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

Mapping Clinical Concepts to Their Corresponding ICD11 Codes

  • en
  • chunk_mapper
  • licensed
  • clinical
  • icd11

Description

This model maps clinical entities and concepts to their corresponding ICD-11 codes. Trained on 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")

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

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

icd11_mapper = ChunkMapperModel.pretrained("icd11_mapper_202601", "en", "clinical/models")\
    .setInputCols(["ner_chunk"])\
    .setOutputCol("mappings")\
    .setRels(["icd11_code"])\
    .setLowerCase(True)

pipeline = Pipeline(stages=[
    document_assembler, sentence_detector, tokenizer, word_embeddings,
    ner_clinical, ner_converter, icd11_mapper
])

data = spark.createDataFrame([[t] for t in ['cholera', 'parkinson disease', 'type 2 diabetes mellitus', 'essential hypertension', 'actinic keratosis']], ["text"])
result = pipeline.fit(data).transform(data)

# ChunkMapperModel.result is the primary/first value only -- read
# metadata['all_k_resolutions'] (':::'-joined) for the full candidate list, e.g. for a genuine
# multi-value collision such as "actinic keratosis" -> [EK90.0, XH36H6].



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

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

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

icd11_mapper = medical.ChunkMapperModel.pretrained("icd11_mapper_202601", "en", "clinical/models")\
    .setInputCols(["ner_chunk"])\
    .setOutputCol("mappings")\
    .setRels(["icd11_code"])\
    .setLowerCase(True)

pipeline = nlp.Pipeline(stages=[
    document_assembler, sentence_detector, tokenizer, word_embeddings,
    ner_clinical, ner_converter, icd11_mapper
])

data = spark.createDataFrame([[t] for t in ['cholera', 'parkinson disease', 'type 2 diabetes mellitus', 'essential hypertension', 'actinic keratosis']], ["text"])
result = pipeline.fit(data).transform(data)



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

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

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

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

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

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

val icd11Mapper = ChunkMapperModel
    .pretrained("icd11_mapper_202601", "en", "clinical/models")
    .setInputCols(Array("ner_chunk"))
    .setOutputCol("mappings")
    .setRels(Array("icd11_code"))
    .setLowerCase(true)

val pipeline = new Pipeline().setStages(Array(
    documentAssembler, sentenceDetector, tokenizer, wordEmbeddings,
    nerClinical, nerConverter, icd11Mapper
))

val data = Seq(['cholera', 'parkinson disease', 'type 2 diabetes mellitus', 'essential hypertension', 'actinic keratosis']).toDF("text")
val result = pipeline.fit(data).transform(data)

Results

| term                     | icd11_code           |
|:-------------------------|:---------------------|
| cholera                  | ['1A00']             |
| parkinson disease        | ['8A00.0']           |
| type 2 diabetes mellitus | ['5A11']             |
| essential hypertension   | ['BA00']             |
| actinic keratosis        | ['EK90.0', 'XH36H6'] |

Model Information

Model Name: icd11_mapper_202601
Compatibility: Healthcare NLP 6.4.1+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 3.2 MB