Description
This model maps clinical/veterinary entities to MeSH (Medical Subject Headings) Unique Identifiers (UI) using bge_base_en_v1_5_onnx Sentence Embeddings.
Trained on the MeSH 2026 dataset, augmented by JSL with a veterinary-focused scope.
Live Demo Open in Colab Copy S3 URI
How to use
documentAssembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentenceDetectorDL = 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")
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_mesh_veterinary_2026","en","clinical/models")\
.setInputCols(["bge_embeddings"])\
.setOutputCol("mesh_code")\
.setDistanceFunction("EUCLIDEAN")
pipeline = Pipeline(stages=[\
documentAssembler, sentenceDetectorDL, tokenizer, word_embeddings,\
ner_model, ner_converter, chunk2doc, embedder, resolver\
])
data = spark.createDataFrame([["The dog was diagnosed with rabies and treated with vaccination; tick infestations were also noted, along with coccidiosis."]]).toDF("text")
result = pipeline.fit(data).transform(data)
documentAssembler = nlp.DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentenceDetectorDL = 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")
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_mesh_veterinary_2026","en","clinical/models")\
.setInputCols(["bge_embeddings"])\
.setOutputCol("mesh_code")\
.setDistanceFunction("EUCLIDEAN")
pipeline = nlp.Pipeline(stages=[\
documentAssembler, sentenceDetectorDL, tokenizer, word_embeddings,\
ner_model, ner_converter, chunk2doc, embedder, resolver\
])
data = spark.createDataFrame([["The dog was diagnosed with rabies and treated with vaccination; tick infestations were also noted, along with coccidiosis."]]).toDF("text")
result = pipeline.fit(data).transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentenceDetectorDL = 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")
val chunk2doc = new Chunk2Doc()
.setInputCols(Array("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_mesh_veterinary_2026", "en", "clinical/models")
.setInputCols(Array("bge_embeddings"))
.setOutputCol("mesh_code")
.setDistanceFunction("EUCLIDEAN")
val pipeline = new Pipeline().setStages(Array(
documentAssembler, sentenceDetectorDL, tokenizer, word_embeddings,
ner_model, ner_converter, chunk2doc, embedder, resolver
))
val data = Seq("The dog was diagnosed with rabies and treated with vaccination; tick infestations were also noted, along with coccidiosis.").toDF("text")
val res = pipeline.fit(data).transform(data)
Results
| ner_chunk | entity | MeSH Code | Resolution | all_k_results | all_k_cosine_distances | all_k_resolutions |
|:------------------|:----------|:------------|:------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| rabies | PROBLEM | D011818 | rabies | D011818:::D011820:::D018114:::D017992 | 0.0000:::0.0597:::0.2011:::0.2824 | rabies:::rabies virus:::rabies virus group:::parvovirus, raccoon |
| vaccination | TREATMENT | D014611 | vaccination | D014611:::D007114:::D032541:::D004673:::D007117:::D003888 | 0.0000:::0.1301:::0.1885:::0.1915:::0.1979:::0.2168 | vaccination:::immunization:::vaccination, mass:::vaccination encephalitis:::boos... |
| tick infestations | PROBLEM | D013984 | tick infestations | D013984:::D013987:::D064927:::D004478:::D000712:::D008924:::D026863:::D017282:::... | 0.0000:::0.1277:::0.1788:::0.1809:::0.1847:::0.1860:::0.2003:::0.2039:::0.2056::... | tick infestations:::ticks:::tick bites:::ectoparasitic infestations:::tick fever... |
| coccidiosis | PROBLEM | D003048 | coccidiosis | D003048:::D003047 | 0.0000:::0.1034 | coccidiosis:::coccidioidomycosis |
Model Information
| Model Name: | bgeresolve_mesh_veterinary_2026 |
| Compatibility: | Healthcare NLP 6.4.1+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [bge_embeddings] |
| Output Labels: | [mesh_code] |
| Language: | en |
| Size: | 539.7 MB |
| Case sensitive: | false |