Description
This pretrained model maps SNOMED codes to corresponding MedDRA LLT (Lowest Level Term) codes.
Predicted Entities
How to use
documentAssembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("ner_chunk")
sbert_embedder = BertSentenceEmbeddings.pretrained("sbiobert_base_cased_mli", "en", "clinical/models")\
.setInputCols(["ner_chunk"])\
.setOutputCol("sbert_embeddings")\
.setCaseSensitive(False)
snomed_resolver = SentenceEntityResolverModel.pretrained("sbiobertresolve_snomed_conditions", "en", "clinical/models")\
.setInputCols(["sbert_embeddings"]) \
.setOutputCol("snomed_code")\
.setDistanceFunction("EUCLIDEAN")
resolver2chunk = Resolution2Chunk()\
.setInputCols(["snomed_code"])\
.setOutputCol("snomed2chunk")
chunkMapper = ChunkMapperModel.load('snomed_meddra_llt_mapper')\
.setInputCols(["snomed2chunk"])\
.setOutputCol("mappings")\
.setRels(["meddra_code"])
pipeline = Pipeline(stages = [
documentAssembler,
sbert_embedder,
snomed_resolver,
resolver2chunk,
chunkMapper])
data = spark.createDataFrame([["Fungal infection of lung"], ["Abdominal pain"], ["wheezing"]]).toDF("text")
result = pipeline.fit(data).transform(data)
Results
+------------------------+-----------+-------------------------------+------------------------------------------------------------+
| chunk|snomed_code| meddra_code| all_k_resolutions|
+------------------------+-----------+-------------------------------+------------------------------------------------------------+
|Fungal infection of lung| 63741006| 10037422:Pulmonary mycosis| 10037422:Pulmonary mycosis:::10085440:Lung infection fungal|
| Abdominal pain| 21522001|10000058:Abdominal crampy pains|10000058:Abdominal crampy pains:::10000081:Abdominal pain...|
| wheezing| 56018004| 10047921:Wheeze| 10047921:Wheeze:::10047924:Wheezing:::10047927:Wheezy|
+------------------------+-----------+-------------------------------+------------------------------------------------------------+
Model Information
| Model Name: | snomed_meddra_llt_mapper |
| Compatibility: | Healthcare NLP 5.4.1+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [ner_chunk] |
| Output Labels: | [mappings] |
| Language: | en |
| Size: | 136.3 KB |
References
This model is trained with the April 2024 release of SNOMED to MedDRA Map 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.