Description
This model detects different types of species of bacteria in clinical texts. It is the version of er_bacterial_species model augmented with langtest library.
| test_type | before fail_count | after fail_count | before pass_count | after pass_count | minimum pass_rate | before pass_rate | after pass_rate |
|---|---|---|---|---|---|---|---|
| lowercase | 200 | 43 | 864 | 1021 | 90% | 81% | 96% |
| swap_entities | 66 | 56 | 264 | 268 | 75% | 80% | 83% |
| titlecase | 273 | 116 | 791 | 948 | 85% | 74% | 89% |
| uppercase | 305 | 114 | 760 | 951 | 90% | 71% | 89% |
| weighted average | 844 | 329 | 2679 | 3188 | 83% | 76.04% | 90.65% |
Predicted Entities
SPECIES
How to use
document_assembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentence_detector = SentenceDetector()\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer = Tokenizer()\
.setInputCols(["sentence"])\
.setOutputCol("token")
embeddings_clinical = WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models")\
.setInputCols(["sentence", "token"])\
.setOutputCol("embeddings")
clinical_ner = MedicalNerModel.pretrained("ner_bacterial_species_langtest", "en", "clinical/models")\
.setInputCols(["sentence", "token", "embeddings"])\
.setOutputCol("ner")
ner_converter = NerConverter()\
.setInputCols(["sentence", "token", "ner"])\
.setOutputCol("ner_chunk")
nlpPipeline = Pipeline(stages=[document_assembler, sentence_detector, tokenizer, embeddings_clinical, clinical_ner, ner_converter])
model = nlpPipeline.fit(spark.createDataFrame([[""]]).toDF("text"))
result = model.transform(spark.createDataFrame([[""""The PRP8 intein, the most widespread among fungi, occurs in important pathogens such as Histoplasma capsulatum and Paracoccidioides brasiliensis, from the Ajellomycetaceae family.""""]], ["text"]))
val document_assembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentence_detector = new SentenceDetector()
.setInputCols("document")
.setOutputCol("sentence")
val tokenizer = new Tokenizer()
.setInputCols("sentence")
.setOutputCol("token")
val embeddings_clinical = WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models")
.setInputCols(Array("sentence", "token"))
.setOutputCol("embeddings")
val ner = MedicalNerModel.pretrained("ner_bacterial_species_langtest", "en", "clinical/models")
.setInputCols(Array("sentence", "token", "embeddings"))
.setOutputCol("ner")
val ner_converter = new NerConverter()
.setInputCols(Array("sentence", "token", "ner"))
.setOutputCol("ner_chunk")
val pipeline = new Pipeline().setStages(Array(document_assembler, sentence_detector, tokenizer, embeddings_clinical, ner, ner_converter))
val data = Seq("""The PRP8 intein, the most widespread among fungi, occurs in important pathogens such as Histoplasma capsulatum and Paracoccidioides brasiliensis, from the Ajellomycetaceae family.""").toDS().toDF("text")
val result = pipeline.fit(data).transform(data)
Results
+-----------------------------+---------+
|chunk |ner_label|
+-----------------------------+---------+
|Histoplasma capsulatum |SPECIES |
|Paracoccidioides brasiliensis|SPECIES |
+-----------------------------+---------+
Model Information
| Model Name: | ner_bacterial_species_langtest |
| Compatibility: | Healthcare NLP 5.1.1+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [sentence, token, embeddings] |
| Output Labels: | [ner] |
| Language: | en |
| Size: | 14.7 MB |
Benchmarking
label precision recall f1-score support
SPECIES 0.84 0.90 0.87 521
micro-avg 0.84 0.90 0.87 521
macro-avg 0.84 0.90 0.87 521
weighted-avg 0.84 0.90 0.87 521