Description
This model maps clinical entities to UMLS CUI codes. It is trained on 2022AA 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
How to use
...
document_assembler = DocumentAssembler()\
.setInputCol('text')\
.setOutputCol('document')
sentence_detector = SentenceDetector()\
.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_model = MedicalNerModel.pretrained("ner_posology_greedy", "en", "clinical/models")\
.setInputCols(["sentence", "token", "embeddings"])\
.setOutputCol("posology_ner")
ner_model_converter = NerConverterInternal()\
.setInputCols(["sentence", "token", "posology_ner"])\
.setOutputCol("posology_ner_chunk")\
.setWhiteList(["DRUG"])
chunk2doc = Chunk2Doc()\
.setInputCols("posology_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 = [
document_assembler,
sentence_detector,
tokenizer,
word_embeddings,
ner_model,
ner_model_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 document_assembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentence_detector = new SentenceDetector()
.setInputCols(Array("document"))
.setOutputCol("sentence")
val tokenizer = new Tokenizer()
.setInputCols("sentence")
.setOutputCol("token")
val word_embeddings = WordEmbeddingsModel
.pretrained("embeddings_clinical", "en", "clinical/models")
.setInputCols(Array("sentence", "token"))
.setOutputCol("embeddings")
val ner_model = MedicalNerModel.pretrained("ner_posology_greedy", "en", "clinical/models")
.setInputCols(["sentence", "token", "embeddings"])
.setOutputCol("posology_ner")
val ner_model_converter = new NerConverterInternal()
.setInputCols(["sentence", "token", "posology_ner"])
.setOutputCol("posology_ner_chunk")
.setWhiteList(["DRUG"])
chunk2doc = new Chunk2Doc()
.setInputCols("posology_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 pipeline = new Pipeline().setStages(Array(
document_assembler,
sentence_detector,
tokenizer,
word_embeddings,
ner_model,
ner_model_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 = pipeline.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 4.0.0+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [sentence_embeddings] |
| Output Labels: | [name] |
| Language: | en |
| Size: | 2.5 GB |
| Case sensitive: | false |
References
Trained on 2022AA UMLS dataset’s Clinical Drug category. https://www.nlm.nih.gov/research/umls/index.html