Edit on GitHub
  • John Snow Labs
  • Sep 11, 2026

Sentence Entity Resolver for SNOMED CT (Drugs) (sbiobert_base_cased_mli_onnx embeddings)

  • en
  • snomed
  • resolver
  • licensed
  • clinical
  • drug
  • sbiobert

Description

This model maps extracted clinical NER entities to SNOMED CT concepts using sbiobert_base_cased_mli_onnx embeddings.

It is trained on SNOMED CT US Edition 20260901 release.

Live Demo Open in Colab Copy S3 URI

How to use

documentAssembler = DocumentAssembler()\
    .setInputCol("text")\
    .setOutputCol("document")

sentenceDetectorDL = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare", "en", "clinical/models")\
    .setInputCols(["document"])\
    .setOutputCol("sentence")

tokenizer = Tokenizer()\
    .setInputCols(["sentence"])\
    .setOutputCol("token")

word_embeddings = WordEmbeddingsModel.pretrained("embeddings_clinical","en","clinical/models")\
    .setInputCols(["sentence","token"])\
    .setOutputCol("embeddings")

ner_model = MedicalNerModel.pretrained("ner_posology","en","clinical/models")\
    .setInputCols(["sentence","token","embeddings"])\
    .setOutputCol("ner_tags")

ner_converter = NerConverterInternal()\
    .setInputCols(["sentence","token","ner_tags"])\
    .setOutputCol("ner_chunk")\
    .setWhiteList(["DRUG"])

chunk2doc = Chunk2Doc()\
    .setInputCols(["ner_chunk"])\
    .setOutputCol("ner_chunk_doc")

embedder = BertSentenceEmbeddings.pretrained("sbiobert_base_cased_mli_onnx", "en", "clinical/models")\
    .setInputCols(["ner_chunk_doc"])\
    .setOutputCol("sbert_embeddings")\
    .setCaseSensitive(False)

resolver = SentenceEntityResolverModel.pretrained("sbiobertresolve_snomed_drug_20260901","en","clinical/models")\
    .setInputCols(["sbert_embeddings"])\
    .setOutputCol("snomed_code")\
    .setDistanceFunction("EUCLIDEAN")\
    .setThreshold(1000)

pipeline = Pipeline(stages=[\
    documentAssembler, sentenceDetectorDL, tokenizer, word_embeddings, ner_model, ner_converter, chunk2doc, embedder, resolver\
])

data = spark.createDataFrame([["John's doctor prescribed aspirin for his heart condition, along with paracetamol for his fever and headache, amoxicillin for his tonsilitis and lansoprazole for his GORD."]]).toDF("text")
result = pipeline.fit(data).transform(data)

documentAssembler = nlp.DocumentAssembler()\
    .setInputCol("text")\
    .setOutputCol("document")

sentenceDetectorDL = nlp.SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare", "en", "clinical/models")\
    .setInputCols(["document"])\
    .setOutputCol("sentence")

tokenizer = nlp.Tokenizer()\
    .setInputCols(["sentence"])\
    .setOutputCol("token")

word_embeddings = nlp.WordEmbeddingsModel.pretrained("embeddings_clinical","en","clinical/models")\
    .setInputCols(["sentence","token"])\
    .setOutputCol("embeddings")

ner_model = medical.NerModel.pretrained("ner_posology","en","clinical/models")\
    .setInputCols(["sentence","token","embeddings"])\
    .setOutputCol("ner_tags")

ner_converter = medical.NerConverterInternal()\
    .setInputCols(["sentence","token","ner_tags"])\
    .setOutputCol("ner_chunk")\
    .setWhiteList(["DRUG"])

chunk2doc = nlp.Chunk2Doc()\
    .setInputCols(["ner_chunk"])\
    .setOutputCol("ner_chunk_doc")

embedder = nlp.BertSentenceEmbeddings.pretrained("sbiobert_base_cased_mli_onnx", "en", "clinical/models")\
    .setInputCols(["ner_chunk_doc"])\
    .setOutputCol("sbert_embeddings")\
    .setCaseSensitive(False)

resolver = medical.SentenceEntityResolverModel.pretrained("sbiobertresolve_snomed_drug_20260901","en","clinical/models")\
    .setInputCols(["sbert_embeddings"])\
    .setOutputCol("snomed_code")\
    .setDistanceFunction("EUCLIDEAN")\
    .setThreshold(1000)

pipeline = nlp.Pipeline(stages=[\
    documentAssembler, sentenceDetectorDL, tokenizer, word_embeddings, ner_model, ner_converter, chunk2doc, embedder, resolver\
])

data = spark.createDataFrame([["John's doctor prescribed aspirin for his heart condition, along with paracetamol for his fever and headache, amoxicillin for his tonsilitis and lansoprazole for his GORD."]]).toDF("text")
result = pipeline.fit(data).transform(data)


val documentAssembler = new DocumentAssembler()
    .setInputCol("text")
    .setOutputCol("document")

val sentenceDetectorDL = SentenceDetectorDLModel
    .pretrained("sentence_detector_dl_healthcare", "en", "clinical/models")
    .setInputCols(Array("document"))
    .setOutputCol("sentence")

val tokenizer = new Tokenizer()
    .setInputCols("sentence")
    .setOutputCol("token")

val word_embeddings = WordEmbeddingsModel
    .pretrained("embeddings_clinical", "en", "clinical/models")
    .setInputCols(Array("sentence", "token"))
    .setOutputCol("embeddings")

val ner_model = MedicalNerModel
    .pretrained("ner_posology", "en", "clinical/models")
    .setInputCols(Array("sentence", "token", "embeddings"))
    .setOutputCol("ner_tags")

val ner_converter = new NerConverterInternal()
    .setInputCols(Array("sentence", "token", "ner_tags"))
    .setOutputCol("ner_chunk")
    .setWhiteList(Array("DRUG"))

val chunk2doc = new Chunk2Doc()
    .setInputCols(Array("ner_chunk"))
    .setOutputCol("ner_chunk_doc")

val embedder = BertSentenceEmbeddings
    .pretrained("sbiobert_base_cased_mli_onnx", "en", "clinical/models")
    .setInputCols(Array("ner_chunk_doc"))
    .setOutputCol("sbert_embeddings")
    .setCaseSensitive(false)

val resolver = SentenceEntityResolverModel
    .pretrained("sbiobertresolve_snomed_drug_20260901", "en", "clinical/models")
    .setInputCols(Array("sbert_embeddings"))
    .setOutputCol("snomed_code")
    .setDistanceFunction("EUCLIDEAN")
    .setThreshold(1000)

val pipeline = new Pipeline().setStages(Array(
    documentAssembler, sentenceDetectorDL, tokenizer, word_embeddings, ner_model, ner_converter, chunk2doc, embedder, resolver
))

val data = Seq("John's doctor prescribed aspirin for his heart condition, along with paracetamol for his fever and headache, amoxicillin for his tonsilitis and lansoprazole for his GORD.").toDF("text")
val res = pipeline.fit(data).transform(data)

Results

| chunk        | label   |   snomed_code | resolution   | all_codes                                                                           | all_resolutions                                                                     |
|:-------------|:--------|--------------:|:-------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| aspirin      | DRUG    |     387458008 | aspirin      | 387458008:::7947003:::426365001:::412566001:::25796002:::87303007:::319796006:::... | aspirin:::aspirin-containing product:::aspirin, buffered:::buffered aspirin-cont... |
| paracetamol  | DRUG    |     387517004 | paracetamol  | 387517004:::1285524005:::90332006:::395833008:::18712002:::724182003:::59034000:... | paracetamol:::propacetamol:::paracetamol-containing product:::piracetam:::phenac... |
| amoxicillin  | DRUG    |     372687004 | amoxicillin  | 372687004:::27658006:::427483001:::117147001:::387170002:::373276005:::442859000... | amoxicillin:::amoxicillin-containing product:::amoxicillin sodium:::almecillin::... |
| lansoprazole | DRUG    |     386888004 | lansoprazole | 386888004:::108666007:::441863009:::716069007:::372549002:::395774003:::39604700... | lansoprazole:::lansoprazole-containing product:::dexlansoprazole:::brexpiprazole... |

Model Information

Model Name: sbiobertresolve_snomed_drug_20260901
Compatibility: Healthcare NLP 6.4.1+
License: Licensed
Edition: Official
Input Labels: [sbert_embeddings]
Output Labels: [snomed_code]
Language: en
Size: 238.2 MB
Case sensitive: false