Pipeline to Resolve ICD-10-CM Codes

Description

This pretrained pipeline maps entities with their corresponding ICD-10-CM codes. You’ll just feed your text and it will return the corresponding ICD-10-CM codes.

Predicted Entities

TREATMENT, PROBLEM,TEST

Live Demo Open in Colab Download Copy S3 URI

How to use

from sparknlp.pretrained import PretrainedPipeline

resolver_pipeline = PretrainedPipeline("icd10cm_resolver_pipeline", "en", "clinical/models")

text = """A 28-year-old female with a history of gestational diabetes mellitus diagnosed eight years and anisakiasis. Also, it was reported that fetal and neonatal hemorrhage"""

result = resolver_pipeline.fullAnnotate(text)

import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

val resolver_pipeline = new PretrainedPipeline("icd10cm_resolver_pipeline", "en", "clinical/models")

val result = resolver_pipeline.fullAnnotate("""A 28-year-old female with a history of gestational diabetes mellitus diagnosed eight years and anisakiasis. Also, it was reported that fetal and neonatal hemorrhage""")

import nlu
nlu.load("en.icd10cm_resolver.pipeline").predict("""A 28-year-old female with a history of gestational diabetes mellitus diagnosed eight years and anisakiasis. Also, it was reported that fetal and neonatal hemorrhage""")

Results

+-----------------------------+---------+------------+
|chunk                        |ner_chunk|icd10cm_code|
+-----------------------------+---------+------------+
|gestational diabetes mellitus|PROBLEM  |O24.919     |
|anisakiasis                  |PROBLEM  |B81.0       |
|fetal and neonatal hemorrhage|PROBLEM  |P545        |
+-----------------------------+---------+------------+

Model Information

Included Models

• DocumentAssembler
• SentenceDetector
• TokenizerModel
• WordEmbeddingsModel
• MedicalNerModel
• NerConverter
• ChunkMapperModel
• ChunkMapperModel
• ChunkMapperFilterer
• Chunk2Doc
• BertSentenceEmbeddings
• SentenceEntityResolverModel
• ResolverMerger