Description
This pipeline extracts TEST entities and maps them to their corresponding Logical Observation Identifiers Names and Codes(LOINC) codes using sbiobert_base_cased_mli sentence embeddings. It is trained with the numeric LOINC codes, without the inclusion of LOINC “Document Ontology” codes starting with the letter “L”. It also provides the official resolution of the codes within the brackets.
Predicted Entities
TEST, Test_Result
How to use
from sparknlp.pretrained import PretrainedPipeline
loinc_pipeline = PretrainedPipeline("loinc_numeric_resolver_pipeline", "en", "clinical/models")
text = """A 65-year-old woman presents to the office with generalized fatigue for the last 4 months. She used to walk 1 mile each evening but now gets tired after 1-2 blocks. She has a history of Crohn disease and hypertension for which she receives appropriate medications. She is married and lives with her husband. She eats a balanced diet that includes chicken, fish, pork, fruits, and vegetables. She rarely drinks alcohol and denies tobacco use. A physical examination is unremarkable. Laboratory studies show the following:
Hemoglobin: 9.8 g/dL
Hematocrit: 32%
Mean Corpuscular Volume: 110 μm3"""
result = loinc_pipeline.fullAnnotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val loinc_pipeline = PretrainedPipeline("loinc_numeric_resolver_pipeline", "en", "clinical/models")
val text = """A 65-year-old woman presents to the office with generalized fatigue for the last 4 months. She used to walk 1 mile each evening but now gets tired after 1-2 blocks. She has a history of Crohn disease and hypertension for which she receives appropriate medications. She is married and lives with her husband. She eats a balanced diet that includes chicken, fish, pork, fruits, and vegetables. She rarely drinks alcohol and denies tobacco use. A physical examination is unremarkable. Laboratory studies show the following:
Hemoglobin: 9.8 g/dL
Hematocrit: 32%
Mean Corpuscular Volume: 110 μm3"""
val result = loinc_pipeline.fullAnnotate(text)
Results
+-----------------------+-----+---+-------+-----------------------------------------------------------------+-----------------------------------------------------------------+-----------------------------------------------------------------+
| chunks|begin|end| code| all_codes| resolutions| all_distances|
+-----------------------+-----+---+-------+-----------------------------------------------------------------+-----------------------------------------------------------------+-----------------------------------------------------------------+
| A physical examination| 443|464|55286-9|[55286-9, 11384-5, 67668-4, 100223-7, 29545-1, 79897-5, 32427-...|[Physical examination by body areas [Physical examination by b...|[0.0704, 0.0913, 0.0908, 0.0910, 0.0961, 0.1091, 0.1114, 0.111...|
| Laboratory studies| 483|500|26436-6|[26436-6, 52482-7, 11502-2, 34075-2, 68989-3, 89756-1, 89763-7...|[Laboratory studies [Laboratory studies], Laboratory [Laborato...|[0.0000, 0.0648, 0.0748, 0.1057, 0.1051, 0.1096, 0.1128, 0.120...|
| Hemoglobin| 522|531|14775-1|[14775-1, 34663-5, 18277-4, 10346-5, 53224-2, 40546-4, 4593-0,...|[Hemoglobin [Hemoglobin], Hemoglobin S [Hemoglobin S], Hemoglo...|[0.0000, 0.0199, 0.0234, 0.0242, 0.0304, 0.0338, 0.0373, 0.044...|
| Hematocrit| 543|552|11151-8|[11151-8, 16931-8, 32354-3, 20570-8, 11153-4, 39227-4, 42908-4...|[Hematocrit [Hematocrit], Hematocrit/Hemoglobin [Hematocrit/He...|[0.0000, 0.0506, 0.0590, 0.0625, 0.0675, 0.0740, 0.1035, 0.101...|
|Mean Corpuscular Volume| 559|581|11272-2|[11272-2, 30386-7, 48706-6, 30899-9, 51641-9, 33878-0, 11666-5...|[Erythrocyte mean corpuscular volume [Erythrocyte mean corpusc...|[0.0857, 0.1056, 0.1270, 0.1213, 0.1289, 0.1257, 0.1352, 0.142...|
+-----------------------+-----+---+-------+-----------------------------------------------------------------+-----------------------------------------------------------------+-----------------------------------------------------------------+
Model Information
| Model Name: | loinc_numeric_resolver_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 5.2.1+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 2.9 GB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverterInternalModel
- MedicalNerModel
- NerConverterInternalModel
- ChunkMergeModel
- Chunk2Doc
- BertSentenceEmbeddings
- SentenceEntityResolverModel