population, or 262.9-446.2 million people, live with an RD. Most RDs lack established treatment protocols, highlighting the need for proper care pathways addressing prognosis, diagnosis, and management. Advances in generative AI and large language models (LLMs) offer new opportunities to document the temporal progression of phenotypic features, addressing gaps in current knowledge bases. This study proposes an LLM-based framework to capture the natural history of diseases, specifically focusing on Noonan syndrome. The framework aims to document phenotypic trajectories, validate against RD knowledge bases, and integrate insights into care coordination using electronic health record (EHR) data from the Undiagnosed Diseases Program Singapore.

A simplified retriever to improve accuracy of phenotype normalizations by large language models

Large language models have shown improved accuracy in phenotype term normalization tasks when augmented with retrievers that suggest candidate normalizations based on term definitions. In this work, we introduce a simplified retriever that enhances large language model accuracy by searching the Human Phenotype Ontology (HPO) for candidate matches using contextual word embeddings from BioBERT without the need for explicit term definitions. Testing this method on terms derived from the clinical synopses of Online Mendelian Inheritance in Man (OMIM®), we demonstrate that the normalization accuracy of GPT-4o increases from a baseline of 62% without augmentation to 85% with retriever augmentation. This approach is potentially generalizable to other biomedical term normalization tasks and offers an efficient alternative to more complex retrieval methods.

Improving Automated Deep Phenotyping Through Large Language Models Using Retrieval Augmented Generation

Background

Diagnosing rare genetic disorders relies on precise phenotypic and genotypic analysis, with the Human Phenotype Ontology (HPO) providing a standardized language for capturing clinical phenotypes. Traditional HPO tools, such as Doc2HPO and ClinPhen, employ concept recognition to automate phenotype extraction but struggle with incomplete phenotype assignment, often requiring intensive manual review. While large language models (LLMs) hold promise for more context-driven phenotype extraction, they are prone to errors and "hallucinations," making them less reliable without further refinement. We present RAG-HPO, a Python-based tool that leverages Retrieval-Augmented Generation (RAG) to elevate LLM accuracy in HPO term assignment, bypassing the limitations of baseline models while avoiding the time and resource intensive process of fine-tuning. RAG-HPO integrates a dynamic vector database, allowing real-time retrieval and contextual matching.

Methods

The high-dimensional vector database utilized by RAG-HPO includes >54,000 phenotypic phrases mapped to HPO IDs, derived from the HPO database and supplemented with additional validated phrases. The RAG-HPO workflow uses an LLM to first extract phenotypic phrases that are then matched via semantic similarity to entries within a vector database before providing best term matches back to the LLM as context for final HPO term assignment. A benchmarking dataset of 120 published case reports with 1,792 manually-assigned HPO terms was developed, and the performance of RAG-HPO measured against existing published tools Doc2HPO, ClinPhen, and FastHPOCR.

Results

In evaluations, RAG-HPO, powered by Llama-3 70B and applied to a set of 120 case reports, achieved a mean precision of 0.84, recall of 0.78, and an F1 score of 0.80-significantly surpassing conventional tools (p<0.00001). False positive HPO term identification occurred for 15.8% (256/1,624) of terms, of which only 2.7% (7/256) represented hallucinations, and 33.6% (86/256) unrelated terms; the remainder of false positives (63.7%, 163/256) were relative terms of the target term.

Conclusions

RAG-HPO is a user-friendly, adaptable tool designed for secure evaluation of clinical text and outperforms standard HPO-matching tools in precision, recall, and F1. Its enhanced precision and recall represent a substantial advancement in phenotypic analysis, accelerating the identification of genetic mechanisms underlying rare diseases and driving progress in genetic research and clinical genomics.