Description
This pipeline includes Named-Entity Recognition and Assertion Status models to extract information from oncology texts. This pipeline focuses on entities related to therapies.
Predicted Entities
Cancer_Surgery, Cancer_Therapy, Chemotherapy, Cycle_Count, Cycle_Day, Cycle_Number, Dosage, Duration, Frequency, Hormonal_Therapy, Immunotherapy, Line_Of_Therapy, Posology_Information, Radiation_Dose, Radiotherapy, Response_To_Treatment, Route, Targeted_Therapy, Unspecific_Therapy
Live Demo Open in Colab Download Copy S3 URI
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("oncology_therapy_pipeline", "en", "clinical/models")
text = '''The patient underwent a mastectomy two years ago. She is currently receiving her second cycle of adriamycin and cyclophosphamide, and is in good overall condition.'''
result = pipeline.fullAnnotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("oncology_therapy_pipeline", "en", "clinical/models")
val text = "The patient underwent a mastectomy two years ago. She is currently receiving her second cycle of adriamycin and cyclophosphamide, and is in good overall condition."
val result = pipeline.fullAnnotate(text)
import nlu
nlu.load("en.oncology_therpay.pipeline").predict("""The patient underwent a mastectomy two years ago. She is currently receiving her second cycle of adriamycin and cyclophosphamide, and is in good overall condition.""")
Results
******************** ner_oncology_wip results ********************
| chunk | ner_label |
|:-----------------|:---------------|
| mastectomy | Cancer_Surgery |
| second cycle | Cycle_Number |
| adriamycin | Chemotherapy |
| cyclophosphamide | Chemotherapy |
******************** ner_oncology_wip results ********************
| chunk | ner_label |
|:-----------------|:---------------|
| mastectomy | Cancer_Surgery |
| second cycle | Cycle_Number |
| adriamycin | Chemotherapy |
| cyclophosphamide | Chemotherapy |
******************** ner_oncology_wip results ********************
| chunk | ner_label |
|:-----------------|:---------------|
| mastectomy | Cancer_Surgery |
| second cycle | Cycle_Number |
| adriamycin | Cancer_Therapy |
| cyclophosphamide | Cancer_Therapy |
******************** ner_oncology_unspecific_posology_wip results ********************
| chunk | ner_label |
|:-----------------|:---------------------|
| mastectomy | Cancer_Therapy |
| second cycle | Posology_Information |
| adriamycin | Cancer_Therapy |
| cyclophosphamide | Cancer_Therapy |
******************** assertion_oncology_wip results ********************
| chunk | ner_label | assertion |
|:-----------------|:---------------|:------------|
| mastectomy | Cancer_Surgery | Past |
| adriamycin | Chemotherapy | Present |
| cyclophosphamide | Chemotherapy | Present |
******************** assertion_oncology_treatment_binary_wip results ********************
| chunk | ner_label | assertion |
|:-----------------|:---------------|:----------------|
| mastectomy | Cancer_Surgery | Present_Or_Past |
| adriamycin | Chemotherapy | Present_Or_Past |
| cyclophosphamide | Chemotherapy | Present_Or_Past |
Model Information
| Model Name: | oncology_therapy_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 4.3.2+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 1.7 GB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverter
- MedicalNerModel
- NerConverter
- MedicalNerModel
- NerConverter
- MedicalNerModel
- NerConverter
- ChunkMergeModel
- ChunkMergeModel
- AssertionDLModel
- AssertionDLModel