With penalties for readmissions, risk-based payment models, and new mandates to measure and improve community health, its more important than its ever been to identify high-risk patients before they show up in the ED. Bostons Steward Health Care Network, one of Medicare's 33 Pioneer ACOs, has been using a combination of claims and clinical data, sophisticated analytics, and the gut feelings of its physicians to stratify its patient population and target certain layers for special interventions. Vice President of Population Health Dominique Morgan-Solomon will share some of the organizations secrets during a HIMSS14 presentation titled Data-Driven: A Pioneer ACO Applies Data to Improve Patient Care on Monday, Feb. 24 at 11:30 a.m. -12:30 p.m.
Theres a misperception that you need to focus all your efforts and resources on the top one or five or ten percent [of high-cost patients] to manage your costs, she says. In theory it makes sense, but if you dig into population level data you find that the top five percent is things you couldnt have managed, like cancer or a car accident. Those people arent going to stay at that level from a cost perspective.
Instead, she and her team look for patients with certain characteristics that predict repeated and possibly escalating episodes of care. For example, a diabetic woman who is also depressed might neglect her daily diet, exercise and medication regimen, and miss screenings that would catch high sugar levels, foot sores, or eye problems. If shes flagged for extra interventions, she might be assigned a case manager and a social worker to keep her on track with her diabetes care plan and also treat her depression so that she can eventually take care of herself without the extra help.
Thats a lot of resources, but to prevent even one hospitalization for dehydration, the investment makes sense for us, Morgan-Solomon says
During the session, shell:
- Describe how clinical data is being tied to financial data to determine success for organizations participating in accountable care models
- Explore the tools necessary to collect, measure and report on clinical effectiveness and outcomes
- Discuss how providing access to individual metrics can help Steward's clinicians improve the quality and cost of care the organization provides
Morgan-Solomons focus will be on identifying actionable data. While much of it is in various databases, a key part is in the brains of primary care physicians.
Physicians can tell you their top ten, and theyre not necessarily the ones that the numbers will show, she says. The care management team uses concrete data to identify a physicians highest risk patients, but finalizes the intervention list based on the physicians feedback. We ask, If I can only call ten folks on your panel, which 10 should it be? And it might not be the people we have picked out.
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
Already have an account? Log In
Don't have an account? Register for Free Unlimited Access