Drug Substance to UMLS Code Pipeline

Description

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

Predicted Entities

DRUG

Live Demo Open in Colab Download Copy S3 URI

How to use

from sparknlp.pretrained import PretrainedPipeline

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

result = resolver_pipeline.annotate("""The patient was given  metformin, lenvatinib and Magnesium hydroxide 100mg/1ml""")

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

result = resolver_pipeline.annotate("""The patient was given  metformin, lenvatinib and Magnesium hydroxide 100mg/1ml""")

import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

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

val result = resolver_pipeline.annotate("""The patient was given  metformin, lenvatinib and Magnesium hydroxide 100mg/1ml""")

Results

+-----------------------------+---------+---------+
|chunk                        |ner_label|umls_code|
+-----------------------------+---------+---------+
|metformin                    |DRUG     |C0025598 |
|lenvatinib                   |DRUG     |C2986924 |
|Magnesium hydroxide 100mg/1ml|DRUG     |C1134402 |
+-----------------------------+---------+---------+

Model Information

Included Models

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