AutoPCR: Automated Phenotype Concept Recognition by Prompting

TL;DR

AutoPCR is a prompt-based method for phenotype concept recognition that generalizes across ontologies and unseen data without requiring ontology-specific training, enhanced by a self-supervised strategy.

Contribution

It introduces AutoPCR, a novel prompt-based approach with self-supervised training, improving generalization and robustness in biomedical phenotype recognition tasks.

Findings

AutoPCR outperforms existing methods on multiple datasets.

It demonstrates strong transferability to new ontologies.

Self-supervised training boosts AutoPCR's performance.

Abstract

Motivation: Phenotype concept recognition (CR) is a fundamental task in biomedical text mining. However, existing methods either require ontology-specific training, making them struggle to generalize across diverse text styles and evolving biomedical terminology, or depend on general-purpose large language models (LLMs) that lack necessary domain knowledge. Results: To address these limitations, we propose AutoPCR, a prompt-based phenotype CR method designed to automatically generalize to new ontologies and unseen data without ontology-specific training. To further boost performance, we also introduce an optional self-supervised training strategy. Experiments show that AutoPCR achieves the best average and most robust performance across datasets. Further ablation and transfer studies demonstrate its inductive capability and generalizability to new ontologies. Availability and Implementation: Our code is available at https://github.com/yctao7/AutoPCR. Contact: drjieliu@umich.edu