AWS launches Comprehend Medical, applies natural language processing to medical records

The service, an extension of Comprehend, adds new terms and relationships, is HIPAA eligible.

Amazon Web Services is extending its Comprehend natural language processing service to medical records.

At AWS' re: Invent conference, the company outlined Amazon Comprehend Medical, an extension of Comprehend for medical customers.

Also: Top cloud providers 2018: How AWS, Microsoft, Google Cloud Platform, IBM Cloud, Oracle, Alibaba stack up

The importance of the service is that it is another toward applying artificial intelligence and machine learning to healthcare. The ability to automate medical record reading and x-ray and MRI analysis could save time for patients as well as physicians. Comprehend can model topics, detect language, conduct sentiment analysis and extract phrases.

Also: AI and the NHS: How artificial intelligence will change everything for patients and doctors | Amazon expands machine learning services ahead of re:Invent | Cloud computing is helping healthcare organisations to digitise paper records

comprehend-medical-overvie.png

In a blog post, AWS said it had to build a version of Comprehend to account for medical terms, anatomy, conditions, medications and various healthcare terms. For instance, AWS had to add a vocabulary for healthcare, train a new API and have code to protect protected health information. While Comprehend Medical can protect health information, the system is HIPAA eligible, but not compliant. HIPAA compliance depends on how an enterprise uses an AWS service. AWS noted:

A word of caution: Amazon Comprehend Medical may not accurately identify protected health information in all circumstances and does not meet the requirements for de-identification of protected health information under HIPAA. You are responsible for reviewing any output provided by Amazon Comprehend Medical to ensure it meets your needs.

AWS did note that Comprehend Medical is HIPAA eligible. Use cases in healthcare would range from clinical decision support, revenue cycle management, trail management and health platforms.

Nevertheless, Comprehend Medical could be handy in various use cases. The system does pick up personal identifiable information and flags it. Comprehend Medical is also designed to understand relationships between things like dosage and conditions.

Also: Cloud TV - Video Series

The model looks like this:

comprehend-medical-model.png

With results like this:

comprehend-medical-results.png

Comprehend Medical is available in the US East, US Central, US West and Europe regions.

Updated to reflect HIPAA eligible and compliant difference.

Also: Amazon, Berkshire and JPMorgan form joint venture to tackle healthcare costs

Primers:

Previous and related coverage:

What a hybrid cloud is in the 'multi-cloud era,' and why you may already have one

Now that the services used by an enterprise and provided to its customers may be hosted on servers in the public cloud or on-premises, maybe "hybrid cloud" isn't an architecture any more. While that may the case, that's not stopping some in the digital transformation business from proclaiming it a way of work unto itself.

Cloud computing: Here comes a major tipping point

Application spending has moved to the cloud fastest, but other areas of IT spending are catching up.

Related stories: