Apixio Inc., a San Mateo, Calif.-based data science company, announced the launch of its Iris cognitive computing platform designed to bring advanced data insights into healthcare by extracting and analyzing patient data from electronic medical records (EMRs).
The Iris platform uses Apixio's proprietary data extraction tools and machine learning algorithms to create a self-learning system that’s designed, according to the company, to give healthcare providers better access to patient data to create a more accurate care profile, thus improving the quality and efficiency of healthcare. IBM’s Watson also applies a cognitive computing platform to healthcare.
The U.S. healthcare industry produces 1.2 billion clinical care documents and most of the information need for patient care is in unstructured documents, according to HIMSS Analytics.
"Healthcare and technology are at a crossroads, and we are on the cusp of a data-rich healthcare future. If doctors and healthcare organizations know more about patients, they can make more informed decisions that will supercharge the value of care," Darren Schulte, CEO of Apixio, said in a statement. "The Iris platform unlocks the untapped 80 percent of patient data that lives in written medical records, unveiling insights that will change the delivery and consumption of healthcare as we know it."
The Iris platform’s comprehensive data integration suite was designed to handle structured and unstructured data whether it comes from electronic healthcare records (EHRs), custom systems or scanned files, the company said in a release. Its scalable data processing pipeline prepares unstructured notes and records for analysis. After processing incoming data, Apixio's advanced analytics are applied to build healthcare models of each patient. Comprised of the latest natural language processing (NLP) and machine learning technologies, the analytics engine profiles health and evaluates risk to ultimately enable better quality care decisions and performance.
Apixio designed a four-layered architecture and implemented it using open source and commercial products as well as its own patented innovations. The platform uses Intel Xeon processor-based servers and the Apache Hadoop solution stack which provides it with the scalability and throughput to process massive data volumes.
"Making sense of unstructured healthcare data is extremely challenging and requires sophisticated technology like cognitive computing to make the information useful," Bob Rogers, chief data scientist for Big Data Solutions, Intel. "By using Intel Xeon processor-based servers, Apixio's cognitive computing platform has the performance needed to do computationally intensive workloads that ultimately unlock untold value in healthcare data."