Description
This pretrained model maps MedDRA-HLT (High Level Term) codes to their corresponding MedDRA-PT (Preferred Term) codes. Some of the MedDRA HLT codes map to more than one MedDRA PT codes. You can find all the mapped MedDRA PT codes in the all_k_resolutions column in the metadata.
Predicted Entities
How to use
document_assembler = DocumentAssembler()\
.setInputCol('text')\
.setOutputCol('doc')
chunk_assembler = Doc2Chunk()\
.setInputCols(['doc'])\
.setOutputCol('hlt_code')
mapperModel = ChunkMapperModel.load('meddra_hlt_pt_mapper')\
.setInputCols(["hlt_code"])\
.setOutputCol("pt_mappings")\
.setRels(["pt_code"])
mapper_pipeline = Pipeline(stages=[
document_assembler,
chunk_assembler,
mapperModel
])
data = spark.createDataFrame([["10000135"], ["10017329"], ["10000332"]]).toDF("text")
mapper_model = mapper_pipeline.fit(data)
result = mapper_model.transform(data)
val document_assembler = DocumentAssembler()
.setInputCol("text")
.setOutputCol("doc")
val chunk_assembler = Doc2Chunk()
.setInputCols(Array("doc"))
.setOutputCol("hlt_code")
val mapperModel = ChunkMapperModel.load("meddra_hlt_pt_mapper")
.setInputCols(Array("hlt_code"))
.setOutputCol("pt_mappings")
.setRels(Array("pt_code"))
val mapper_pipeline = new Pipeline().setStages(Array(
document_assembler,
chunk_assembler,
mapperModel
)
val data = Seq("10000135", "10017329", "10000332").toDF("text")
val mapper_model = mapper_pipeline.fit(data)
val result = mapper_model.transform(data)
Results
+--------+-----------------------------+---------------------------------------------------------------------------------------------------------------+
|hlt_code|pt_mappings |all_k_resolutions |
+--------+-----------------------------+---------------------------------------------------------------------------------------------------------------+
|10000135|10037544:Purging |10037544:Purging:::10048636:Self-induced vomiting |
|10017329|10035736:Pneumonia tularaemia|10035736:Pneumonia tularaemia:::10045146:Tularaemia |
|10000332|10034759:Petit mal epilepsy |10034759:Petit mal epilepsy:::10083376:Generalised onset non-motor seizure:::10085031:Juvenile absence epilepsy|
+--------+-----------------------------+---------------------------------------------------------------------------------------------------------------+
Model Information
| Model Name: | meddra_hlt_pt_mapper |
| Compatibility: | Healthcare NLP 5.4.1+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [ner_chunk] |
| Output Labels: | [pt_mappings] |
| Language: | en |
| Size: | 505.0 KB |
References
This model is trained with the September 2024 (v27.1) release of MedDRA dataset.
To utilize this model, possession of a valid MedDRA license is requisite. If you possess one and wish to use this model, kindly contact us at support@johnsnowlabs.com.