Brian Wolf, M.D.Starting with models developed at Johns Hopkins University, Wolf’s analytics team came up with risk-adjusted scores to identify “impactable” patients who have complex conditions such as cancer or severe behavioral health issues. Starting in 2008, Blue Cross & Blue Shield of Rhode Island began sharing this data and helping groups of local providers set up patient-centered medical homes following the concepts delineated by the National Committee for Quality Assurance (NCQA).“We now have 200 practitioners in five large physician groups in the patient-centered medical homes,” Wolf says. The insurer also pays to fund on-site case managers and in some cases co-located behavioral health specialists. Although they haven’t published any findings yet, Wolf says the early research suggests that the patient-centered medical homes have been able to lower rates of hospital readmission, especially among the complex patients the predictive analytics identified. “Readmission is a good measure,” Wolf says, “because it tells you that probably there wasn’t good resolution of the complaint initially.”Tufts Health PlanFor their Medicare Advantage offering, executives at Tufts Health Plan in Watertown, Mass., realize that disease management efforts are labor-intensive and expensive, because they involve more direct interaction with members. “So we want to make sure the interventions work and that we are targeting the right population in order to get the return on investment,” explains Jonathan Harding, M.D., senior medical director of senior products.“We needed to have a predictive model to identify the members to target,” he recalls. “We went to the vendor of analytic software used on the commercial side but weren’t impressed with what they had because it was not designed for the Medicare population, so we developed our own product.”Harding and his team had to work through many variables before identifying what was truly predictive. They rejected some ideas that seemed intuitive, such as the number of doctors seen in a given period, which might indicate discontinuity of care. “It didn’t turn out to predict anything,” he says. But recent hospital admission or re-admission, age above 80, or a recent fall all were good predictors. “We came up with this complex report that lists for physicians all patients at high risk of being admitted or re-admitted. And it gives the member a score.”In the fall of 2010, Tufts began sharing the data with 100 provider entities. Only a small number are NCQA-certified medical homes, but that number is increasing. For the most part, the response from physicians has been positive, Harding says. “Some were doing similar things on their own and stopped because they liked our list,” he says. “Some complain about the three- or four-month time lag. They want to get upstream of that. But we can only give them what we have. They have to supplement that with their own data that is more current.”QualChoice, a small health plan in Arkansas that had been hospital-owned but is now independent, is piloting a patient-centered medical home, and the idea is to get the primary care providers information about their patient population before they reach the stage of being catastrophic, says Richard Armstrong, M.D., the plan’s vice president of medical affairs. QualChoice is just starting to use Clinical CareAdvance, a solution from the Denver-based TriZetto Group, which allows payers to manage members who have chronic diseases by coordinating resources, automating manual processes, and identifying and stratifying at-risk members for support across the care continuum.But for any of these tools to help clinicians, Armstrong believes, the flow of data between payers and providers has to improve. “For ACOs to flourish, they need to be able to do analyses and have actionable data,” he explains. “The reason capitation didn’t work before is because we just threw the money over the wall and said good luck. The providers couldn’t analyze how they were doing.” Payers have always had better health IT infrastructure for doing analyses, he adds. The trick is to figure out how to put it to use for clinical purposes.TriZetto’s payer clients are still in the early stages of using these clinical analytics tools, says Jerry Osband, M.D., vice president of product management at The TriZetto Group Inc. “What we found in the past was that different parts of payer organizations had different business intelligence needs, so we might find one payer organization with five or six different analytics vendors,” he notes. “Now they are starting to aggregate that data in a data warehouse and reducing the number of vendors they work with to one or two.”Those payers who used to focus on individual claims are now looking across their entire membership to better define the appropriate level of financial risk to assign and to drive the right kinds of interventions, he says. “They can reach down to patients at lower levels of acuity,” Osband says, “and plan mitigations that will help prevent members from poor and expensive outcomes.”Analytics for Wellness ProgramsOne integrated health system used its own employees in a test to see whether predictive analytics could have an impact on its wellness and disease management efforts.Starting in 2007, Optima Health, the insurance arm of Sentara Healthcare in Norfolk, Va., used Risk Navigator analytics from the Orlando-based Elsevier/MEDai to support Sentara employees with customized prevention programs.Karen Bray, Ph.D., R.N., vice president of clinical care services for Optima, reports that the “Mission Health” program both improved awareness and treatment of health risks such as high blood pressure and high cholesterol and bent the cost curve.
