Description
This pipeline is designed to extract ADE and DRUG entities, and establish relations between the extracted DRUG and ADE results from the clinical documents.
2 NER models and a text matcher are used to accomplish the designated tasks.
How to use
from sparknlp.pretrained import PretrainedPipeline
ner_pipeline = PretrainedPipeline("explain_clinical_doc_ade_light", "en", "clinical/models")
result = ner_pipeline.annotate("""We describe the side effects of 5-FU in a colon cancer patient who suffered severe mucositis, desquamating dermatitis, prolonged myelosuppression, and neurologic toxicity that required admission to the intensive care unit.
Anterior lumbosacral radiculopathy after intrathecal methotrexate treatment and acute erythroid leukemia after cyclophosphamide therapy for multiple myeloma: report of two cases.""")
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val ner_pipeline = PretrainedPipeline("explain_clinical_doc_ade_light", "en", "clinical/models")
val result = ner_pipeline.annotate("""We describe the side effects of 5-FU in a colon cancer patient who suffered severe mucositis, desquamating dermatitis, prolonged myelosuppression, and neurologic toxicity that required admission to the intensive care unit.
Anterior lumbosacral radiculopathy after intrathecal methotrexate treatment and acute erythroid leukemia after cyclophosphamide therapy for multiple myeloma: report of two cases.""")
Results
NER Result
| | chunks | begin | end | entities |
|---:|:-----------------------------------|--------:|------:|:-----------|
| 0 | 5-FU | 32 | 35 | DRUG |
| 1 | severe mucositis | 76 | 91 | ADE |
| 2 | desquamating dermatitis | 94 | 116 | ADE |
| 3 | prolonged myelosuppression | 119 | 144 | ADE |
| 4 | neurologic toxicity | 151 | 169 | ADE |
| 5 | Anterior lumbosacral radiculopathy | 224 | 257 | ADE |
| 6 | methotrexate | 277 | 288 | DRUG |
| 7 | acute erythroid leukemia | 304 | 327 | ADE |
| 8 | cyclophosphamide | 335 | 350 | DRUG |
# RE Result
| | relation | entity1 | entity1_begin | entity1_end | chunk1 | entity2 | entity2_begin | entity2_end | chunk2 | confidence |
|---:|-----------:|:----------|----------------:|--------------:|:-----------------------------------|:----------|----------------:|--------------:|:---------------------------|-------------:|
| 0 | 1 | DRUG | 32 | 35 | 5-FU | ADE | 76 | 91 | severe mucositis | 1 |
| 1 | 1 | DRUG | 32 | 35 | 5-FU | ADE | 94 | 116 | desquamating dermatitis | 1 |
| 2 | 1 | DRUG | 32 | 35 | 5-FU | ADE | 119 | 144 | prolonged myelosuppression | 1 |
| 3 | 1 | DRUG | 32 | 35 | 5-FU | ADE | 151 | 169 | neurologic toxicity | 1 |
| 4 | 1 | ADE | 223 | 256 | Anterior lumbosacral radiculopathy | DRUG | 276 | 287 | methotrexate | 1 |
| 5 | 1 | ADE | 223 | 256 | Anterior lumbosacral radiculopathy | DRUG | 334 | 349 | cyclophosphamide | 1 |
| 6 | 1 | DRUG | 276 | 287 | methotrexate | ADE | 303 | 326 | acute erythroid leukemia | 1 |
Model Information
| Model Name: | explain_clinical_doc_ade_light |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 6.0.2+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 1.8 GB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- WordEmbeddingsModel
- TextMatcherInternalModel
- MedicalNerModel
- NerConverterInternalModel
- MedicalNerModel
- NerConverterInternalModel
- ChunkMergeModel
- ChunkMergeModel
- ChunkMapperModel
- PerceptronModel
- DependencyParserModel
- RelationExtractionModel