Description
This pretrained model maps SNOMED codes to corresponding UMLS codes.
Predicted Entities
umls_code
How to use
documentAssembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("ner_chunk")
sbert_embedder = BertSentenceEmbeddings.pretrained("sbiobert_base_cased_mli", "en", "clinical/models")\
.setInputCols(["ner_chunk"])\
.setOutputCol("sbert_embeddings")\
.setCaseSensitive(False)
snomed_resolver = SentenceEntityResolverModel.pretrained("sbiobertresolve_snomed_drug", "en", "clinical/models")\
.setInputCols(["sbert_embeddings"]) \
.setOutputCol("snomed_code")\
.setDistanceFunction("EUCLIDEAN")
resolver2chunk = Resolution2Chunk()\
.setInputCols(["snomed_code"])\
.setOutputCol("snomed2chunk")
chunkerMapper = ChunkMapperModel.pretrained("snomed_umls_mapper", "en", "clinical/models")\
.setInputCols(["snomed2chunk"])\
.setOutputCol("mappings")\
.setRels(["umls_code"])
pipeline = Pipeline(stages = [
documentAssembler,
sbert_embedder,
snomed_resolver,
resolver2chunk,
chunkerMapper])
data = spark.createDataFrame([["acebutolol"],["aspirin"]]).toDF("text")
mapper_model = pipeline.fit(data)
result= mapper_model.transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("ner_chunk")
val sbert_embedder = BertSentenceEmbeddings.pretrained("sbiobert_base_cased_mli","en","clinical/models")
.setInputCols(Array("ner_chunk"))
.setOutputCol("sbert_embeddings")
.setCaseSensitive(false)
val snomed_resolver = SentenceEntityResolverModel.pretrained("sbiobertresolve_snomed_drug","en","clinical/models")
.setInputCols(Array("sbert_embeddings"))
.setOutputCol("snomed_code")
.setDistanceFunction("EUCLIDEAN")
val resolver2chunk = new Resolution2Chunk()
.setInputCols(Array("snomed_code"))
.setOutputCol("snomed2chunk")
val chunkerMapper = ChunkMapperModel.pretrained("snomed_umls_mapper","en","clinical/models")
.setInputCols(Array("snomed2chunk"))
.setOutputCol("mappings")
.setRels(["umls_code"])
val Pipeline(stages = Array(
documentAssembler,
sbert_embedder,
snomed_resolver,
resolver2chunk,
chunkerMapper))
val data = Seq("acebutolol", "aspirin").toDF("text")
val mapper_model = pipeline.fit(data)
result= mapper_model.transform(data)
Results
+----------+-----------+---------+
|chunk |snomed_code|umls_code|
+----------+-----------+---------+
|acebutolol|372815001 |C0000946 |
|aspirin |387458008 |C0004057 |
+----------+-----------+---------+
Model Information
| Model Name: | snomed_umls_mapper |
| Compatibility: | Healthcare NLP 5.2.1+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [ner_chunk] |
| Output Labels: | [mappings] |
| Language: | en |
| Size: | 7.5 MB |