This week, Amazon announced the launch of a product called HealthLake, a cloud data repository and analysis tool for healthcare organizations. We’re no stranger to the amount of medical data that has been transformed into actionable, discrete data as we’ve been transforming millions of pages of these PDFs or image files into key data points for years. A surprising amount of data has been locked away in PDFs that clinicians may need to review while with a patient or that must be manually combed through and entered to become useful in an EMR or other electronic repository.
The goal of the new Amazon repository is to let healthcare organizations standardize (including automatically structuring data into the FHIR standard), tag, query, and analyze their data to reveal insights and benefits from it that wouldn’t have been apparent otherwise. With the Amazon feature set in place, companies should see benefits in the aggregation and analysis of their structured and unstructured data.
It looks like a beneficial tool, particularly for the purposes of research or population health. At Extract, we see the benefits of getting data structured which is why we like to take care of issues like unstructured data or results that need to be normalized as soon as possible in the process. Our software reads incoming unstructured documents like your data entry staff would, determining the document type, what information should be on it, and indicators of where that information should be before sending it to the downstream system of your choice.
The big benefit of taking care of your data this way on the front end is the access granted to participants along the way. Rather than have a clinician going through that same process of determining what document should have the information he or she wants and where within the document it can be found, automating the entry process leaves you with discrete results in the EMR. This leads to time saved, smoother interactions with patients, and better diagnosis and treatment results.
The great thing about having all of this aggregated data with a solution like the one Amazon announced is that it can be easily shared with vendors or other healthcare institutions. This is likely to make Amazon a big time vendor when organizations are building out their strategy to comply with certain Cures Act provisions. They already have EHR-vendor Cerner using the product.
Amazon is cognizant of the fact that healthcare institutions will use solutions like Extract’s HealthyData platform to take care of data ingestion, structuring, and normalizing, but still feels they will provide an important service with a robust machine learning-enhanced analytics platform that can rapidly uncover insights. Amazon says that their platform will bring analysis time from weeks to minutes and talks about processing scale in terms of petabytes. A petabyte, for those like me who weren’t familiar, is a million gigabytes of data.
Interoperability is a noble and intuitive goal for healthcare, so more solutions that have this aim are welcome. Check out the linked article for more information on Amazon’s offering, or reach out to us if you’d like to find out more about how we can get your data structured as your faxes and scans arrive.
About the Author: Chris Mack
Chris is a Marketing Manager at Extract with experience in product development, data analysis, and both traditional and digital marketing. Chris received his bachelor’s degree in English from Bucknell University and has an MBA from the University of Notre Dame. A passionate marketer, Chris strives to make complex ideas more accessible to those around him in a compelling way.