High-Throughput Phenotyping of Clinical Text Using Large Language Models
This work addresses the need for efficient phenotyping in precision medicine by demonstrating the potential of large language models to automate tasks without requiring manually annotated training data, though it is incremental as it compares existing models on a specific dataset.
This study tackled the problem of automating high-throughput phenotyping of clinical text from the OMIM database by evaluating GPT-4 and GPT-3.5-Turbo, finding that GPT-4 outperformed GPT-3.5-Turbo in identifying, categorizing, and normalizing signs with concordance comparable to manual inter-rater agreement.
High-throughput phenotyping automates the mapping of patient signs to standardized ontology concepts and is essential for precision medicine. This study evaluates the automation of phenotyping of clinical summaries from the Online Mendelian Inheritance in Man (OMIM) database using large language models. Due to their rich phenotype data, these summaries can be surrogates for physician notes. We conduct a performance comparison of GPT-4 and GPT-3.5-Turbo. Our results indicate that GPT-4 surpasses GPT-3.5-Turbo in identifying, categorizing, and normalizing signs, achieving concordance with manual annotators comparable to inter-rater agreement. Despite some limitations in sign normalization, the extensive pre-training of GPT-4 results in high performance and generalizability across several phenotyping tasks while obviating the need for manually annotated training data. Large language models are expected to be the dominant method for automating high-throughput phenotyping of clinical text.