Enhancing Phenotype Recognition in Clinical Notes Using Large Language Models: PhenoBCBERT and PhenoGPT

TL;DR

This paper introduces two transformer-based models, PhenoBCBERT and PhenoGPT, that improve automated detection of clinical phenotype terms in notes and literature, including novel terms beyond HPO, aiding disease research.

Contribution

The study develops and compares BERT-based and GPT-based models for phenotype recognition, incorporating negation and normalization layers for enhanced accuracy and discovery of new phenotype concepts.

Findings

Models extract more phenotype concepts than existing tools.

GPT-based models offer advantages in speed and privacy.

Case studies demonstrate discovery of novel phenotype information.

Abstract

We hypothesize that large language models (LLMs) based on the transformer architecture can enable automated detection of clinical phenotype terms, including terms not documented in the HPO. In this study, we developed two types of models: PhenoBCBERT, a BERT-based model, utilizing Bio+Clinical BERT as its pre-trained model, and PhenoGPT, a GPT-based model that can be initialized from diverse GPT models, including open-source versions such as GPT-J, Falcon, and LLaMA, as well as closed-source versions such as GPT-3 and GPT-3.5. We compared our methods with PhenoTagger, a recently developed HPO recognition tool that combines rule-based and deep learning methods. We found that our methods can extract more phenotype concepts, including novel ones not characterized by HPO. We also performed case studies on biomedical literature to illustrate how new phenotype information can be recognized and extracted. We compared current BERT-based versus GPT-based models for phenotype tagging, in multiple aspects including model architecture, memory usage, speed, accuracy, and privacy protection. We also discussed the addition of a negation step and an HPO normalization layer to the transformer models for improved HPO term tagging. In conclusion, PhenoBCBERT and PhenoGPT enable the automated discovery of phenotype terms from clinical notes and biomedical literature, facilitating automated downstream tasks to derive new biological insights on human diseases.