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

Sentence Entity Resolver for SNOMED CT (Auxiliary Concepts) (bge_base_en_v1_5_onnx embeddings)

  • en
  • snomed
  • resolver
  • licensed
  • clinical
  • auxconcepts
  • bge

Description

This model maps extracted clinical NER entities to SNOMED CT concepts using bge_base_en_v1_5_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_jsl","en","clinical/models")\
    .setInputCols(["sentence","token","embeddings"])\
    .setOutputCol("ner_tags")

ner_converter = NerConverterInternal()\
    .setInputCols(["sentence","token","ner_tags"])\
    .setOutputCol("ner_chunk")\
    .setWhiteList(["Procedure", "Substance", "Drug_Ingredient", "Internal_organ_or_component", "Modifier", "BMI", "LDL", "External_body_part_or_region", "Alcohol", "Treatment", "Test", "Smoking"])

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

embedder = BGEEmbeddings.pretrained("bge_base_en_v1_5_onnx", "en")\
    .setInputCols(["ner_chunk_doc"])\
    .setOutputCol("bge_embeddings")\
    .setCaseSensitive(False)

resolver = SentenceEntityResolverModel.pretrained("bgeresolve_snomed_auxConcepts_20260901","en","clinical/models")\
    .setInputCols(["bge_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([["She underwent an appendectomy for appendicitis. Post-operatively, she was started on penicillin. An echocardiogram showed normal left ventricle function."]]).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_jsl","en","clinical/models")\
    .setInputCols(["sentence","token","embeddings"])\
    .setOutputCol("ner_tags")

ner_converter = medical.NerConverterInternal()\
    .setInputCols(["sentence","token","ner_tags"])\
    .setOutputCol("ner_chunk")\
    .setWhiteList(["Procedure", "Substance", "Drug_Ingredient", "Internal_organ_or_component", "Modifier", "BMI", "LDL", "External_body_part_or_region", "Alcohol", "Treatment", "Test", "Smoking"])

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

embedder = nlp.BGEEmbeddings.pretrained("bge_base_en_v1_5_onnx", "en")\
    .setInputCols(["ner_chunk_doc"])\
    .setOutputCol("bge_embeddings")\
    .setCaseSensitive(False)

resolver = medical.SentenceEntityResolverModel.pretrained("bgeresolve_snomed_auxConcepts_20260901","en","clinical/models")\
    .setInputCols(["bge_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([["She underwent an appendectomy for appendicitis. Post-operatively, she was started on penicillin. An echocardiogram showed normal left ventricle function."]]).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_jsl", "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("Procedure", "Substance", "Drug_Ingredient", "Internal_organ_or_component", "Modifier", "BMI", "LDL", "External_body_part_or_region", "Alcohol", "Treatment", "Test", "Smoking"))

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

val embedder = BGEEmbeddings
    .pretrained("bge_base_en_v1_5_onnx", "en")
    .setInputCols(Array("ner_chunk_doc"))
    .setOutputCol("bge_embeddings")
    .setCaseSensitive(false)

val resolver = SentenceEntityResolverModel
    .pretrained("bgeresolve_snomed_auxConcepts_20260901", "en", "clinical/models")
    .setInputCols(Array("bge_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("She underwent an appendectomy for appendicitis. Post-operatively, she was started on penicillin. An echocardiogram showed normal left ventricle function.").toDF("text")
val res = pipeline.fit(data).transform(data)

Results

| chunk          | label           |   snomed_code | resolution     | all_codes                                                                           | all_resolutions                                                                     |
|:---------------|:----------------|--------------:|:---------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| appendectomy   | Procedure       |      80146002 | appendectomy   | 80146002:::17041004:::6025007:::49586007:::174036004:::428251008:::42332004:::86... | appendectomy:::appendicotomy:::laparoscopic appendectomy:::appendicocecostomy:::... |
| penicillin     | Drug_Ingredient |     764146007 | penicillin     | 764146007:::373291007:::300041008:::323389000:::292954005:::373218000:::89045800... | penicillin:::natural penicillin:::penicillin prophylaxis:::penicillin g:::penici... |
| echocardiogram | Test            |      40701008 | echocardiogram | 40701008:::401000009:::105376000:::439238004:::8151003:::433236007:::1354543009:... | echocardiogram:::echocardiogram requested:::transesophageal echocardiogram:::ech... |

Model Information

Model Name: bgeresolve_snomed_auxConcepts_20260901
Compatibility: Healthcare NLP 6.4.1+
License: Licensed
Edition: Official
Input Labels: [bge_embeddings]
Output Labels: [snomed_code]
Language: en
Size: 1.9 GB
Case sensitive: false