Description
This model maps clinical entities and concepts to 4 major categories of UMLS CUI codes using sbiobert_base_cased_mli Sentence Bert Embeddings. It has faster load time, with a speedup of about 6X when compared to previous versions. Also the load process now is more memory friendly meaning that the maximum memory required during load time is smaller, reducing the chances of OOM exceptions, and thus relaxing hardware requirements.
Predicted Entities
This model returns CUI (concept unique identifier) codes for 200K concepts from clinical findings.https://www.nlm.nih.gov/research/umls/index.html
Live Demo Open in Colab Copy S3 URI
How to use
documentAssembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentenceDetector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare", "en", "clinical/models") \
.setInputCols(["document"]) \
.setOutputCol("sentence")
tokenizer = Tokenizer()\
.setInputCols(["sentence"])\
.setOutputCol("token")
stopwords = StopWordsCleaner.pretrained()\
.setInputCols("token")\
.setOutputCol("cleanTokens")\
.setCaseSensitive(False)
word_embeddings = WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models")\
.setInputCols(["sentence", "cleanTokens"])\
.setOutputCol("embeddings")
clinical_ner = MedicalNerModel.pretrained("ner_clinical_large", "en", "clinical/models") \
.setInputCols(["sentence", "token", "embeddings"]) \
.setOutputCol("ner")
ner_converter = NerConverter() \
.setInputCols(["sentence", "cleanTokens", "ner"]) \
.setOutputCol("entities")
chunk2doc = Chunk2Doc()\
.setInputCols("entities")\
.setOutputCol("ner_chunk_doc")
sbert_embedder = BertSentenceEmbeddings.pretrained("sbiobert_base_cased_mli",'en','clinical/models')\
.setInputCols(["ner_chunk_doc"])\
.setOutputCol("sbert_embeddings")
resolver = SentenceEntityResolverModel.pretrained("sbiobertresolve_umls_findings","en", "clinical/models") \
.setInputCols(["sbert_embeddings"]) \
.setOutputCol("resolution")\
.setDistanceFunction("EUCLIDEAN")
pipeline = Pipeline(stages = [documentAssembler, sentenceDetector, tokenizer, stopwords, word_embeddings, clinical_ner, ner_converter, chunk2doc, sbert_embedder, resolver])
data = spark.createDataFrame([["""A 28-year-old female with a history of gestational diabetes mellitus diagnosed eight years prior to presentation and subsequent type two diabetes mellitus (T2DM), one prior episode of HTG-induced pancreatitis three years prior to presentation, associated with an acute hepatitis, and obesity with a body mass index (BMI) of 33.5 kg/m2, presented with a one-week history of polyuria, polydipsia, poor appetite, and vomiting."""]]).toDF("text")
results = pipeline.fit(data).transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentenceDetector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare", "en", "clinical/models")
.setInputCols("document")
.setOutputCol("sentence")
val tokenizer = new Tokenizer()
.setInputCols("sentence")
.setOutputCol("token")
val stopwords = StopWordsCleaner.pretrained()
.setInputCols("token")
.setOutputCol("cleanTokens")
.setCaseSensitive(False)
val word_embeddings = WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models")
.setInputCols(Array("sentence", "cleanTokens"))
.setOutputCol("embeddings")
val clinical_ner = MedicalNerModel.pretrained("ner_clinical_large", "en", "clinical/models")
.setInputCols(Array("sentence", "token", "embeddings"))
.setOutputCol("ner")
val ner_converter = new NerConverter()
.setInputCols(Array("sentence", "cleanTokens", "ner"))
.setOutputCol("entities")
val chunk2doc = new Chunk2Doc()
.setInputCols("entities")
.setOutputCol("ner_chunk_doc")
val sbert_embedder = BertSentenceEmbeddings.pretrained("sbiobert_base_cased_mli",'en','clinical/models')
.setInputCols("ner_chunk_doc")
.setOutputCol("sbert_embeddings")
val resolver = SentenceEntityResolverModel.pretrained("sbiobertresolve_umls_findings","en", "clinical/models")
.setInputCols(Array("sbert_embeddings"))
.setOutputCol("resolution")
.setDistanceFunction("EUCLIDEAN")
val pipeline = new Pipeline().setStages(Array(documentAssembler, sentenceDetector, tokenizer, stopwords, word_embeddings, clinical_ner, ner_converter, chunk2doc, sbert_embedder, resolver))
val text = """A 28-year-old female with a history of gestational diabetes mellitus diagnosed eight years prior to presentation and subsequent type two diabetes mellitus (T2DM), one prior episode of HTG-induced pancreatitis three years prior to presentation, associated with an acute hepatitis, and obesity with a body mass index (BMI) of 33.5 kg/m2, presented with a one-week history of polyuria, polydipsia, poor appetite, and vomiting."""
val data = Seq(text).toDS.toDF("text")
val results = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.resolve.umls.findings").predict("""A 28-year-old female with a history of gestational diabetes mellitus diagnosed eight years prior to presentation and subsequent type two diabetes mellitus (T2DM), one prior episode of HTG-induced pancreatitis three years prior to presentation, associated with an acute hepatitis, and obesity with a body mass index (BMI) of 33.5 kg/m2, presented with a one-week history of polyuria, polydipsia, poor appetite, and vomiting.""")
Results
| | ner_chunk | cui_code |
|---:|:--------------------------------------|:-----------|
| 0 | gestational diabetes mellitus | C2183115 |
| 1 | subsequent type two diabetes mellitus | C3532488 |
| 2 | T2DM | C3280267 |
| 3 | HTG-induced pancreatitis | C4554179 |
| 4 | an acute hepatitis | C4750596 |
| 5 | obesity | C1963185 |
| 6 | a body mass index | C0578022 |
| 7 | polyuria | C3278312 |
| 8 | polydipsia | C3278316 |
| 9 | poor appetite | C0541799 |
| 10 | vomiting | C0042963 |
Model Information
| Model Name: | sbiobertresolve_umls_findings |
| Compatibility: | Healthcare NLP 3.0.4+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [sentence_embeddings] |
| Output Labels: | [umls_code] |
| Language: | en |
| Case sensitive: | false |