Predictive analytics is nothing new. Both healthcare providers and payers have used predictive models based on claims data for many years. But predictive analytics based on real-time, standardized clinical data from a statewide HIE is something very new.
HealthInfoNet, which operates Maine’s statewide health information exchange (HIE) introduced a reporting and analytics service in the first half of 2014 and has already signed up a number of its current HIE participants. These customers can use the new advanced analytic and predictive tools to study market share, clinical performance, population health and patient risk, all in real-time. The service is offered in partnership with HBI Solutions of Palo Alto, CA.
HealthInfoNet’s comprehensive clinical data repository contains records for close to all of Maine’s 1.3 million residents. It collects clinical information from 31 of the State’s 36 acute care hospitals and 326 ambulatory locations including primary and specialty care practices and long-term care facilities. This rich dataset allows for much more timely assessment of patient risk that can be leveraged for clinical treatment and care coordination before high-cost events occur. A patient’s risk score is updated in real-time each time the patient has a new clinical event at a participating site. HealthInfoNet includes a list of participants on their website. Those categorized as bi-directional submit data to the HIE.
HealthInfoNet has contracts with five organizations in Maine including two large hospitals, two smaller hospitals and the State’s Pioneer ACO. A number of others are considering signing on to the new service in 2015. St. Joseph Healthcare in Bangor was the first organization to use the new tools and is currently studying whether their use has resulted in a reduction in hospital readmissions.
“They dove right into the tools and have been a great partner to help us expand and improve our service,” said Devore Culver, HealthInfoNet’s CEO. “They took a team approach to testing the new tool, setting up super users in the hospital and the outpatient setting. And they are seeing results.”
Amber Sloat, RN and Darcy Bond, RN, care coordinators at St. Joseph Hospital, are responsible for managing patients at risk for readmission. While they’ve used a number of other protocols in the past, they are finding HealthInfoNet’s analytics tool predictions to be the most accurate. “It picks up patients we may not have thought about,” said Bond. Sloat explained that for example, “a patient may have come in with a diagnosis of anemia and we wouldn’t have followed them. But the tool flags them and then we’re able to use the health information exchange to get a fuller picture of their health and the clinical background for why they are here.” The two firmly believe they have reduced readmissions using the HealthInfoNet tools.
Jessica Taylor, RN, is a care manager in the organization’s internal medicine practice. She said the greatest barrier to managing patients at high risk for readmission is identifying them quickly. “It’s easy to capture the patients that we know need a lot of help. My goal was to reach those patients that are doing ok but might be getting into trouble and get them the help they need.” She explains that sometimes a simple early intervention, like timely home care services for someone with congestive heart failure, can prevent a hospitalization. “Nurse care managers are a limited resource and we have to use our time wisely.” She explained that using the HealthInfoNet’s analytic tool, she could focus her time on the patients most at risk.
William Wood, MD, St. Joseph Healthcare’s Chief Medical Officer admitted that in today’s healthcare market, everyone is working hard to reduce costs. He explained that historically making cost predictions based on risk meant turning to outdated claims data. He pointed out that HealthInfoNet’s new service couples 837 claims data with real-time clinical data, “which allows us to sit down and negotiate with payers, using data more current that what they’re using.” He added that as the industry adopts value based healthcare design and risk-based contracts, providers must tightly manage their patient populations and get a firm handle on their data in order to succeed. He sees this service as an important tool for him and his administrative team to plan for the future.
In addition to selling the service to HIE customers in Maine, HealthInfoNet is partnering with HBI Solutions to help HIEs outside of Maine set up similar tools for their customers. The two companies have met with a number of statewide and private HIEs in the past few months. “HealthInfoNet has been a leader in the HIE space for sometime and feel we have a lot to offer other HIE organizations as they set up similar services,” said Culver. He added that an HIE needs to provide additional value to its customers in order to be sustainable. “We believe this type of service is an important piece of the sustainability pie for the HIE and its customers.”
“Our goal is to improve the health of populations through data science,” said Eric Widen, HBI Solutions President. “I think we’re achieving that in Maine.” He said that the combination of the robust Maine HIE data set, predictive analytic applications, and the dedication of Maine providers have let to better care coordination and more appropriate resource utilization. He added, “We’re all dedicated to continuing this success.”
Visit HealthInfoNet’s Youtube page at http://youtu.be/VUk3uA5pKz4 for video interviews with St. Joseph Healthcare staff quoted in this release.
For HealthInfoNet contact:
Amy Landry, Communications Manager
Phone: 207-541-9250 ext 202
For HBI contact:
Eric Widen, President
HealthInfoNet is an independent, nonprofit organization using information technology to improve patient care quality and safety. The organization manages Maine’s statewide health information exchange and offers services to encourage health information technology adoption and support new and emerging models of care and care management. The organization maintains administrative offices in Portland, Maine. For more information, please visit www.hinfonet.org