Pipeline to Extract Cancer Therapies and Granular Posology Information

Description

This pretrained pipeline is built on the top of ner_oncology_posology model.

Predicted Entities

Cancer_Surgery, Cancer_Therapy, Cycle_Count, Cycle_Day, Cycle_Number, Dosage, Duration, Frequency, Radiation_Dose, Radiotherapy, Route

Copy S3 URI

How to use

from sparknlp.pretrained import PretrainedPipeline

pipeline = PretrainedPipeline("ner_oncology_posology_pipeline", "en", "clinical/models")

text = '''The patient underwent a regimen consisting of adriamycin (60 mg/m2) and cyclophosphamide (600 mg/m2) over six courses. She is currently receiving his second cycle of chemotherapy and is in good overall condition.'''

result = pipeline.fullAnnotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

val pipeline = new PretrainedPipeline("ner_oncology_posology_pipeline", "en", "clinical/models")

val text = "The patient underwent a regimen consisting of adriamycin (60 mg/m2) and cyclophosphamide (600 mg/m2) over six courses. She is currently receiving his second cycle of chemotherapy and is in good overall condition."

val result = pipeline.fullAnnotate(text)

Results

|    | ner_chunks       |   begin |   end | ner_label      |   confidence |
|---:|:-----------------|--------:|------:|:---------------|-------------:|
|  0 | adriamycin       |      46 |    55 | Cancer_Therapy |      1       |
|  1 | 60 mg/m2         |      58 |    65 | Dosage         |      0.92005 |
|  2 | cyclophosphamide |      72 |    87 | Cancer_Therapy |      0.9999  |
|  3 | 600 mg/m2        |      90 |    98 | Dosage         |      0.9229  |
|  4 | six courses      |     106 |   116 | Cycle_Count    |      0.494   |
|  5 | second cycle     |     150 |   161 | Cycle_Number   |      0.98675 |
|  6 | chemotherapy     |     166 |   177 | Cancer_Therapy |      1       |

Model Information

Model Name: ner_oncology_posology_pipeline
Type: pipeline
Compatibility: Healthcare NLP 4.3.0+
License: Licensed
Edition: Official
Language: en
Size: 1.7 GB

Included Models

  • DocumentAssembler
  • SentenceDetectorDLModel
  • TokenizerModel
  • WordEmbeddingsModel
  • MedicalNerModel
  • NerConverterInternalModel