Description
This pipeline maps drug entities to their corresponding RxNorm codes. It provides fast and accurate drug code mapping without requiring embeddings.
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("rxnorm_mapper_pipeline", "en", "clinical/models")
sample_text = """ The patient reported persistent musculoskeletal discomfort, for which ibuprofen topical cream was initiated. Due to concurrent scalp irritation, selenium sulfide 25 mg/ml was also prescribed, and salicylamide 250 mg was added for additional symptomatic relief."""
result = pipeline.transform(spark.createDataFrame([[sample_text]]).toDF("text"))
from johnsnowlabs import nlp, medical
pipeline = nlp.PretrainedPipeline("rxnorm_mapper_pipeline", "en", "clinical/models")
sample_text = """ The patient reported persistent musculoskeletal discomfort, for which ibuprofen topical cream was initiated. Due to concurrent scalp irritation, selenium sulfide 25 mg/ml was also prescribed, and salicylamide 250 mg was added for additional symptomatic relief."""
result = pipeline.transform(spark.createDataFrame([[sample_text]]).toDF("text"))
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = PretrainedPipeline("rxnorm_mapper_pipeline", "en", "clinical/models")
val sample_text = """ The patient reported persistent musculoskeletal discomfort, for which ibuprofen topical cream was initiated. Due to concurrent scalp irritation, selenium sulfide 25 mg/ml was also prescribed, and salicylamide 250 mg was added for additional symptomatic relief."""
val result = pipeline.transform(spark.createDataFrame([[sample_text]]).toDF("text"))
Results
| ner_chunk | mapping_result |
| :------------------------ | :------------- |
| ibuprofen topical cream | 377732 |
| selenium sulfide 25 mg/ml | 328880 |
| salicylamide 250 mg | 316651 |
Model Information
| Model Name: | rxnorm_mapper_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 6.3.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 1.7 GB |
Included Models
- DocumentAssembler
- SentenceDetector
- TokenizerModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverterInternalModel
- ChunkMapperModel