Amazon Comprehend Medical
Amazon Comprehend Medical is a natural language processing service that makes it easy to use machine learning to extract relevant medical information from unstructured text. Using Amazon Comprehend Medical, you can quickly and accurately gather information, such as medical condition, medication, dosage, strength, and frequency from a variety of sources like doctors’ notes, clinical trial reports, and patient health records. Amazon Comprehend Medical can also link the detected information to medical ontologies such as ICD-10-CM or RxNorm so it can be used easily by downstream healthcare applications.
One of the important ways to improve patient care and accelerate clinical research is by understanding and analyzing the insights and relationships that are “trapped” in free-form medical text, including hospital admission notes and a patient’s medical history.
Today this is achieved by writing and maintaining a set of customized rules for natural language processing software, which are complicated to build, time-consuming to maintain, and fragile. A change to a single classification code name can impact dozens of hard-coded rules and failing to update a single one of them can result in missed or incorrect data. Machine learning can eliminate the risk with models that reliably understand the medical information in unstructured text, identify meaningful relationships, while continuously improving over-time.
Amazon Comprehend Medical uses advanced machine learning models to accurately and quickly identify medical information, such as medical conditions and medications, and determines their relationship to each other, for instance, medicine dosage and strength. Amazon Comprehend Medical can also link the detected information to medical ontologies such as ICD-10-CM or RxNorm.
You can also use the extracted medical information and their relationships to build applications for use cases like clinical decision support, revenue cycle management (medical coding), and clinical trial management. Because Amazon Comprehend Medical is HIPAA eligible and is built in to quickly identify protected health information (PHI), such as name, age, and medical record number, you can also use it to create applications that securely process, maintain, and transmit PHI.
Amazon Comprehend Medical is accessible through a simple API call, no machine learning expertise is required, no complicated rules to write, and no models to train. You only pay for what you use, and there are no minimum fees or upfront commitments.
Extract medical information quickly and accurately
Powered by state-of-the-art machine learning models, Amazon Comprehend Medical understands and identifies complex medical information quickly and more accurately. For example, Amazon Comprehend Medical can extract "methicillin-resistant Staphylococcus aureus" (often input as "MRSA") link it to the "J15.212" IDC-10-CM code, and provide context, such as whether a patient has tested positive or negative, to make the extracted term meaningful.
Protect patient information
Amazon Comprehend Medical provides a number of capabilities to help healthcare providers stay compliant and protect patient data. The service is HIPAA eligible and can identify protected health information (PHI) stored in medical record systems while adhering to the standards for General Data Protection Regulation (GDPR). Amazon Comprehend Medical allows developers to implement data privacy and security solutions by extracting and then identifying relevant patient identifiers as described in HIPAA’s Safe Harbor method of de-identification. Finally, the service does not store or save any customer data.
Lower medical document processing costs
Amazon Comprehend Medical makes it easy to automate and lower the cost of processing and coding unstructured medical text from patient records, billing, and clinical indexing. It offers 2 APIs that developers can integrate into existing workflows and applications with only a few lines of code, costing a penny or less for every 100 characters of analyzed text. You pay only for what you use, and there are no minimum fees.
How it works
With Amazon Comprehend Medical, you pay only for what you use. You are charged based on the amount of text processed on a monthly basis. Amazon Comprehend Medical provides two APIs: Medical Named Entity and Relationship Extraction (NERe) and Protected Health Information Data Extraction and Identification (PHId).
The Medical NERe API extracts entities, entity relationships, entity traits, and Protected Health Information (PHI). If you want to only identify PHI for data protection, you can request the PHId API. All API requests are measured in units of 100 characters, with one unit (100 characters) minimum charge per request.
|Feature||Price per unit|
|Medical Named Entity and Relationship Extraction (NERe) API||$0.01|
|Medical Protected Health Information Data Extraction and Identification (PHId) API||$0.0014|
|Medical ICD-10-CM Ontology Linking API||$0.0005|
|Medical RxNORM Ontology Linking API||$0.00025|
Amazon Comprehend Medical offers a free tier covering 25k units of text (2.5M characters) for the first three months when you start using the service for any of the APIs.
Perform medical cohort analysis
In oncology, it is critical that the right selection criteria are quickly discovered to recruit patients for clinical trials. Amazon Comprehend Medical understands and identifies complex medical information found in unstructured text to help make indexing and searching easier. You can use these insights to identify recruit patients to the appropriate clinical trial in a fraction of the time and cost from manual selection processes.
Support clinical decisions
Amazon Comprehend Medical extracts medical information from patient data stored in Amazon S3 and returns structured results that you can integrate into a healthcare dashboard a care support team can access. For example, a developer can build an early warning system to help identify individuals at risk of multiple sclerosis by extracting diagnosis, sign, and symptoms from more than 100,000 clinical notes using Amazon Comprehend Medical. By providing a “single lens” into the patients’ medical history, clinical teams can make decisions that are more informed.
Improve medical coding in revenue cycle management
For a hospital, the process of finding the right diagnosis in the patient notes that should be mapped to the correct code in the International Classification of Diseases (ICD) can be time-consuming and tedious. It is particularly challenging to extract diagnoses that can be represented in different ways. For example, “atrial fibrillation” is sometimes written as “AF.” Amazon Comprehend Medical can accurately identify abbreviations, misspellings, and typos in medical text. This reduces the time a medical coder must spend analyzing unstructured notes, decreases the time burden on clinical staff, and improves efficiency.