Rare Disease Identification from Clinical Notes with Ontologies and Weak Supervision

05/05/2021

∙

The identification of rare diseases from clinical notes with Natural Language Processing (NLP) is challenging due to the few cases available for machine learning and the need of data annotation from clinical experts. We propose a method using ontologies and weak supervision. The approach includes two steps: (i) Text-to-UMLS, linking text mentions to concepts in Unified Medical Language System (UMLS), with a named entity linking tool (e.g. SemEHR) and weak supervision based on customised rules and Bidirectional Encoder Representations from Transformers (BERT) based contextual representations, and (ii) UMLS-to-ORDO, matching UMLS concepts to rare diseases in Orphanet Rare Disease Ontology (ORDO). Using MIMIC-III discharge summaries as a case study, we show that the Text-to-UMLS process can be greatly improved with weak supervision, without any annotated data from domain experts. Our analysis shows that the overall pipeline processing discharge summaries can surface rare disease cases, which are mostly uncaptured in manual ICD codes of the hospital admissions.

READ FULL TEXT

Rare Disease Identification from Clinical Notes with Ontologies and Weak Supervision

Ontology-Based and Weakly Supervised Rare Disease Phenotyping from Clinical Notes

Adverse Childhood Experiences Identification from Clinical Notes with Ontologies and NLP

Semantic rule Web-based Diagnosis and Treatment of Vector-Borne Diseases using SWRL rules

Ontology-Driven Self-Supervision for Adverse Childhood Experiences Identification Using Social Media Datasets

Exploring deep learning methods for recognizing rare diseases and their clinical manifestations from texts

Language Models sounds the Death Knell of Knowledge Graphs

The RareDis corpus: a corpus annotated with rare diseases, their signs and symptoms

Rare Disease Identification from Clinical Notes with Ontologies and Weak Supervision

Related Research

Ontology-Based and Weakly Supervised Rare Disease Phenotyping from Clinical Notes

Adverse Childhood Experiences Identification from Clinical Notes with Ontologies and NLP

Semantic rule Web-based Diagnosis and Treatment of Vector-Borne Diseases using SWRL rules

Ontology-Driven Self-Supervision for Adverse Childhood Experiences Identification Using Social Media Datasets

Exploring deep learning methods for recognizing rare diseases and their clinical manifestations from texts

Language Models sounds the Death Knell of Knowledge Graphs

The RareDis corpus: a corpus annotated with rare diseases, their signs and symptoms