Description
This pipeline is designed to extract all entities mappable to SNOMED (Clinical Findings) codes.
How to use
from sparknlp.pretrained import PretrainedPipeline
ner_pipeline = PretrainedPipeline("ner_snomed_findings_pipeline", "en", "clinical/models")
result = ner_pipeline.annotate("""
The patient exhibited recurrent upper respiratory tract infections, fever, unintentional weight loss, and occasional night sweats.
Clinically, they appeared cachectic and pale, with notable hepatosplenomegaly. Laboratory results confirmed pancytopenia.
""")
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val ner_pipeline = PretrainedPipeline("ner_snomed_findings_pipeline", "en", "clinical/models")
val result = ner_pipeline.annotate("""
The patient exhibited recurrent upper respiratory tract infections, fever, unintentional weight loss, and occasional night sweats.
Clinically, they appeared cachectic and pale, with notable hepatosplenomegaly. Laboratory results confirmed pancytopenia.
""")
Results
| | chunks | begin | end | entities |
|---:|:---------------------------------------------|--------:|------:|:-----------|
| 0 | recurrent upper respiratory tract infections | 23 | 66 | PROBLEM |
| 1 | fever | 69 | 73 | PROBLEM |
| 2 | unintentional weight loss | 76 | 100 | PROBLEM |
| 3 | occasional night sweats | 107 | 129 | PROBLEM |
| 4 | cachectic | 159 | 167 | PROBLEM |
| 5 | pale | 173 | 176 | PROBLEM |
| 6 | notable hepatosplenomegaly | 184 | 209 | PROBLEM |
| 7 | pancytopenia | 241 | 252 | PROBLEM |
Model Information
| Model Name: | ner_snomed_findings_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 6.0.2+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 1.8 GB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverterInternalModel
- MedicalNerModel
- NerConverterInternalModel
- MedicalNerModel
- NerConverterInternalModel
- MedicalNerModel
- NerConverterInternalModel
- ChunkMergeModel