Description
This pipeline is designed to extract all entities mappable to HCPCS codes.
2 NER models are used to achieve those tasks.
How to use
from sparknlp.pretrained import PretrainedPipeline
ner_pipeline = PretrainedPipeline("ner_hcpcs_pipeline", "en", "clinical/models")
result = ner_pipeline.annotate("""
Mary received a mechanical prosthetic heart valve in June 2020, and the results were successful.
Diabetes screening test performed, revealing abnormal result.
She uses infusion pump for diabetes and a CPAP machine for sleep apnea.
In 2021, She received a breast prosthesis implant.
""")
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val ner_pipeline = PretrainedPipeline("ner_hcpcs_pipeline", "en", "clinical/models")
val result = ner_pipeline.annotate("""
Mary received a mechanical prosthetic heart valve in June 2020, and the results were successful.
Diabetes screening test performed, revealing abnormal result.
She uses infusion pump for diabetes and a CPAP machine for sleep apnea.
In 2021, She received a breast prosthesis implant.
""")
Results
| | chunks | begin | end | entities |
|---:|:------------------------------------|--------:|------:|:-----------|
| 0 | a mechanical prosthetic heart valve | 15 | 49 | PROCEDURE |
| 1 | infusion pump | 172 | 184 | PROCEDURE |
| 2 | a CPAP machine | 203 | 216 | PROCEDURE |
| 3 | a breast prosthesis implant | 258 | 284 | PROCEDURE |
Model Information
| Model Name: | ner_hcpcs_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
- MedicalNerModel
- NerConverterInternalModel
- ChunkMergeModel