Sentence Entity Resolver for UMLS CUI Codes (Clinical Drug)

Description

This model maps clinical entities to UMLS CUI codes. It is trained on 2021AB UMLS dataset. The complete dataset has 127 different categories, and this model is trained on the Clinical Drug category using sbiobert_base_cased_mli embeddings.

Predicted Entities

Predicts UMLS codes for Clinical Drug medical concepts

Open in Colab Download Copy S3 URI

How to use

sbiobertresolve_umls_clinical_drugs resolver model must be used with sbiobert_base_cased_mli as embeddings ner_posology as NER model. DRUG set in .setWhiteList().

...
chunk2doc = Chunk2Doc().setInputCols("ner_chunk").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_clinical_drugs","en", "clinical/models") \
.setInputCols(["ner_chunk", "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([["""She was immediately given hydrogen peroxide 30 mg to treat the infection on her leg, and has been advised Neosporin Cream for 5 days. She has a history of taking magnesium hydroxide 100mg/1ml and metformin 1000 mg."""]]).toDF("text")

results = pipeline.fit(data).transform(data)

...
val chunk2doc = Chunk2Doc().setInputCols("ner_chunk").setOutputCol("ner_chunk_doc")

val sbert_embedder = BertSentenceEmbeddings
.pretrained("sbiobert_base_cased_mli", "en","clinical/models")
.setInputCols(Array("ner_chunk_doc"))
.setOutputCol("sbert_embeddings")
.setCaseSensitive(False)

val resolver = SentenceEntityResolverModel
.pretrained("sbiobertresolve_umls_clinical_drugs", "en", "clinical/models") 
.setInputCols(Array("ner_chunk_doc", "sbert_embeddings")) 
.setOutputCol("resolution")
.setDistanceFunction("EUCLIDEAN")

val p_model = new Pipeline().setStages(Array(documentAssembler, sentenceDetector, tokenizer, stopwords, word_embeddings, clinical_ner, ner_converter, chunk2doc, sbert_embedder, resolver))

val data = Seq("She was immediately given hydrogen peroxide 30 mg to treat the infection on her leg, and has been advised Neosporin Cream for 5 days. She has a history of taking magnesium hydroxide 100mg/1ml and metformin 1000 mg.").toDF("text") 

val res = p_model.fit(data).transform(data)

import nlu
nlu.load("en.resolve.umls_clinical_drugs").predict("""She was immediately given hydrogen peroxide 30 mg to treat the infection on her leg, and has been advised Neosporin Cream for 5 days. She has a history of taking magnesium hydroxide 100mg/1ml and metformin 1000 mg.""")

Results

|    | chunk                         | code     | code_description           | all_k_code_desc                                              | all_k_codes                                                                                                                                                                             |
|---:|:------------------------------|:---------|:---------------------------|:-------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|  0 | hydrogen peroxide 30 mg       | C1126248 | hydrogen peroxide 30 mg/ml | ['C1126248', 'C0304655', 'C1605252', 'C0304656', 'C1154260'] | ['hydrogen peroxide 30 mg/ml', 'hydrogen peroxide solution 30%', 'hydrogen peroxide 30 mg/ml [proxacol]', 'hydrogen peroxide 30 mg/ml cutaneous solution', 'benzoyl peroxide 30 mg/ml'] |
|  1 | Neosporin Cream               | C0132149 | neosporin cream            | ['C0132149', 'C0358174', 'C0357999', 'C0307085', 'C0698810'] | ['neosporin cream', 'nystan cream', 'nystadermal cream', 'nupercainal cream', 'nystaform cream']                                                                                        |
|  2 | magnesium hydroxide 100mg/1ml | C1134402 | magnesium hydroxide 100 mg | ['C1134402', 'C1126785', 'C4317023', 'C4051486', 'C4047137'] | ['magnesium hydroxide 100 mg', 'magnesium hydroxide 100 mg/ml', 'magnesium sulphate 100mg/ml injection', 'magnesium sulfate 100 mg', 'magnesium sulfate 100 mg/ml']                     |
|  3 | metformin 1000 mg             | C0987664 | metformin 1000 mg          | ['C0987664', 'C2719784', 'C0978482', 'C2719786', 'C4282269'] | ['metformin 1000 mg', 'metformin hydrochloride 1000 mg', 'metformin hcl 1000mg tab', 'metformin hydrochloride 1000 mg [fortamet]', 'metformin hcl 1000mg sa tab']                       |

Model Information

Model Name:	sbiobertresolve_umls_clinical_drugs
Compatibility:	Healthcare NLP 3.2.3+
License:	Licensed
Edition:	Official
Input Labels:	[sentence_chunk_embeddings]
Output Labels:	[output]
Language:	en
Case sensitive:	false

Data Source

Trained on 2021AB UMLS dataset’s Clinical Drug category. https://www.nlm.nih.gov/research/umls/index.html

PREVIOUSSentence Entity Resolver for RxNorm (sbiobert_base_cased_mli embeddings)

NEXTSentence Entity Resolver for UMLS CUI Codes (Disease or Syndrome)