CPX Domains: High-Risk Patients
Are you using predictive models to risk-stratify patient populations, prioritize proactive interventions, and avoid unnecessary costs?
AMGA’s Collaborative for Performance Excellence (CPXTM) empowers medical groups and health systems to leverage the latest analytic models to inform shared decision-making for patients with chronic conditions and avert unnecessary ER visits and hospital admissions, as part of our High-Risk Patients Domain. Advocate Aurora Health’s Richard Bone, M.D., senior medical director, population health, serves as the domain advisor, offering his wealth of knowledge of the field.
CPXTM participants will receive the following measures:
- “High/Rising Risk” Patients (list of patients at high risk or rising risk for IP admission in the next 12 month period, as well as benchmark performance)
- “Leaky Bucket” – HbA1c Control
- And others
The power of data and advanced analytics, illustrated below, enables collaborative participants to:
- Leverage predictive analytics to stratify your patient population into risk categories and provide targeted interventions appropriate for each category.
- Collaborate to design and refine the ways longitudinal data and predictive analytics are used in practice to deliver more proactive, cost-effective care to patients.
Figure 1 – “Leaky Bucket” for Glycemic Control in People with Type 2 Diabetes Example
Despite concerted efforts, healthcare organizations often fail to substantially increase the proportion of patients with type 2 diabetes whose A1c is in control. Tracking patients longitudinally reveals the reason: all the work to bring some patients into control is offset by nearly as many patients slipping out of control. It’s like trying to fill up a leaky bucket!
Using the population target of A1c < 8.0 adopted for AMGA’s Diabetes: Together 2 Goal® campaign, Figure 1 shows that glycemic control, for the CPXTM organizations shown, improved just 1.85% over the last year. Many of the patients who had been out of control came into control in the last quarter, accounting for nearly 10% of the total population (9.7%). This gain was nearly offset by 7.9% who had been in control slipping out of control, resulting in the modest net improvement. As you can see on the right-hand side, this frustrating effect was very consistent across the 22 CPXTM participants shown with data available, with markedly less variability across organizations than is typically seen in performance or outcome measures.
Figure 2 – Leaky Bucket Population Comparison
Further, it’s not surprising that patients with an A1c just above or slightly below 8.0 might switch status a year later, but there are also about 5% of patients with a baseline A1c < 7.0 who slip out of control, a subset who would normally be viewed as “safe.” AMGA’s “leaky bucket” predictive model helps by identifying the patients, with an A1c in the range 6.5–6.9, who absent intervention are most likely to slip out of control a year later.
Our CPXTM dashboard allows you to engage in population comparison at your organization with a drill down by site of care, for all patients compared to the smaller population with A1c in the range of 6.5–6.9. Utilizing predictive modeling, and benchmarking your population against others in the Collaborative, empowers medical groups to focus extra attention on a critical subset of this population, and in doing so, can significantly reduce the amount of patients who fall out of the “leaky bucket.”
* Data source: Optum, AMGA’s Distinguished Data and Analytics Collaborator