Detect Normalized Genes and Human Phenotypes

Description

This model can be used to detect normalized mentions of genes (go) and human phenotypes (hp) in medical text.

Predicted Entities

: GO, HP

Live Demo Open in Colab Download

How to use

...
word_embeddings = WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models")\
  .setInputCols(["sentence", "token"])\
  .setOutputCol("embeddings")
clinical_ner = MedicalNerModel.pretrained("ner_human_phenotype_go_clinical", "en", "clinical/models") \
  .setInputCols(["sentence", "token", "embeddings"]) \
  .setOutputCol("ner")
...
nlp_pipeline = Pipeline(stages=[document_assembler, sentence_detector, tokenizer, word_embeddings, clinical_ner, ner_converter])
                               
light_pipeline = LightPipeline(nlp_pipeline.fit(spark.createDataFrame([['']]).toDF("text")))

annotations = light_pipeline.fullAnnotate("Another disease that shares two of the tumor components of CT, namely GIST and tricarboxylic acid cycle is the Carney-Stratakis syndrome (CSS) or dyad.")
...
val word_embeddings = WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models")
  .setInputCols(Array("sentence", "token"))
  .setOutputCol("embeddings")
val ner = MedicalNerModel.pretrained("ner_human_phenotype_go_clinical", "en", "clinical/models")
  .setInputCols("sentence", "token", "embeddings") 
  .setOutputCol("ner")
...
val pipeline = new Pipeline().setStages(Array(document_assembler, sentence_detector, tokenizer, word_embeddings, ner, ner_converter))

val result = pipeline.fit(Seq.empty["Another disease that shares two of the tumor components of CT, namely GIST and tricarboxylic acid cycle is the Carney-Stratakis syndrome (CSS) or dyad."].toDS.toDF("text")).transform(data)

Results

+----+--------------------------+---------+-------+----------+
|    | chunk                    |   begin |   end | entity   |
+====+==========================+=========+=======+==========+
|  0 | tumor                    |      39 |    43 | HP       |
+----+--------------------------+---------+-------+----------+
|  1 | tricarboxylic acid cycle |      79 |   102 | GO       |
+----+--------------------------+---------+-------+----------+

Model Information

Model Name: ner_human_phenotype_go_clinical
Compatibility: Spark NLP for Healthcare 3.0.0+
License: Licensed
Edition: Official
Input Labels: [sentence, token, embeddings]
Output Labels: [ner]
Language: en

Benchmarking

|    | label         |    tp |   fp |   fn |     prec |      rec |       f1 |
|---:|--------------:|------:|-----:|-----:|---------:|---------:|---------:|
|  0 | B-GO          | 1530  |  129 |   57 | 0.922242 | 0.964083 | 0.942699 |
|  1 | B-HP          |  950  |  133 |  130 | 0.877193 |  0.87963 |  0.87841 |
|  2 | I-HP          |  253  |   46 |   68 | 0.846154 | 0.788162 | 0.816129 |
|  3 | I-GO          | 4550  |  344 |  154 |  0.92971 | 0.967262 | 0.948114 |
|  4 | Macro-average | 7283  |  652 |  409 | 0.893825 | 0.899784 | 0.896795 |
|  5 | Micro-average | 7283  |  652 |  409 | 0.917832 | 0.946828 | 0.932105 |