Description
This model maps clinical entities to ICD-10-CM codes using bge_base_en_v1_5_onnx embeddings. It resolves entities from the following domains: Condition, Observation, Measurement, and Procedure. Trained on the ICD-10-CM 20260401 (FY2026, effective April 1, 2026) code set.
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 = BGEEmbeddings.pretrained("bge_base_en_v1_5_onnx","en")\
.setInputCols(["ner_chunk_doc"])\
.setOutputCol("bge_embeddings")\
.setCaseSensitive(False)
resolver = SentenceEntityResolverModel.pretrained("bgeresolve_icd10cm","en","clinical/models")\
.setInputCols(["bge_embeddings"])\
.setOutputCol("icd10cm_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 and essential hypertension, presented with acute appendicitis and was noted to have chronic obstructive pulmonary disease on exam. Past psychiatric history notable for major depressive disorder."]]).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.BGEEmbeddings.pretrained("bge_base_en_v1_5_onnx","en")\
.setInputCols(["ner_chunk_doc"])\
.setOutputCol("bge_embeddings")\
.setCaseSensitive(False)
resolver = medical.SentenceEntityResolverModel.pretrained("bgeresolve_icd10cm","en","clinical/models")\
.setInputCols(["bge_embeddings"])\
.setOutputCol("icd10cm_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 and essential hypertension, presented with acute appendicitis and was noted to have chronic obstructive pulmonary disease on exam. Past psychiatric history notable for major depressive disorder."]]).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 = BGEEmbeddings
.pretrained("bge_base_en_v1_5_onnx", "en")
.setInputCols(Array("ner_chunk_doc"))
.setOutputCol("bge_embeddings")
.setCaseSensitive(false)
val resolver = SentenceEntityResolverModel
.pretrained("bgeresolve_icd10cm", "en", "clinical/models")
.setInputCols(Array("bge_embeddings"))
.setOutputCol("icd10cm_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 and essential hypertension, presented with acute appendicitis and was noted to have chronic obstructive pulmonary disease on exam. Past psychiatric history notable for major depressive disorder.").toDF("text")
val res = pipeline.fit(data).transform(data)
Results
| ner_chunk | entity | icd10cm_code | resolution | all_k_results | all_k_cosine_distances | all_k_resolutions |
|:--------------------------------------|:---------|:---------------|:-------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type 2 diabetes mellitus | PROBLEM | E11 | type 2 diabetes mellitus [type 2 diabetes mellitus] | E11:::E11.9:::E10.9:::E11.65:::E11.8:::E66.9:::E11.64:::Z86.39:::E11.6:::E11.22:... | 0.0000:::0.0359:::0.1077:::0.1225:::0.1244:::0.1302:::0.1329:::0.1392:::0.1393::... | type 2 diabetes mellitus [type 2 diabetes mellitus]:::diabetes mellitus type 2 [... |
| essential hypertension | PROBLEM | I10 | essential hypertension [essential (primary) hypertension] | I10:::I27.0:::O10.0:::O10.03:::O10.02:::O10.01 | 0.0000:::0.1449:::0.1474:::0.1683:::0.1950:::0.2024 | essential hypertension [essential (primary) hypertension]:::essential pulmonary ... |
| acute appendicitis | PROBLEM | K35 | acute appendicitis [acute appendicitis] | K35:::K35.8:::K35.20:::K37:::K35.2:::K35.80:::K35.3:::K35.89:::K36:::K35.33:::R1... | 0.0000:::0.0773:::0.0809:::0.0854:::0.1106:::0.1172:::0.1225:::0.1407:::0.1551::... | acute appendicitis [acute appendicitis]:::acute appendicitis (disorder) [other a... |
| chronic obstructive pulmonary disease | PROBLEM | J44.9 | chronic obstructive pulmonary disease [chronic obstructive pulmonary disease, unspecified] | J44.9:::J98.4:::J62.8:::Z91.89:::J98.9:::J44 | 0.0000:::0.1381:::0.1396:::0.1444:::0.1465:::0.1583 | chronic obstructive pulmonary disease [chronic obstructive pulmonary disease, un... |
| major depressive disorder | PROBLEM | F32.9 | major depressive disorder [major depressive disorder, single episode, unspecified] | F32.9:::F32.2:::F41.8:::F33:::F33.9:::F33.1:::F33.0:::O99.34:::F32.1:::F33.4:::O... | 0.0000:::0.0122:::0.1628:::0.1658:::0.1665:::0.1710:::0.1828:::0.1833:::0.1947::... | major depressive disorder [major depressive disorder, single episode, unspecifie... |
Model Information
| Model Name: | bgeresolve_icd10cm |
| Compatibility: | Healthcare NLP 6.4.0+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [bge_embeddings] |
| Output Labels: | [icd10cm_code] |
| Language: | en |
| Size: | 1.3 GB |
| Case sensitive: | false |