Edit on GitHub
  • John Snow Labs
  • Aug 26, 2026

Sentence Entity Resolver for ICD11 (Augmented)

  • licensed
  • en
  • clinical
  • entity_resolution
  • icd11
  • sbiobert

Description

This model performs entity mapping to ICD-11 standards using sentence embeddings. It takes clinical concepts and returns corresponding ICD-11 codes along with official resolution text in metadata. Trained on an augmented pool of the WHO ICD-11 2026-01 release.

Live Demo Open in Colab Copy S3 URI

How to use


document_assembler = 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("word_embeddings")

ner = MedicalNerModel.pretrained("ner_clinical", "en", "clinical/models")\
    .setInputCols(["sentence", "token", "word_embeddings"])\
    .setOutputCol("ner")

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

c2doc = Chunk2Doc()\
    .setInputCols("ner_chunk")\
    .setOutputCol("ner_chunk_doc")

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

icd11_resolver = SentenceEntityResolverModel.pretrained("sbiobertresolve_icd11_augmented_202601", "en", "clinical/models")\
    .setInputCols(["sbert_embeddings"])\
    .setOutputCol("resolution")\
    .setDistanceFunction("EUCLIDEAN")

resolver_pipeline = Pipeline(stages=[
    document_assembler, sentenceDetectorDL, tokenizer, word_embeddings,
    ner, ner_converter, c2doc, sbert_embedder, icd11_resolver
])

data = spark.createDataFrame([["The patient has a history of type 2 diabetes mellitus and essential hypertension, and was recently diagnosed with Parkinson disease."]]).toDF("text")
result = resolver_pipeline.fit(data).transform(data)



document_assembler = 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("word_embeddings")

ner = medical.NerModel.pretrained("ner_clinical", "en", "clinical/models")\
    .setInputCols(["sentence", "token", "word_embeddings"])\
    .setOutputCol("ner")

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

c2doc = nlp.Chunk2Doc()\
    .setInputCols("ner_chunk")\
    .setOutputCol("ner_chunk_doc")

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

icd11_resolver = medical.SentenceEntityResolverModel.pretrained("sbiobertresolve_icd11_augmented_202601", "en", "clinical/models")\
    .setInputCols(["sbert_embeddings"])\
    .setOutputCol("resolution")\
    .setDistanceFunction("EUCLIDEAN")

resolver_pipeline = nlp.Pipeline(stages=[
    document_assembler, sentenceDetectorDL, tokenizer, word_embeddings,
    ner, ner_converter, c2doc, sbert_embedder, icd11_resolver
])

data = spark.createDataFrame([["The patient has a history of type 2 diabetes mellitus and essential hypertension, and was recently diagnosed with Parkinson disease."]]).toDF("text")
result = resolver_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("word_embeddings")

val ner = MedicalNerModel.pretrained("ner_clinical", "en", "clinical/models")
    .setInputCols(Array("sentence", "token", "word_embeddings"))
    .setOutputCol("ner")

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

val c2doc = new Chunk2Doc()
    .setInputCols("ner_chunk")
    .setOutputCol("ner_chunk_doc")

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

val icd11_resolver = SentenceEntityResolverModel.pretrained("sbiobertresolve_icd11_augmented_202601", "en", "clinical/models")
    .setInputCols(Array("sbert_embeddings"))
    .setOutputCol("resolution")
    .setDistanceFunction("EUCLIDEAN")

val resolver_pipeline = new Pipeline().setStages(Array(
    documentAssembler, sentenceDetectorDL, tokenizer, word_embeddings,
    ner, ner_converter, c2doc, sbert_embedder, icd11_resolver
))

val data = Seq("The patient has a history of type 2 diabetes mellitus and essential hypertension, and was recently diagnosed with Parkinson disease.").toDF("text")
val result = resolver_pipeline.fit(data).transform(data)

Results

| ner_chunk                | entity   | icd11_code   | resolution_text                                     | all_k_results                                                                       | all_k_cosine_distances                                                              | all_k_resolutions                                                                   |
|:-------------------------|:---------|:-------------|:----------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type 2 diabetes mellitus | PROBLEM  | 5A11         | type 2 diabetes mellitus [type 2 diabetes mellitus] | 5A11:::SP60:::EL3Y:::5A12:::5A13:::MF83:::5A10:::KB60.2:::9B71.00:::5A14:::DA93.... | 0.0000:::0.0648:::0.0641:::0.0940:::0.0966:::0.1001:::0.0995:::0.1025:::0.1096::... | type 2 diabetes mellitus [type 2 diabetes mellitus]:::diabetes mellitus disorder... |
| essential hypertension   | PROBLEM  | BA00         | essential hypertension [essential hypertension]     | BA00:::BA04:::BA00.Y:::BA01:::BA00.Z:::BA00.1:::BA00.2:::5A72.0:::BA00.0            | 0.0000:::0.0514:::0.0547:::0.0558:::0.0571:::0.0580:::0.0719:::0.0755:::0.0761      | essential hypertension [essential hypertension]:::secondary hypertension [second... |
| Parkinson disease        | PROBLEM  | 8A00.0       | parkinson disease [parkinson disease]               | 8A00.0:::8A00:::8A00.01:::8A00.3:::8A00.2Y:::8A00.2:::8A00.1Y:::8A00.24:::8A00.2... | 0.0000:::0.0533:::0.0572:::0.0630:::0.0780:::0.0883:::0.0871:::0.0894:::0.0937::... | parkinson disease [parkinson disease]:::parkinsonism [parkinsonism]:::parkinson ... |

Model Information

Model Name: sbiobertresolve_icd11_augmented_202601
Compatibility: Healthcare NLP 6.4.1+
License: Licensed
Edition: Official
Input Labels: [sbert_embeddings]
Output Labels: [icd11_code]
Language: en
Size: 357.1 MB
Case sensitive: false