The 10.5 Platform Release: New Features

The Extract Engineers have been hard at work, perfecting the new 10.5 platform release. This release is largely targeted toward fulfilling requirements for enterprise-wide document classification and distribution for healthcare organizations. It is already being deployed and configured at a large Michigan medical center. Extract looks forward to this being the first of many new installations in the new market space!


New Features Include...

Support for EMR Encounter Records

For enterprise-wide document routing, Extract will be filing documents into the EMR not just for orders (which is done for most healthcare customers), but also for encounters (office visits, phone calls, ultrasounds, etc.). In the 10.5 release, Extract has added the ability to receive and store encounter information in the Extract database and also link documents to encounters within the verification UI in the same way that lab results can be linked to orders.


Full Indexing Verification UI in Pagination Task

While 10.4 introduced pagination as an integrated workflow task, it had limited features available for verifying and editing extracted data. The 10.5 release provides the pagination UI with the full data verification feature set found in previous verification interfaces. This includes validation using logic and/or databases, business logic to automatically populate various fields, highlighting corresponding data in the image, full swiping support and undo/redo.


Database Data Storage and Statistics

Version 10.3 introduced the ability to store all found/verified data traditionally stored in VOA files in the Extract database. However, while reporting on this data was technically possible, the tools to do it efficiently did not exist—until now. The 10.5 release introduces a utility to calculate data accuracy entirely from the database. Extract can now provide on-demand accuracy data to customers without the resource intensive professional services and data capture analyst effort required in previous versions. Extract has also optimized data storage to prevent performance considerations providing reason to skip the database storage step.


Expanded Machine Learning Capabilities

The introduction of machine learning in 10.4 allowed for document classification and the identification of how to divide a single packet of pages into individual logical documents. With 10.5, Extract has expanded the machine learning capability to enable much broader use in rulesets; for the first time machine learning can be used to identify data on a document. Extract is excited to see all the ways the rule writing team is able to take advantage of this new capability.

The engineers are already focused on carefully crafting the 10.6 release and are looking forward to the next round of enhancements!

if you would like to learn more about the 10.5 software release, contact our professional services team.

About the Author: Steve Kurth

Steve Kurth is the Software Development Manager at Extract. With 15 years of experience, Steve is an expert in the design, development and testing of primarily Windows-based enterprise software. Steve is always eager to find creative software solutions for complex customer requests.