Description
A pipeline with ner_clinical_events, assertion_dl and re_temporal_events_clinical. It will extract clinical entities, assign assertion status and find temporal relationships between clinical entities.
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("explain_clinical_doc_era", "en", "clinical/models")
text = """She is admitted to The John Hopkins Hospital 2 days ago with a history of gestational diabetes mellitus diagnosed. She denied pain and any headache. She was seen by the endocrinology service and she was discharged on 03/02/2018 on 40 units of insulin glargine, 12 units of insulin lispro, and metformin 1000 mg two times a day. She had close follow-up with endocrinology post discharge. """
result = pipeline.fullAnnotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("explain_clinical_doc_era", "en", "clinical/models")
val text = """She is admitted to The John Hopkins Hospital 2 days ago with a history of gestational diabetes mellitus diagnosed. She denied pain and any headache. She was seen by the endocrinology service and she was discharged on 03/02/2018 on 40 units of insulin glargine, 12 units of insulin lispro, and metformin 1000 mg two times a day. She had close follow-up with endocrinology post discharge. """
val result = pipeline.fullAnnotate(text)
import nlu
nlu.load("en.explain_doc.era").predict("""She is admitted to The John Hopkins Hospital 2 days ago with a history of gestational diabetes mellitus diagnosed. She denied pain and any headache. She was seen by the endocrinology service and she was discharged on 03/02/2018 on 40 units of insulin glargine, 12 units of insulin lispro, and metformin 1000 mg two times a day. She had close follow-up with endocrinology post discharge. """)
Results
| | relation | entity1 | entity1_begin | entity1_end | chunk1 | entity2 | entity2_begin | entity2_end | chunk2 | confidence |
|---:|:-----------|:--------------|----------------:|--------------:|:--------------------------|:--------------|----------------:|--------------:|:------------------------------|-------------:|
| 0 | AFTER | OCCURRENCE | 7 | 14 | admitted | CLINICAL_DEPT | 19 | 43 | The John Hopkins Hospital | 0.963836 |
| 1 | BEFORE | OCCURRENCE | 7 | 14 | admitted | DATE | 45 | 54 | 2 days ago | 0.587098 |
| 2 | BEFORE | OCCURRENCE | 7 | 14 | admitted | PROBLEM | 74 | 102 | gestational diabetes mellitus | 0.999991 |
| 3 | OVERLAP | CLINICAL_DEPT | 19 | 43 | The John Hopkins Hospital | DATE | 45 | 54 | 2 days ago | 0.996056 |
| 4 | BEFORE | CLINICAL_DEPT | 19 | 43 | The John Hopkins Hospital | PROBLEM | 74 | 102 | gestational diabetes mellitus | 0.995216 |
| 5 | OVERLAP | DATE | 45 | 54 | 2 days ago | PROBLEM | 74 | 102 | gestational diabetes mellitus | 0.996954 |
| 6 | BEFORE | EVIDENTIAL | 119 | 124 | denied | PROBLEM | 126 | 129 | pain | 1 |
| 7 | BEFORE | EVIDENTIAL | 119 | 124 | denied | PROBLEM | 135 | 146 | any headache | 1 |
Model Information
| Model Name: | explain_clinical_doc_era |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 4.3.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 1.7 GB |
Included Models
- DocumentAssembler
- SentenceDetector
- TokenizerModel
- PerceptronModel
- DependencyParserModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverterInternalModel
- RelationExtractionModel
- AssertionDLModel