Description
This pretrained pipeline is built on the top of icd10cm_umls_mapper model and maps ICD10CM codes to corresponding UMLS codes
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("icd10cm_umls_mapping", "en", "clinical/models")
sample_text = """ [['A01.2'], ['F10.220']]"""
result = pipeline.transform(spark.createDataFrame(sample_text).toDF("text"))
from johnsnowlabs import nlp, medical
pipeline = nlp.PretrainedPipeline("icd10cm_umls_mapping", "en", "clinical/models")
sample_text = """ [['A01.2'], ['F10.220']]"""
result = pipeline.transform(spark.createDataFrame(sample_text).toDF("text"))
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = PretrainedPipeline("icd10cm_umls_mapping", "en", "clinical/models")
val sample_text = """ [['A01.2'], ['F10.220']]"""
val result = pipeline.transform(spark.createDataFrame(sample_text).toDF("text"))
Results
| icd10cm_code | umls_code |
| :----------- | :-------- |
| A01.2 | C0343376 |
| F10.220 | C2874385 |
Model Information
| Model Name: | icd10cm_umls_mapping |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 6.3.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 1.4 MB |
Included Models
- DocumentAssembler
- Doc2Chunk
- ChunkMapperModel