Description
This pretrained pipeline is built on the top of loinc_umls_mapper model and maps LOINC codes to corresponding UMLS codes.
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("loinc_umls_mapping", "en", "clinical/models")
sample_text = """ [['LA26702-3'], ['LP99998-4']]"""
result = pipeline.transform(spark.createDataFrame(sample_text).toDF("text"))
from johnsnowlabs import nlp, medical
pipeline = nlp.PretrainedPipeline("loinc_umls_mapping", "en", "clinical/models")
sample_text = """ [['LA26702-3'], ['LP99998-4']]"""
result = pipeline.transform(spark.createDataFrame(sample_text).toDF("text"))
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = PretrainedPipeline("loinc_umls_mapping", "en", "clinical/models")
val sample_text = """ [['LA26702-3'], ['LP99998-4']]"""
val result = pipeline.transform(spark.createDataFrame(sample_text).toDF("text"))
Results
| loinc_code | umls_code |
| :--------- | :-------- |
| LA26702-3 | C0004057 |
| LP99998-4 | C0050078 |
Model Information
| Model Name: | loinc_umls_mapping |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 6.3.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 3.4 MB |
Included Models
- DocumentAssembler
- Doc2Chunk
- ChunkMapperModel