Description
This pretrained model maps LOINC 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)
loinc_resolver = SentenceEntityResolverModel.pretrained("sbiobertresolve_loinc_augmented", "en", "clinical/models")\
.setInputCols(["sbert_embeddings"])\
.setOutputCol("loinc_code")\
.setDistanceFunction("EUCLIDEAN")
resolver2chunk = Resolution2Chunk()\
.setInputCols(["loinc_code"])\
.setOutputCol("loinc2chunk")
chunkMapper = ChunkMapperModel.pretrained("loinc_umls_mapper", "en", "clinical/models")\
.setInputCols(["loinc2chunk"])\
.setOutputCol("mappings")\
pipeline = Pipeline(stages = [
documentAssembler,
sbert_embedder,
loinc_resolver,
resolver2chunk,
chunkMapper])
data = spark.createDataFrame([["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 loinc_resolver = SentenceEntityResolverModel.pretrained("sbiobertresolve_loinc_augmented", "en", "clinical/models")
.setInputCols(Array("sbert_embeddings"))
.setOutputCol("loinc_code")
.setDistanceFunction("EUCLIDEAN")
val resolver2chunk = new Resolution2Chunk()
.setInputCols(Array("loinc_code"))
.setOutputCol("loinc2chunk")
val chunkMapper = ChunkMapperModel.pretrained("loinc_umls_mapper", "en", "clinical/models")
.setInputCols(Array("loinc2chunk"))
.setOutputCol("mappings")
val pipeline = new Pipeline().setStages(Array(
documentAssembler,
sbert_embedder,
loinc_resolver,
resolver2chunk,
chunkMapper
))
val data = spark.createDataFrame(Seq(("aspirin"))).toDF("text")
val mapper_model = pipeline.fit(data)
val result = mapper_model.transform(data)
Results
+-------+----------+---------+
|chunk |loinc_code|umls_code|
+-------+----------+---------+
|aspirin|LA26702-3 |C0004057 |
+-------+----------+---------+
Model Information
| Model Name: | loinc_umls_mapper |
| Compatibility: | Healthcare NLP 5.2.1+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [ner_chunk] |
| Output Labels: | [mappings] |
| Language: | en |
| Size: | 1.9 MB |