ICD10 to UMLS Code Mapping

Description

This pretrained pipeline maps ICD10CM codes to UMLS codes without using any text data. You’ll just feed white space-delimited ICD10CM codes and it will return the corresponding UMLS codes as a list. If there is no mapping, the original code is returned with no mapping.

Predicted Entities

Live Demo Open in Colab Download Copy S3 URI

Available as Private API Endpoint

Deploy

Deploy

Deploy

How to use

from sparknlp.pretrained import PretrainedPipeline

pipeline = PretrainedPipeline("icd10cm_umls_mapping", "en", "clinical/models")

result = pipeline.fullAnnotate(['M8950', 'R822', 'R0901'])

import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

val pipeline = new PretrainedPipeline("icd10cm_umls_mapping", "en", "clinical/models")

val result = pipeline.fullAnnotate(['M8950', 'R822', 'R0901'])

import nlu
nlu.load("en.icd10cm.umls.mapping").predict("""Put your text here.""")

Results

|   | icd10cm_code | umls_code |
|--:|-------------:|----------:|
| 0 |        M8950 |  C4721411 |
| 1 |         R822 |  C0159076 |
| 2 |        R0901 |  C0004044 |

Model Information

Included Models

• DocumentAssembler
• TokenizerModel
• ChunkMapperModel