SciBite Elsevier curation jamboree for World Psoriasis Day

2025-10-28 · Source: SciBite · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, AI in Life Sciences · Depth: Intermediate, quick

Summary

SciBite Elsevier expanded its psoriasis-related concept coverage on October 29th for World Psoriasis Day. The initiative aimed to identify and integrate missing psoriasis-related terms into SciBite's VOCabs, which are specialized vocabularies for named entity recognition (NER) in healthcare and pharmaceuticals. Using their TERMite NER engine, SciBite scanned documents and articles to find approximately 100 new concepts, synonyms, and context-appropriate curations, such as "chronic plaque-type psoriasis" and "flaky patches of skin." This enrichment enhances information recall for customers in drug discovery and manufacturing. Additionally, SciBite curator Paola contributed to the bio-ontology community by reviewing and suggesting improvements to the representation of psoriasis within the Mondo Disease Ontology.

Key takeaway

For NLP Engineers developing healthcare search solutions, regularly curating and expanding specialized vocabularies is crucial. Your systems will achieve higher recall and precision by integrating specific, context-appropriate terms like "chronic plaque-type psoriasis" and their synonyms. Consider participating in community efforts like the Mondo Disease Ontology to improve public resources, which can indirectly benefit your own data standardization and literature discovery processes.

Key insights

Expanding specialized vocabularies improves information recall and contributes to public bio-ontology resources.

Principles

• FAIR philosophy guides vocabulary development.
• Maximal recall requires comprehensive vocabularies.

Method

SciBite used its TERMite NER engine to scan psoriasis-related documents, identify missing terms, and augment VOCabs with new entities and synonyms, while also contributing improvements to the Mondo Disease Ontology.

In practice

• Use NER engines to identify vocabulary gaps.
• Contribute identified issues to public ontologies.

Topics

• Named Entity Recognition
• Biocuration
• Disease Ontology
• Psoriasis
• Healthcare Informatics

Best for: NLP Engineer, AI Scientist, AI Data Scientist, Research Scientist, Data Engineer

Related on AIssential

• BioGraphletQA: Knowledge-Anchored Generation of Complex QA Datasets — Graphlet-anchored LLM generation creates complex, factually grounded QA datasets, mitigating hallucination in specialized domains.
• A Practitioner's Guide To Taxonomies, Part I — Taxonomies offer high ROI as low-fidelity semantic structures, enabling context and inference without full ontological complexity.
• Towards a Universal Dependencies Corpus for Portuguese Epidemiological Reports — Document extraction and representation significantly impact parsing epidemiological texts more than parser selection.
• Talos: Scaling rare disease diagnosis with automated, iterative genomic reanalysis — Talos automates genomic reanalysis for rare diseases, significantly increasing diagnostic yield by utilizing evolving scientific knowledge.
• From Annotated Clinical Narratives to Ontology: Structuring Brazilian Portuguese Clinical Data — A new ontology structures Brazilian Portuguese clinical narratives, enhancing NLP interoperability and semantic expressiveness.
• AAbAAC: An Annotated Corpus for Autoimmunity Information Extraction — Small, specialized annotated corpora significantly boost information extraction performance in niche biomedical domains.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by SciBite.