Amazon Comprehend Medical
Amazon Comprehend Medical is a HIPAA-eligible natural language processing (NLP) service that uses machine learning to extract health data from medical text–no machine learning experience is required.
Much of health data today is in free-form medical text like doctors’ notes, clinical trial reports, and patient health records. Manually extracting the data is a time consuming process, while automated rule-based attempts to extract the data don’t capture the full story as they fail to take context into account. As a result, the data remains unusable in large-scale analytics needed to advance the healthcare and life sciences industry and improve patient outcomes and create efficiencies.
With a simple API call to Amazon Comprehend Medical you can quickly and accurately extract information such as medical conditions, medications, dosages, tests, treatments and procedures, and protected health information while retaining the context of the information. Amazon Comprehend Medical can identify the relationships among the extracted information to help you build applications for use cases like population health analytics, clinical trial management, pharmacovigilance, and summarization. You can also use Amazon Comprehend Medical to link the extracted information to medical ontologies such as ICD10-CM or RxNorm to help you build applications for use cases like revenue cycle management (medical coding), claim validation and processing, and electronic health record creation.
Amazon Comprehend Medical is fully managed, so there are no servers to provision, and no machine learning models to build, train, or deploy. You pay only for what you use, and there are no minimum fees and no 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" ICD-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.