KU AIGEN ICL EDI@BC8 Track 3: Advancing Phenotype Named Entity Recognition and Normalization for Dysmorphology Physical Examination Reports

2025-01-16

AI Summary

This study addresses the challenge of high phenotypic description heterogeneity and poor standardizability in clinical examination reports for developmental disorders. To tackle this, we propose a joint modeling framework integrating named entity recognition (NER) and normalization. Our approach innovatively introduces synonym marginalization for data augmentation, coupled with a pre-trained language model–based NER module, an HPO term alignment mechanism, and rule-guided post-processing—enabling precise phenotypic entity recognition and robust mapping to the Human Phenotype Ontology (HPO). Evaluated on BioCreative8 Track 3, our end-to-end system achieves a state-of-the-art F1 score, outperforming the competition average by 2.6%; its normalization-only F1 improves by 1.9%, significantly mitigating semantic normalization difficulties arising from lexical variability in clinical text.

Technology Category

• Natural Language Processing: Information Extraction
• Knowledge Representation and Reasoning: Description Logics
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

The objective of BioCreative8 Track 3 is to extract phenotypic key medical findings embedded within EHR texts and subsequently normalize these findings to their Human Phenotype Ontology (HPO) terms. However, the presence of diverse surface forms in phenotypic findings makes it challenging to accurately normalize them to the correct HPO terms. To address this challenge, we explored various models for named entity recognition and implemented data augmentation techniques such as synonym marginalization to enhance the normalization step. Our pipeline resulted in an exact extraction and normalization F1 score 2.6% higher than the mean score of all submissions received in response to the challenge. Furthermore, in terms of the normalization F1 score, our approach surpassed the average performance by 1.9%. These findings contribute to the advancement of automated medical data extraction and normalization techniques, showcasing potential pathways for future research and application in the biomedical domain.

Problem

• Electronic Medical Records
• Phenotype Ontology
• Standardization of Medical Information

Innovation

• Phenotype Naming Normalization
• Electronic Patient-Doctor Communication Records
• Synonym Replacement Enhancement