Posted On: Dec 16, 2019
Medical ontologies, such as ICD-10, make it possible to classify unstructured medical information into standardized codes that downstream healthcare applications, such as revenue cycle management tools (medical coding) can read. Amazon Comprehend Medical ICD-10-CM RXNorm Ontology Linking extracts medical condition and medication entities from medical text and links them to the relevant ICD-10-CM and RXNorm concepts respectively.
Using Amazon Comprehend Medical ICD-10-CM and RXNorm Ontology Linking APIs, developers can quickly and accurately extract codes (e.g. “R51” as the ICD-10-CM code for headache) from a variety of data sources, such as doctor’s notes or patient health records. Our deep learning approach to ontology linking provides much higher accuracy than existing rules-based systems by understanding the context each entity is found in.
Developers can use the linked ICD-10-CM and RXNorm concepts to build applications for use cases like revenue cycle management (medical coding) or population health management. ICD-10-CM and RXNorm Ontology Linking is available through simple API calls, no machine learning expertise required.