Description
This model detects the assertion status of entities related to oncology (including diagnoses, therapies and tests).
Predicted Entities
Absent, Family, Hypothetical, Past, Possible, Present
Live Demo Open in Colab Copy S3 URI
How to use
document_assembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentence_detector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare","en","clinical/models")\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer = Tokenizer() \
.setInputCols(["sentence"]) \
.setOutputCol("token")
word_embeddings = WordEmbeddingsModel().pretrained("embeddings_clinical", "en", "clinical/models")\
.setInputCols(["sentence", "token"]) \
.setOutputCol("embeddings")
ner = MedicalNerModel.pretrained("ner_oncology_wip", "en", "clinical/models") \
.setInputCols(["sentence", "token", "embeddings"]) \
.setOutputCol("ner")
ner_converter = NerConverter() \
.setInputCols(["sentence", "token", "ner"]) \
.setOutputCol("ner_chunk")\
.setWhiteList(["Cancer_Dx", "Tumor_Finding", "Cancer_Surgery", "Chemotherapy", "Pathology_Test", "Imaging_Test"])
assertion = AssertionDLModel.pretrained("assertion_oncology_wip", "en", "clinical/models") \
.setInputCols(["sentence", "ner_chunk", "embeddings"]) \
.setOutputCol("assertion")
pipeline = Pipeline(stages=[document_assembler,
sentence_detector,
tokenizer,
word_embeddings,
ner,
ner_converter,
assertion])
data = spark.createDataFrame([["The patient is suspected to have breast cancer. Family history is positive for other cancers. The result of the biopsy was positive."]]).toDF("text")
result = pipeline.fit(data).transform(data)
val document_assembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentence_detector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare","en","clinical/models")
.setInputCols(Array("document"))
.setOutputCol("sentence")
val tokenizer = new Tokenizer()
.setInputCols(Array("sentence"))
.setOutputCol("token")
val word_embeddings = WordEmbeddingsModel().pretrained("embeddings_clinical", "en", "clinical/models")
.setInputCols(Array("sentence", "token"))
.setOutputCol("embeddings")
val ner = MedicalNerModel.pretrained("ner_oncology_wip", "en", "clinical/models")
.setInputCols(Array("sentence", "token", "embeddings"))
.setOutputCol("ner")
val ner_converter = new NerConverter()
.setInputCols(Array("sentence", "token", "ner"))
.setOutputCol("ner_chunk")
.setWhiteList(Array("Cancer_Dx", "Tumor_Finding", "Cancer_Surgery", "Chemotherapy", "Pathology_Test", "Imaging_Test"))
val clinical_assertion = AssertionDLModel.pretrained("assertion_oncology_wip","en","clinical/models")
.setInputCols(Array("sentence","ner_chunk","embeddings"))
.setOutputCol("assertion")
val pipeline = new Pipeline().setStages(Array(document_assembler,
sentence_detector,
tokenizer,
word_embeddings,
ner,
ner_converter,
assertion))
val data = Seq("""The patient is suspected to have breast cancer. Family history is positive for other cancers. The result of the biopsy was positive.""").toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.assert.oncology_wip").predict("""The patient is suspected to have breast cancer. Family history is positive for other cancers. The result of the biopsy was positive.""")
Results
| chunk | ner_label | assertion |
|:--------------|:---------------|:------------|
| breast cancer | Cancer_Dx | Possible |
| cancers | Cancer_Dx | Family |
| biopsy | Pathology_Test | Past |
Model Information
| Model Name: | assertion_oncology_wip |
| Compatibility: | Healthcare NLP 4.1.0+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [document, chunk, embeddings] |
| Output Labels: | [assertion_pred] |
| Language: | en |
| Size: | 1.4 MB |
References
In-house annotated oncology case reports.
Benchmarking
label precision recall f1-score support
Absent 0.81 0.77 0.79 264.0
Family 0.78 0.82 0.80 34.0
Hypothetical 0.67 0.61 0.64 182.0
Past 0.91 0.93 0.92 1583.0
Possible 0.59 0.59 0.59 51.0
Present 0.89 0.89 0.89 1645.0
macro-avg 0.77 0.77 0.77 3759.0
weighted-avg 0.88 0.88 0.88 3759.0