A technology company is incorporating machine learning into a new enterprise master patient index that it contends can improve patient data sharing across the care continuum by dispersed and otherwise unconnected providers.

HSBlox is launching its SmartMPI product, which uses machine learning to improve accuracy in patient identification.

SmartMPI uses machine learning to analyze and consolidate patient data from multiple systems—including disparate EHRs, medical charts, e-prescribing technologies, clinical documentation solutions and revenue cycle management platforms—to produce longitudinal patient records that can be shared by care teams.

HSBlox says the new product provides detailed analytics and a way to address these duplicates in a phased approach. It also enables for merge and unmerge capabilities that can be automated, based on configurable thresholds.

Also See: EMPI helps Colorado network better identify vulnerable residents

The lack of solutions to consistently match patients with their records with nearly perfect accuracy remains a challenge within healthcare. For a variety of factors, current methods of patient matching are believed to be only about 90 percent accurate.

Bloomberg photo

According to a study by Johns Hopkins University, preventable medical errors frequently can be linked to inaccurate patient data. In addition, approximately 33 percent of all denied claims are associated with inaccurate patient identification, which costs the average hospital $1.5 million and the U.S. healthcare system more than $6 billion annually, according to a survey from Black Book Research.

Transitions between electronic health records systems and exchanges with other siloed clinical systems also make it difficult to match patients with their records, company executives say.

“Hospitals deal with hundreds of thousands, and sometimes millions, of electronic patient records,” says Navneet Verma, director of data science for HSBlox. “In today’s healthcare climate of consolidation among physician practices—and mergers and acquisitions among health systems—many organizations are facing challenging migrations of critical patient data from one EHR to another, significantly increasing the need for effective solutions for patient matching.”

Register or login for access to this item and much more

All Health Data Management content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access