Description
This model maps SNOMED codes to their corresponding ICD10-CM codes.
It performs a direct lookup against the training dictionary, providing fast, exact-match code mapping.
Trained on SNOMED CT US Edition 20260901 crosswalk data.
Live Demo Open in Colab Copy S3 URI
How to use
documentAssembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
chunkAssembler = Doc2Chunk()\
.setInputCols(["document"])\
.setOutputCol("snomed_code")
mapper = ChunkMapperModel.pretrained("snomed_icd10cm_mapper_20260901", "en", "clinical/models")\
.setInputCols(["snomed_code"])\
.setOutputCol("mappings")\
.setRels(["icd10cm_code"])
pipeline = Pipeline(stages=[documentAssembler, chunkAssembler, mapper])
data = spark.createDataFrame([["1001000119102"]]).toDF("text")
result = pipeline.fit(data).transform(data)
documentAssembler = nlp.DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
chunkAssembler = nlp.Doc2Chunk()\
.setInputCols(["document"])\
.setOutputCol("snomed_code")
mapper = medical.ChunkMapperModel.pretrained("snomed_icd10cm_mapper_20260901", "en", "clinical/models")\
.setInputCols(["snomed_code"])\
.setOutputCol("mappings")\
.setRels(["icd10cm_code"])
pipeline = nlp.Pipeline(stages=[documentAssembler, chunkAssembler, mapper])
data = spark.createDataFrame([["1001000119102"]]).toDF("text")
result = pipeline.fit(data).transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val chunkAssembler = new Doc2Chunk()
.setInputCols(Array("document"))
.setOutputCol("snomed_code")
val mapper = ChunkMapperModel.pretrained("snomed_icd10cm_mapper_20260901", "en", "clinical/models")
.setInputCols(Array("snomed_code"))
.setOutputCol("mappings")
.setRels(Array("icd10cm_code"))
val pipeline = new Pipeline().setStages(Array(documentAssembler, chunkAssembler, mapper))
val data = Seq("1001000119102").toDF("text")
val result = pipeline.fit(data).transform(data)
Results
| snomed_code | icd10cm_code | all_k_resolutions |
|--------------:|:---------------|:--------------------|
| 1001000119102 | I26.99 | I26.99::: |
| 10001005 | A41.9 | A41.9:::P36.9 |
| 10000006 | R07.9 | R07.9::: |
Model Information
| Model Name: | snomed_icd10cm_mapper_20260901 |
| Compatibility: | Healthcare NLP 6.4.1+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [snomed_code] |
| Output Labels: | [mappings] |
| Language: | en |
| Size: | 2.3 MB |