Description
This model maps extracted medical entities to Hierarchical Condition Categories (HCC) codes using sbiobert_base_cased_mli_onnx Sentence Bert Embeddings. Trained on the ICD-10-CM 20260401 release.
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")
word_embeddings = WordEmbeddingsModel.pretrained("embeddings_clinical","en","clinical/models")\
.setInputCols(["sentence","token"])\
.setOutputCol("word_embeddings")
ner_model = MedicalNerModel.pretrained("ner_clinical","en","clinical/models")\
.setInputCols(["sentence","token","word_embeddings"])\
.setOutputCol("ner")
ner_converter = NerConverterInternal()\
.setInputCols(["sentence","token","ner"])\
.setOutputCol("ner_chunk")\
.setWhiteList(['PROBLEM'])
chunk2doc = Chunk2Doc()\
.setInputCols("ner_chunk")\
.setOutputCol("ner_chunk_doc")
embedder = BertSentenceEmbeddings.pretrained("sbiobert_base_cased_mli_onnx","en","clinical/models")\
.setInputCols(["ner_chunk_doc"])\
.setOutputCol("sbert_embeddings")\
.setCaseSensitive(False)
resolver = SentenceEntityResolverModel.pretrained("sbiobertresolve_hcc_augmented","en","clinical/models")\
.setInputCols(["sbert_embeddings"])\
.setOutputCol("hcc_code")\
.setDistanceFunction("EUCLIDEAN")
pipeline = Pipeline(stages=[
documentAssembler, sentenceDetector, tokenizer, word_embeddings,
ner_model, ner_converter, chunk2doc, embedder, resolver
])
data = spark.createDataFrame([["The patient has a history of type 2 diabetes mellitus, essential hypertension, and end stage renal disease, presented with acute appendicitis, and was noted to have chronic obstructive pulmonary disease and other heart failure on exam."]]).toDF("text")
result = pipeline.fit(data).transform(data)
documentAssembler = nlp.DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentenceDetector = nlp.SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare","en","clinical/models")\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer = nlp.Tokenizer()\
.setInputCols(["sentence"])\
.setOutputCol("token")
word_embeddings = nlp.WordEmbeddingsModel.pretrained("embeddings_clinical","en","clinical/models")\
.setInputCols(["sentence","token"])\
.setOutputCol("word_embeddings")
ner_model = medical.NerModel.pretrained("ner_clinical","en","clinical/models")\
.setInputCols(["sentence","token","word_embeddings"])\
.setOutputCol("ner")
ner_converter = medical.NerConverterInternal()\
.setInputCols(["sentence","token","ner"])\
.setOutputCol("ner_chunk")\
.setWhiteList(['PROBLEM'])
chunk2doc = nlp.Chunk2Doc()\
.setInputCols("ner_chunk")\
.setOutputCol("ner_chunk_doc")
embedder = nlp.BertSentenceEmbeddings.pretrained("sbiobert_base_cased_mli_onnx","en","clinical/models")\
.setInputCols(["ner_chunk_doc"])\
.setOutputCol("sbert_embeddings")\
.setCaseSensitive(False)
resolver = medical.SentenceEntityResolverModel.pretrained("sbiobertresolve_hcc_augmented","en","clinical/models")\
.setInputCols(["sbert_embeddings"])\
.setOutputCol("hcc_code")\
.setDistanceFunction("EUCLIDEAN")
pipeline = nlp.Pipeline(stages=[
documentAssembler, sentenceDetector, tokenizer, word_embeddings,
ner_model, ner_converter, chunk2doc, embedder, resolver
])
data = spark.createDataFrame([["The patient has a history of type 2 diabetes mellitus, essential hypertension, and end stage renal disease, presented with acute appendicitis, and was noted to have chronic obstructive pulmonary disease and other heart failure on exam."]]).toDF("text")
result = 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(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("word_embeddings")
val ner_model = MedicalNerModel
.pretrained("ner_clinical", "en", "clinical/models")
.setInputCols(Array("sentence", "token", "word_embeddings"))
.setOutputCol("ner")
val ner_converter = new NerConverterInternal()
.setInputCols(Array("sentence", "token", "ner"))
.setOutputCol("ner_chunk")
.setWhiteList(Array("PROBLEM"))
val chunk2doc = new Chunk2Doc()
.setInputCols("ner_chunk")
.setOutputCol("ner_chunk_doc")
val embedder = BertSentenceEmbeddings
.pretrained("sbiobert_base_cased_mli_onnx", "en","clinical/models")
.setInputCols(Array("ner_chunk_doc"))
.setOutputCol("sbert_embeddings")
.setCaseSensitive(false)
val resolver = SentenceEntityResolverModel
.pretrained("sbiobertresolve_hcc_augmented", "en", "clinical/models")
.setInputCols(Array("sbert_embeddings"))
.setOutputCol("hcc_code")
.setDistanceFunction("EUCLIDEAN")
val pipeline = new Pipeline().setStages(Array(
documentAssembler, sentenceDetector, tokenizer, word_embeddings,
ner_model, ner_converter, chunk2doc, embedder, resolver
))
val data = Seq("The patient has a history of type 2 diabetes mellitus, essential hypertension, and end stage renal disease, presented with acute appendicitis, and was noted to have chronic obstructive pulmonary disease and other heart failure on exam.").toDF("text")
val res = pipeline.fit(data).transform(data)
Results
| ner_chunk | entity | hcc_code | resolution | all_k_results | all_k_cosine_distances | all_k_resolutions | all_k_aux_labels |
|:--------------------------------------|:---------|-----------:|:-------------------------------------------------------------------------------------------|:-------------------|:----------------------------------|:------------------------------------------------------------------------------------|:-------------------|
| type 2 diabetes mellitus | PROBLEM | 0 | type 2 diabetes mellitus [type 2 diabetes mellitus] | 0:::19:::18:::108 | 0.0000:::0.0134:::0.0212:::0.0548 | type 2 diabetes mellitus [type 2 diabetes mellitus]:::diabetes mellitus type 2 [... | |
| essential hypertension | PROBLEM | 0 | essential hypertension [essential (primary) hypertension] | 0 | 0.0000 | essential hypertension [essential (primary) hypertension] | |
| end stage renal disease | PROBLEM | 136 | end stage renal disease [end stage renal disease] | 136:::134:::0 | 0.0000:::0.0164:::0.0367 | end stage renal disease [end stage renal disease]:::end-stage renal disease (dis... | |
| acute appendicitis | PROBLEM | 0 | acute appendicitis [acute appendicitis] | 0 | 0.0000 | acute appendicitis [acute appendicitis] | |
| chronic obstructive pulmonary disease | PROBLEM | 111 | chronic obstructive pulmonary disease [chronic obstructive pulmonary disease, unspecified] | 111:::112:::85:::0 | 0.0000:::0.0433:::0.0622:::0.0632 | chronic obstructive pulmonary disease [chronic obstructive pulmonary disease, un... | |
| other heart failure | PROBLEM | 85 | other heart failure [other heart failure] | 85:::0 | 0.0000:::0.0841 | other heart failure [other heart failure]:::other ill-defined heart diseases [ot... | |
Model Information
| Model Name: | sbiobertresolve_hcc_augmented |
| Compatibility: | Healthcare NLP 6.4.1+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [sbert_embeddings] |
| Output Labels: | [hcc_code] |
| Language: | en |
| Size: | 1.3 GB |
| Case sensitive: | false |