Description
This model extracts Anatomical and Observation entities from Chest Radiology Reports.
Predicted Entities
ANAT - Anatomy, OBS - Observation
Live Demo Open in Colab Copy S3 URI
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_chexpert", "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"))
results = model.transform(spark.createDataFrame([["FINAL REPORT HISTORY : Chest tube leak , to assess for pneumothorax. FINDINGS : In comparison with study of ___ , the endotracheal tube and Swan - Ganz catheter have been removed . The left chest tube remains in place and there is no evidence of pneumothorax. Mild atelectatic changes are seen at the left base."]], ["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_chexpert", "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("""FINAL REPORT HISTORY : Chest tube leak , to assess for pneumothorax. FINDINGS : In comparison with study of ___ , the endotracheal tube and Swan - Ganz catheter have been removed . The left chest tube remains in place and there is no evidence of pneumothorax. Mild atelectatic changes are seen at the left base.""").toDS.toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.med_ner.chexpert").predict("""FINAL REPORT HISTORY : Chest tube leak , to assess for pneumothorax. FINDINGS : In comparison with study of ___ , the endotracheal tube and Swan - Ganz catheter have been removed . The left chest tube remains in place and there is no evidence of pneumothorax. Mild atelectatic changes are seen at the left base.""")
Results
| | chunk | label |
|---:|:-------------------------|:--------|
| 0 | endotracheal tube | OBS |
| 1 | Swan - Ganz catheter | OBS |
| 2 | left chest | ANAT |
| 3 | tube | OBS |
| 4 | in place | OBS |
| 5 | pneumothorax | OBS |
| 6 | Mild atelectatic changes | OBS |
| 7 | left base | ANAT |
Model Information
| Model Name: | ner_chexpert |
| Compatibility: | Healthcare NLP 3.3.0+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [sentence, token, embeddings] |
| Output Labels: | [ner] |
| Language: | en |
Data Source
Trained on CheXpert dataset explain in https://arxiv.org/pdf/2106.14463.pdf.
Benchmarking
label tp fp fn prec rec f1
I-ANAT_DP 26 11 11 0.7027027 0.7027027 0.7027027
B-OBS_DP 1489 141 104 0.9134969 0.9347144 0.9239839
I-OBS_DP 16 3 54 0.84210527 0.22857143 0.35955057
B-ANAT_DP 1125 39 45 0.96649486 0.96153843 0.96401024
Macro-average 2656 194 214 0.8561999 0.70688176 0.7744088
Micro-average 2656 194 214 0.9319298 0.92543554 0.9286713