Clinical Findings to UMLS Code Pipeline

Description

This pretrained pipeline maps entities (Clinical Findings) 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_clinical_findings_resolver_pipeline", "en", "clinical/models")

result = resolver_pipeline.annotate("""HTG-induced pancreatitis associated with an acute hepatitis, and obesity""")

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

result = resolver_pipeline.annotate("""HTG-induced pancreatitis associated with an acute hepatitis, and obesity""")

import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

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

val result = resolver_pipeline.annotate("""HTG-induced pancreatitis associated with an acute hepatitis, and obesity""")

Results

+------------------------+---------+---------+
|chunk                   |ner_label|umls_code|
+------------------------+---------+---------+
|HTG-induced pancreatitis|PROBLEM  |C3808945 |
|an acute hepatitis      |PROBLEM  |C4750596 |
|obesity                 |PROBLEM  |C4759928 |
+------------------------+---------+---------+

Model Information

Included Models

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