Pipeline to Detect Chemicals in Medical Texts

Description

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

Live Demo Open in Colab Download

How to use

chemicals_pipeline = PretrainedPipeline("bert_token_classifier_ner_chemicals_pipeline", "en", "clinical/models")

chemicals_pipeline.annotate("""The results have shown that the product p - choloroaniline is not a significant factor in chlorhexidine - digluconate associated erosive cystitis. A high percentage of kanamycin - colistin and povidone - iodine irrigations were associated with erosive cystitis.""")
val chemicals_pipeline = new PretrainedPipeline("bert_token_classifier_ner_chemicals_pipeline", "en", "clinical/models")

chemicals_pipeline.annotate("The results have shown that the product p - choloroaniline is not a significant factor in chlorhexidine - digluconate associated erosive cystitis. A high percentage of kanamycin - colistin and povidone - iodine irrigations were associated with erosive cystitis.")

Results

+---------------------------+---------+
|chunk                      |ner_label|
+---------------------------+---------+
|p - choloroaniline         |CHEM     |
|chlorhexidine - digluconate|CHEM     |
|kanamycin                  |CHEM     |
|colistin                   |CHEM     |
|povidone - iodine          |CHEM     |
+---------------------------+---------+

Model Information

Model Name: bert_token_classifier_ner_chemicals_pipeline
Type: pipeline
Compatibility: Spark NLP for Healthcare 3.4.1+
License: Licensed
Edition: Official
Language: en
Size: 404.3 MB

Included Models

  • DocumentAssembler
  • TokenizerModel
  • MedicalBertForTokenClassifier
  • NerConverter
  • Finisher