Edit on GitHub
  • John Snow Labs
  • Jul 28, 2025

HPO Code To Extraocular Movements (EOM) Mapping

  • licensed
  • en
  • hpo
  • eom
  • mapping
  • extraocular

Description

This pretrained model maps HPO codes to their related extraocular movements (EOM). It also returns all the possible EOMs in the all_k_resolutions in the metadata.

Open in Colab Copy S3 URI

How to use


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

chunk_assembler = Doc2Chunk()\
      .setInputCols(["document"])\
      .setOutputCol("hpo_code")

mapperModel = ChunkMapperModel.pretrained("hpo_code_eom_mapper", "en", "clinical/models")\
    .setInputCols(["hpo_code"])\
    .setOutputCol("mappings")\
    .setRels(["eom"])

mapper_pipeline = Pipeline(stages=[
    document_assembler,
    chunk_assembler,
    mapperModel
])

data = spark.createDataFrame([["HP:0000154"],["HP:0400001"],["HP:0009765"]]).toDF("text")

result = mapper_pipeline.fit(data).transform(data)



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

chunk_assembler = nlp.Doc2Chunk()\
      .setInputCols(["document"])\
      .setOutputCol("hpo_code")

mapperModel = medical.ChunkMapperModel.pretrained("hpo_code_eom_mapper", "en", "clinical/models")\
    .setInputCols(["hpo_code"])\
    .setOutputCol("mappings")\
    .setRels(["eom"])

mapper_pipeline = nlp.Pipeline(stages=[
    document_assembler,
    chunk_assembler,
    mapperModel
])

data = spark.createDataFrame([["HP:0000154"],["HP:0400001"],["HP:0009765"]]).toDF("text")

result = mapper_pipeline.fit(data).transform(data)



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

val chunk_assembler = new Doc2Chunk()
      .setInputCols("document")
      .setOutputCol("hpo_code")

val mapperModel = ChunkMapperModel.pretrained("hpo_code_eom_mapper", "en", "clinical/models")
    .setInputCols("hpo_code")
    .setOutputCol("mappings")
    .setRels(Array("eom"))

val mapper_pipeline = new Pipeline().setStages(Array(
    document_assembler,
    chunk_assembler,
    mapperModel
))


val data = Seq("HP:0000154","HP:0400001","HP:0009765").toDF("text")

val result = mapper_pipeline.fit(data).transform(data)

Results


+----------+--------------------+-----------------------+
|  hpo_code|                 eom|      all_k_resolutions|
+----------+--------------------+-----------------------+
|HP:0000154|EOM:a6a2d57a281ead72|EOM:a6a2d57a281ead72:::|
|HP:0400001|EOM:8a5493c72e0dd13c|EOM:8a5493c72e0dd13c:::|
|HP:0009765|EOM:49acd433e354541b|EOM:49acd433e354541b:::|
+----------+--------------------+-----------------------+

Model Information

Model Name: hpo_code_eom_mapper
Compatibility: Healthcare NLP 6.0.4+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 10.3 KB