Zero-shot Medical Entity Retrieval without Annotation: Learning From Rich Knowledge Graph Semantics
This addresses the challenge of generalizing medical entity retrieval to unseen sub-specialties, which is crucial during public health crises, though it is incremental as it builds on existing knowledge graph methods.
The paper tackled the problem of zero-shot medical entity retrieval by leveraging knowledge graph semantics without human annotation, achieving 7% to 30% higher recall across major medical ontologies compared to benchmarks like BM25 and Clinical BERT.
Medical entity retrieval is an integral component for understanding and communicating information across various health systems. Current approaches tend to work well on specific medical domains but generalize poorly to unseen sub-specialties. This is of increasing concern under a public health crisis as new medical conditions and drug treatments come to light frequently. Zero-shot retrieval is challenging due to the high degree of ambiguity and variability in medical corpora, making it difficult to build an accurate similarity measure between mentions and concepts. Medical knowledge graphs (KG), however, contain rich semantics including large numbers of synonyms as well as its curated graphical structures. To take advantage of this valuable information, we propose a suite of learning tasks designed for training efficient zero-shot entity retrieval models. Without requiring any human annotation, our knowledge graph enriched architecture significantly outperforms common zero-shot benchmarks including BM25 and Clinical BERT with 7% to 30% higher recall across multiple major medical ontologies, such as UMLS, SNOMED, and ICD-10.