AI Insight
Researchers have developed PatientPheX, a specialized corpus of 200 full-text biomedical articles annotated to extract patient-specific phenotype information for rare disease research. The corpus includes detailed annotations for seven entity types, patient-entity associations across document sections, and negated findings, achieving 86.95% overall entity recognition accuracy and 79.33% for phenotypes specifically. When combining entity extraction with patient attribution, performance decreased significantly from 84.14% to 54.98%, demonstrating the complexity of linking phenotypes to individual patients in clinical literature.
Why it matters
This resource addresses a critical gap in biomedical text mining by enabling better extraction of patient-level phenotype data from case reports, which is essential for rare disease diagnosis, genotype-phenotype studies, and precision medicine applications. The corpus provides benchmarks for developing automated systems that can process clinical literature to build structured knowledge bases linking patients with their specific clinical characteristics.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Patient-specific phenotype information extraction identifiers and normalizes phenotype entities and links them with individual patients, supporting rare disease research and genotype-phenotype analysis. However, existing datasets rarely combine full-text biomedical content with detailed annotations of patients, phenotypes, related entities, and their associations. In this work, we present PatientPheX, a corpus for patient-specific phenotype information extraction comprising 200 full-text articles, primarily case reports and case series. The corpus provides mention annotations and normalization for seven biomedical entity types, together with explicit associations between patients and entities across sentences, paragraphs, and sections. Negated findings and composite phenotype mentions are also annotated. Corpus construction combines automated pre-annotation, large language model (LLM)-assisted verification, and manual review and adjudication. Benchmarks cover entity recognition and normalization and patient-phenotype association extraction using gold-standard and predicted entities. The overall document-level entity F1 was 86.95%, while phenotype F1 was 79.33%. The best relation extraction macro-F1 decreased from 84.14% with gold-standard entities to 54.98% with predicted entities, highlighting the combined challenges of phenotype extraction and patient attribution. PatientPheX provides a resource for developing and evaluating patient-centered information extraction methods and supports the construction of structured patient-level knowledge resources for phenotype-driven biomedical research.
Source: PatientPheX: A Full-Text Biomedical Corpus for Patient-Specific Phenotype Information Extraction