Once data has been transmitted to the Apixio Platform, they are indexed using a proprietary data specification. We execute hundreds of separate data validation checks against imported datasets to ensure that we have the minimum elements required for customer projects. Processing does not occur until the data is considered satisfactory.  

The Apixio Data Coordinator shuttles files to different processing routines based upon their specific properties. Our data processing pipeline pipeline operates in a parallel computing environment for speed and scale. We can process hundreds of millions of clinical notes in just hours.

Images are processed by our optical character reader (OCR) pipeline. Signal pathway enhancements are used to ensure that very poorly scanned text is made machine readable.

The Customer Data Inventory system then tracks files during their journey from data import to insight generation. 

Our platform extracts a variety of signals from our data using various machine learning techniques. These signals can be used to answer specific questions about individuals or source data. We combine signals using ensembles to create insights, which are then bundled into configurable application workflows to support user decision making. Feedback from application users are stored in our APOMs and later used to improve and re-train our algorithms.