Diseases and Syndromes to UMLS Code Pipeline

Description

This pretrained pipeline maps entities (Diseases and Syndromes) with their corresponding UMLS CUI codes. You’ll just feed your text and it will return the corresponding UMLS codes.

Predicted Entities

PROBLEM

Live Demo Open in Colab Download Copy S3 URI

How to use

from sparknlp.pretrained import PretrainedPipeline

resolver_pipeline = PretrainedPipeline("umls_disease_syndrome_resolver_pipeline", "en", "clinical/models")

result = resolver_pipeline.annotate("""A 34-year-old female with a history of poor appetite, gestational diabetes mellitus, acyclovir allergy and polyuria.""")

resolver_pipeline = nlp.PretrainedPipeline("umls_disease_syndrome_resolver_pipeline", "en", "clinical/models")

result = resolver_pipeline.annotate("""A 34-year-old female with a history of poor appetite, gestational diabetes mellitus, acyclovir allergy and polyuria.""")

import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

val resolver_pipeline = PretrainedPipeline("umls_disease_syndrome_resolver_pipeline", "en", "clinical/models")

val result = resolver_pipeline.annotate("""A 34-year-old female with a history of poor appetite, gestational diabetes mellitus, acyclovir allergy and polyuria.""")

Results

+-----------------------------+---------+---------+
|chunk                        |ner_label|umls_code|
+-----------------------------+---------+---------+
|poor appetite                |PROBLEM  |C0003123 |
|gestational diabetes mellitus|PROBLEM  |C0085207 |
|acyclovir allergy            |PROBLEM  |C0571297 |
|polyuria                     |PROBLEM  |C0011848 |
+-----------------------------+---------+---------+

Model Information

Included Models

• DocumentAssembler
• SentenceDetector
• TokenizerModel
• WordEmbeddingsModel
• MedicalNerModel
• NerConverter
• MedicalNerModel
• NerConverter
• ChunkMergeModel
• ChunkMapperModel
• ChunkMapperFilterer
• Chunk2Doc
• BertSentenceEmbeddings
• SentenceEntityResolverModel
• ResolverMerger