HIMSS18: Machine learning system mines data to reduce costs, minimize waste

Twitter icon
Facebook icon
LinkedIn icon
e-mail icon
Google icon
 - algorithm analytics AI machine learning

On March 6 at HIMSS18 in Las Vegas, Orion Health has announced its machine learning system, Amadeus Intelligence, could improve patient care while reducing operating costs and minimizing waste.

Healthcare expenses top $3 trillion in America, with over a third of expenses including unnecessary services and excess administration. To reduce these costs, Orion’s Amadeus Intelligence combines datasets from diverse sets of data to predict financial, operational and administrative outcomes.

"More than $1 trillion in the U.S. is wasted each year on costly administration and avoidable hospital readmissions. Orion Health's Amadeus Intelligence will use machine learning models initially to predict patient costs and readmission risks, analyze clinical and financial outliers and enable accurate diagnosis coding and quality metric reporting to improve decision making at the point of care and target resources which will result in significant cost savings,” said Ian McCrae, CEO of Orion Health. "We have yet to see the true impact of machine learning on healthcare. The last decade has been focused on integrating IT systems and capturing massive amounts of information about patients and their environments, the next decade will be to connect all that data and use machine learning for daily healthcare decisions, driving improved care, operational efficiencies, and cost effectiveness.”

With readmission rates accounting for $30 billion in healthcare expenses, researchers are searching for way to advance predicative analytics capable of catching patient deterioration before a hospital visit is necessary. Using research collected from Orion Health's public private partnership, Precision Driven Health, data were applied to machine learning models to improve prediction accuracy. The prediction models were then able to calculate potential savings four times higher than current models.

"The key to making a meaningful impact on healthcare is in the accuracy of the prediction, and the ability to respond," said McCrae. "Tapping into the vast amounts of data available through many different sources—including relevant genomic, socio-economic and behavioral data, information from devices, and data based on demographics and climate—will engender better decision-making, drawing on information from entire populations to treat and manage a person's health. Today healthcare organizations need more accuracy in their predictive analytics to reduce operational costs and improve patient care and outcomes."