Description
This pretrained pipeline is built on the top of ner_posology_experimental model.
How to use
pipeline = PretrainedPipeline("ner_posology_experimental_pipeline", "en", "clinical/models")
pipeline.annotate("Y-90 Humanized Anti-Tac: 10 mCi (if a bone marrow transplant was part of the patient's previous therapy) or 15 mCi of yttrium labeled anti-TAC; followed by calcium trisodium Inj (Ca DTPA). Calcium-DTPA: Ca-DTPA will be administered intravenously on Days 1-3 to clear the radioactive agent from the body.")
val pipeline = new PretrainedPipeline("ner_posology_experimental_pipeline", "en", "clinical/models")
pipeline.annotate("Y-90 Humanized Anti-Tac: 10 mCi (if a bone marrow transplant was part of the patient's previous therapy) or 15 mCi of yttrium labeled anti-TAC; followed by calcium trisodium Inj (Ca DTPA). Calcium-DTPA: Ca-DTPA will be administered intravenously on Days 1-3 to clear the radioactive agent from the body.")
import nlu
nlu.load("en.med_ner.posology_experimental.pipeline").predict("""Y-90 Humanized Anti-Tac: 10 mCi (if a bone marrow transplant was part of the patient's previous therapy) or 15 mCi of yttrium labeled anti-TAC; followed by calcium trisodium Inj (Ca DTPA). Calcium-DTPA: Ca-DTPA will be administered intravenously on Days 1-3 to clear the radioactive agent from the body.""")
Results
| | chunk | begin | end | entity |
|---:|:-------------------------|--------:|------:|:---------|
| 0 | Anti-Tac | 15 | 22 | Drug |
| 1 | 10 mCi | 25 | 30 | Dosage |
| 2 | 15 mCi | 108 | 113 | Dosage |
| 3 | yttrium labeled anti-TAC | 118 | 141 | Drug |
| 4 | calcium trisodium Inj | 156 | 176 | Drug |
| 5 | Calcium-DTPA | 191 | 202 | Drug |
| 6 | Ca-DTPA | 205 | 211 | Drug |
| 7 | intravenously | 234 | 246 | Route |
| 8 | Days 1-3 | 251 | 258 | Cycleday |
Model Information
| Model Name: | ner_posology_experimental_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 3.4.1+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 1.7 GB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverter