Description
This pipeline is designed to extract all entities mappable to ATC codes.
1 NER model and a Text Matcher are used to achieve those tasks.
How to use
from sparknlp.pretrained import PretrainedPipeline
ner_pipeline = PretrainedPipeline("ner_atc_pipeline", "en", "clinical/models")
result = ner_pipeline.annotate("""
The patient was prescribed Albuterol inhaler when needed. She was seen by the endocrinology service, prescribed Avandia 4 mg at nights,
Coumadin 5 mg with meals, Metformin 100 mg two times a day, and a daily dose of Lisinopril 10 mg.
""")
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val ner_pipeline = PretrainedPipeline("ner_atc_pipeline", "en", "clinical/models")
val result = ner_pipeline.annotate("""
The patient was prescribed Albuterol inhaler when needed. She was seen by the endocrinology service, prescribed Avandia 4 mg at nights,
Coumadin 5 mg with meals, Metformin 100 mg two times a day, and a daily dose of Lisinopril 10 mg.
""")
Results
| | chunks | begin | end | entities |
|---:|:------------------|--------:|------:|:-----------|
| 0 | Albuterol inhaler | 28 | 44 | DRUG |
| 1 | Avandia 4 mg | 113 | 124 | DRUG |
| 2 | Coumadin 5 mg | 137 | 149 | DRUG |
| 3 | Metformin 100 mg | 163 | 178 | DRUG |
| 4 | Lisinopril 10 mg | 217 | 232 | DRUG |
Model Information
| Model Name: | ner_atc_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 6.0.2+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 1.7 GB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverterInternalModel
- TextMatcherInternalModel
- ChunkMergeModel