Pipeline to Detect Entities Related to Cancer Therapies

Description

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

Predicted Entities

Cancer_Surgery, Chemotherapy, Cycle_Count, Cycle_Day, Cycle_Number, Dosage, Duration, Frequency, Hormonal_Therapy, Immunotherapy, Line_Of_Therapy, Radiation_Dose, Radiotherapy, Response_To_Treatment, Route, Targeted_Therapy, Unspecific_Therapy

Copy S3 URI

How to use

from sparknlp.pretrained import PretrainedPipeline

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

text = '''The had previously undergone a left mastectomy and an axillary lymph node dissection for a left breast cancer twenty years ago.
The tumor was positive for ER and PR. Postoperatively, radiotherapy was administered to her breast.
The cancer recurred as a right lung metastasis 13 years later. The patient underwent a regimen consisting of adriamycin (60 mg/m2) and cyclophosphamide (600 mg/m2) over six courses, as first line therapy.'''

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

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

val text = "The had previously undergone a left mastectomy and an axillary lymph node dissection for a left breast cancer twenty years ago.
The tumor was positive for ER and PR. Postoperatively, radiotherapy was administered to her breast.
The cancer recurred as a right lung metastasis 13 years later. The patient underwent a regimen consisting of adriamycin (60 mg/m2) and cyclophosphamide (600 mg/m2) over six courses, as first line therapy."

val result = pipeline.fullAnnotate(text)

Results

|    | ner_chunks                     |   begin |   end | ner_label             |   confidence |
|---:|:-------------------------------|--------:|------:|:----------------------|-------------:|
|  0 | mastectomy                     |      36 |    45 | Cancer_Surgery        |     0.9817   |
|  1 | axillary lymph node dissection |      54 |    83 | Cancer_Surgery        |     0.719725 |
|  2 | radiotherapy                   |     183 |   194 | Radiotherapy          |     0.9984   |
|  3 | recurred                       |     239 |   246 | Response_To_Treatment |     0.9481   |
|  4 | adriamycin                     |     337 |   346 | Chemotherapy          |     0.9981   |
|  5 | 60 mg/m2                       |     349 |   356 | Dosage                |     0.58815  |
|  6 | cyclophosphamide               |     363 |   378 | Chemotherapy          |     0.9976   |
|  7 | 600 mg/m2                      |     381 |   389 | Dosage                |     0.64205  |
|  8 | six courses                    |     397 |   407 | Cycle_Count           |     0.46815  |
|  9 | first line                     |     413 |   422 | Line_Of_Therapy       |     0.95015  |

Model Information

Model Name: ner_oncology_therapy_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