Health IT

Lumiata harnesses AI for predictive analytics to make big data analysis manageable

Lumiata’s Risk Matrix is designed to offer predictions for 20 chronic condition patient populations, such as diabetes, chronic kidney disease and congestive heart failure.

lumiata image

A few years after the company’s launch, some fundraising and proof-of-concept pilots with insurers, Lumiata launched its Risk Matrix platform aimed at health plans and the health systems they work with to assess the future health of individuals with or at risk for chronic diseases. The product enlists artificial intelligence to help physicians make better use of the data they are inundated with and meet some of the goals of value-based care.

The health IT business stated in a news release that the product is designed to offer predictions for 20 chronic conditions, such as diabetes, chronic kidney disease and congestive heart failure. The idea is to help insurers allocate resources more effectively. For providers it could mean more efficient patient triage and discharge, and better prescriptive information around symptoms, medications, risk factors and diagnoses. But for payers, it can produce insights on the medical and financial risks associated with their members.

The platform collects data from claims forms, electronic health records and lab results, using the Fast Healthcare Interoperability Resources, or FHIR, standard. The Risk Matrix deep learning model generates insights for each patient. The company claims the platform can process more than 1 million claims in less than three hours.

Although most of its customers are health plans, it is also working with accountable health organizations and other health IT vendors.

In a phone interview with Tony Jones, Lumiata’s chief commercial officer, he said the company’s approach offers a logical solution for physicians who are being flooded with data but have less and less time to digest it.

Jones observed that when payers have an unexpectedly higher than normal medical-loss ratio, such as a spike in patient complications from diabetes or another chronic condition, that’s when they tend to seek out Lumiata.

He acknowledged that there are lots of companies doing predictive modeling, and included companies such as Verisk Health, which rebranded as Verscend Technologies last month and Optum Health, among its competition. But he noted that generally, many companies in the predictive analytics space fail to deliver the level of precision that earns the trust of physicians.

“Physicians using older technologies and approaches without AI simply cannot do it at a fast enough volume to be effective,” said Jones. “But if you’re asking doctors to ask patients to change their behavior, you want to ensure that those conversations are necessary. You want to be right.”

Photo: BigStock Photo