Description
This pretrained pipeline is built on the top of umls_loinc_mapper model and maps UMLS codes to corresponding LOINC codes.
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("umls_loinc_mapping", "en", "clinical/models")
sample_text = """ [['C0000530'], ['C0000726'], ['C0000343'], ['C0000714']]"""
result = pipeline.transform(spark.createDataFrame(sample_text).toDF("text"))
from johnsnowlabs import nlp, medical
pipeline = nlp.PretrainedPipeline("umls_loinc_mapping", "en", "clinical/models")
sample_text = """ [['C0000530'], ['C0000726'], ['C0000343'], ['C0000714']]"""
result = pipeline.transform(spark.createDataFrame(sample_text).toDF("text"))
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = PretrainedPipeline("umls_loinc_mapping", "en", "clinical/models")
val sample_text = """ [['C0000530'], ['C0000726'], ['C0000343'], ['C0000714']]"""
val result = pipeline.transform(spark.createDataFrame(sample_text).toDF("text"))
Results
| umls_code | loinc_code |
| :-------- | :--------- |
| C0000530 | LP15844-1 |
| C0000726 | MTHU059270 |
| C0000343 | MTHU063786 |
| C0000714 | LP101132-1 |
Model Information
| Model Name: | umls_loinc_mapping |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 6.3.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 3.4 MB |
Included Models
- DocumentAssembler
- Doc2Chunk
- ChunkMapperModel