Search



Page tree

Natural Language Processing (NLP) is a linguistic technique that enables a computer program to analyze and extract meaning from human language. Clinical NLP, using SNOMED CT's concepts, descriptions, and relationships, may be applied to repositories of clinical information to search, index, selectively retrieve and analyze free text. These techniques can be used to extract SNOMED CT encoded data from free-text patient records, it can be applied to detect meaning on historical free-text data, or it can be used in real-time to support clinical data entry, populating structured fields with information extracted from free-text fields of the clinical record.

It should be noted that while clinical NLP techniques have increased in sophistication over recent years, it is not possible to guarantee full accuracy or completeness using a computer-based algorithm. Spelling errors, grammatical errors, abbreviations, unexpected synonyms, unusual vernacular (i.e. local) phrases, and hidden contextual information continue to provide challenges that human intelligence is uniquely equipped to handle. Also, most advances have been focused on the English Language and most algorithms are still being ported or trained to work with other languages.

The sections below describe some of the product-ready tools that can be incorporated into data recording and analytics workflows.

Amazon Comprehend Medical

A web service that detects clinical entities in free text, encoded with SNOMED CT.

https://aws.amazon.com/comprehend/medical/

Clinithink

Provides Clinical Natural Language tools that encode information with SNOMED CT from free-text data entries.

https://www.clinithink.com/

Google Healthcare Natural Language AI

A Clinical NLP service based on Google AI capabilities.

https://cloud.google.com/healthcare-api/docs/how-tos/nlp

MedCAT (Open Source)

MedCAT (Medical Concept Annotation Tool) is part of the CogStack application framework. MedCAT can be used to extract information from Electronic Health Records (EHRs) and link it to biomedical ontologies like SNOMED-CT and UMLS.

https://github.com/CogStack/CogStack-Pipeline

  • No labels

Feedback