Edit on GitHub
  • John Snow Labs
  • Dec 05, 2025

Mapping Entities with Corresponding CPT Codes

  • mapper
  • cpt
  • en
  • licensed
  • clinical
  • chunk_mapper

Description

This model maps clinical entities (procedures, tests, treatments) to their corresponding CPT (Current Procedural Terminology) codes. It provides fast and accurate procedural code mapping without requiring embeddings.

Predicted Entities

CPT Codes

Copy S3 URI

How to use


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

sentence_detector = SentenceDetector()\
    .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")

ner_model_converter = NerConverterInternal()\
    .setInputCols(["sentence", "token", "ner"])\
    .setOutputCol("ner_chunk")\
    .setWhiteList(["Procedure", "Test", "Treatment", "Clinical_Dept"])

cpt_mapper = ChunkMapperModel.load("cpt_mapper")\
    .setInputCols(["ner_chunk"])\
    .setOutputCol("mappings")\
    .setRels(["cpt_code"])\
    .setLowerCase(True)

pipeline = Pipeline().setStages([
    document_assembler,
    sentence_detector,
    tokenizer,
    word_embeddings,
    ner_model,
    ner_model_converter,
    cpt_mapper
])

text = """A 28-year-old female underwent episiotomy during vaginal delivery. Pulse oximetry was monitored continuously throughout the procedure. Due to postpartum hemorrhage, blood transfusion was administered. The patient was transferred to the inpatient hospital for overnight observation."""

data = spark.createDataFrame([[text]]).toDF("text")

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



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

sentence_detector = nlp.SentenceDetector()\
    .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")

ner_model_converter = medical.NerConverter()\
    .setInputCols(["sentence", "token", "ner"])\
    .setOutputCol("ner_chunk")\
    .setWhiteList(["Procedure", "Test", "Treatment", "Clinical_Dept"])

cpt_mapper = medical.ChunkMapperModel.load("cpt_mapper")\
    .setInputCols(["ner_chunk"])\
    .setOutputCol("mappings")\
    .setRels(["cpt_code"])\
    .setLowerCase(True)

pipeline = nlp.Pipeline().setStages([
    document_assembler,
    sentence_detector,
    tokenizer,
    word_embeddings,
    ner_model,
    ner_model_converter,
    cpt_mapper
])

text = """A 28-year-old female underwent episiotomy during vaginal delivery. Pulse oximetry was monitored continuously throughout the procedure. Due to postpartum hemorrhage, blood transfusion was administered. The patient was transferred to the inpatient hospital for overnight observation."""

data = spark.createDataFrame([[text]]).toDF("text")

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



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

val sentenceDetector = new SentenceDetector()
    .setInputCols(Array("document"))
    .setOutputCol("sentence")

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

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

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

val nerModelConverter = new NerConverterInternal()
    .setInputCols(Array("sentence", "token", "ner"))
    .setOutputCol("ner_chunk")
    .setWhiteList(Array("Procedure", "Test", "Treatment", "Clinical_Dept"))

val cptMapper = ChunkMapperModel.load("cpt_mapper")
    .setInputCols(Array("ner_chunk"))
    .setOutputCol("mappings")
    .setRels(Array("cpt_code"))
    .setLowerCase(true)

val pipeline = new Pipeline().setStages(Array(
    documentAssembler,
    sentenceDetector,
    tokenizer,
    wordEmbeddings,
    nerModel,
    nerModelConverter,
    cptMapper
))

val data = Seq("""A 28-year-old female underwent episiotomy during vaginal delivery. Pulse oximetry was monitored continuously throughout the procedure. Due to postpartum hemorrhage, blood transfusion was administered. The patient was transferred to the inpatient hospital for overnight observation.""").toDF("text")

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

Results


|ner_chunk         |mapping_result|
|------------------|--------------|
|episiotomy        |59300         |
|Pulse oximetry    |94760         |
|blood transfusion |36430         |
|inpatient hospital|1021881       |

Model Information

Model Name: cpt_mapper
Compatibility: Healthcare NLP 6.2.0+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 5.1 MB

References

CPT resolver models are removed from the Models Hub due to license restrictions and can only be shared with the users who already have a valid CPT license. If you possess one and wish to use this model, kindly contact us at support@johnsnowlabs.com.