Anatomical Entity Recognition with a Hierarchical Framework Augmented by External Resources

Yan Xu, Hua Ji, Zhaoheng Ni, Qinlang Chen, Yubo Fan, Sophia Ananiadou, Eric Chang, Jun’ichi TsujiiPLoS 2014 · DOI

Introduction

In clinical Natural Language Processing (NLP), identifying anatomical locations is a fundamental task for extracting patient context and understanding medical narratives. However, clinical records are notoriously complex. They do not always refer to anatomy directly (e.g., "lung"); instead, they often use implicit references through diseases ("pneumonia"), clinical tests ("ECG"), or treatments ("appendectomy").

Existing Named Entity Recognition (NER) tools typically excel at identifying explicit mentions but struggle with these implicit references. Implicit entities are difficult to capture because they belong to diverse semantic classes and appear in varied linguistic contexts. To bridge this gap, this paper proposes a hierarchical framework that leverages external medical knowledge to "reason" about the anatomical foundations of clinical concepts.

Methodology: The Hierarchical Framework

The core of the proposed system is a hierarchical framework consisting of three distinct layers of NERs, each implemented using Conditional Random Fields (CRF). This structure allows the system to process information in stages, moving from broad medical concepts to specific anatomical links.

  1. Concept Recognition Layer: This initial layer identifies broad medical concepts, specifically Diseases, Clinical Tests, and Clinical Treatments. These serve as the candidates for implicit anatomical references.
  2. Explicit Recognition Layer: A dedicated NER focuses on identifying direct anatomical mentions, such as "liver," "artery," or "femur."
  3. Implicit Recognition Layer: This final layer determines whether the concepts identified in the first layer function as implicit anatomical references in their specific context.
Overview of the hierarchical framework and feature builder architecture.

The Feature Builder and External Knowledge

The "secret sauce" of this approach lies in the Feature Builder, which augments standard NLP features (like POS tagging and prefixes) with rich external data:

  • Ontological Features: The researchers compiled a massive anatomical dictionary by integrating four major resources: UMLS, MeSH, RadLex, and BodyPart3D.
  • World Knowledge Features: To handle the semantic leap from a disease to an organ, the system queries Wikipedia and WordNet. For instance, if a Wikipedia entry for "Hypertension" mentions "arteries" in its introductory text, the system generates a feature that links the two, providing the model with "common sense" medical knowledge.
  • Coreference Chains: Clinical notes are often filled with abbreviations. The system uses coreference data to link local shorthand (e.g., "cp") to its full form ("chest pain") before processing, ensuring the NER has the most complete information possible.

Experimental Results

The framework was evaluated using 300 discharge summaries from the i2b2 challenge dataset, re-annotated by clinical experts to include 16,690 explicit and 5,564 implicit anatomical tokens.

The results demonstrated the effectiveness of the hierarchical approach:

  • Explicit NER: Achieved an F1 score of 0.8137 (0.8509 Precision / 0.7796 Recall).
  • Implicit NER: Achieved an F1 score of 0.7690 (0.8695 Precision / 0.6893 Recall).
  • Overall Impact: The integration of the hierarchical framework and external knowledge resources resulted in a 5.08% increment in F1 score over a baseline CRF model using only standard linguistic features.

Discussion and Insights

A key insight from the study is the utility of Wikipedia as a bridge. Because a comprehensive, manually curated database of "implicit anatomy" does not exist, using Wikipedia definitions allows the system to discover these links dynamically. Furthermore, the researchers found that the hierarchical structure is essential; feeding the output of the explicit recognizer into the implicit recognizer (the "Hierarchical Feature") helped the model disambiguate complex cases where a term might be either a disease or a body part.

However, limitations remain. The current system primarily handles "one-step" inferences (e.g., pneumonia $\rightarrow$ lung). It struggles with multi-step links, such as connecting Diabetes Mellitus (DM) to the pancreas via insulin. Additionally, non-standard clinical shorthand (e.g., "cabgx4") and linguistic ambiguities (e.g., "back" as an adverb vs. an anatomical location) continue to pose challenges.

Conclusion

By combining multi-layered NERs with external ontological and world knowledge, this research provides a robust framework for capturing the full spectrum of anatomical references in clinical text. Future work will focus on integrating more structured knowledge bases like Freebase and improving automated coreference resolution to enhance the system's performance in real-world, un-annotated clinical environments.

Summary updated

Abstract

References to anatomical entities in medical records consist not only of explicit references to anatomical locations, but also other diverse types of expressions, such as specific diseases, clinical tests, clinical treatments, which constitute implicit references to anatomical entities. In order to identify these implicit anatomical entities, we propose a hierarchical framework, in which two layers of named entity recognizers (NERs) work in a cooperative manner. Each of the NERs is implemented using the Conditional Random Fields (CRF) model, which use a range of external resources to generate features. We constructed a dictionary of anatomical entity expressions by exploiting four existing resources, i.e., UMLS, MeSH, RadLex and BodyPart3D, and supplemented information from two external knowledge bases, i.e., Wikipedia and WordNet, to improve inference of anatomical entities from implicit expressions. Experiments conducted on 300 discharge summaries showed a micro-averaged performance of 0.8509 Precision, 0.7796 Recall and 0.8137 F1 for explicit anatomical entity recognition, and 0.8695 Precision, 0.6893 Recall and 0.7690 F1 for implicit anatomical entity recognition. The use of the hierarchical framework, which combines the recognition of named entities of various types (diseases, clinical tests, treatments) with information embedded in external knowledge bases, resulted in a 5.08% increment in F1. The resources constructed for this research will be made publicly available.
BibTeX
@inproceedings{xu2014anatomical,
  author = {Yan Xu and Hua Ji and Zhaoheng Ni and Qinlang Chen and Yubo Fan and Sophia Ananiadou and Eric Chang and Jun’ichi Tsujii},
  title = {{Anatomical Entity Recognition with a Hierarchical Framework Augmented by External Resources}},
  booktitle = {PLoS},
  year = {2014},
  doi = {10.1371/journal.pone.0108396},
}
Figure