Showing contents from:

Improving Population Health: Data-Driven Approach to Identifying and Engaging Patients with High Risk of Mortality from COVID-19

Leveraging the Health Catalyst® Data Operating System (DOS™) platform and the ACO Risk Stratification Dashboard, MemorialCare developed and implemented an algorithm to identify and risk-stratify members at the highest risk of mortality from COVID-19. Care managers can visualize at-risk members and the specific factors contributing to the increased risk, allowing them to quickly prioritize member lists for outreach—improving population health and decreasing mortality.

Featured Outcomes

  • Developed and deployed the algorithm for COVID-19 risk for mortality within four days. The algorithm was applied and visualized on MemorialCare’s entire ACO population.
  • Within one week, the algorithm was expanded to include MemorialCare’s entire HMO population.
  • 66 percent of individuals in the extremely high-risk category of MemorialCare’s ACO population were engaged by care management.

Population Health Strategies Improve Diabetes Management

Thibodaux Regional Health System recognized its patients with Type 2 diabetes had hemoglobin A1C (HbA1c) levels that exceeded the evidence-based guidelines for blood glucose control and sought to improve the health of this patient population. Using a data platform and a consistent improvement methodology, Thibodaux Regional learned more about the challenges to diabetes self-management in its population. The organization was then able to improve its outreach and support for patients with diabetes.

Featured Outcomes

  • 19.1 percent relative reduction of HbA1c for patients with diabetes in the first year of the organization’s improvement efforts.
  • 14.5 percent relative reduction of HbA1c for patients with diabetes in the second year of its improvement efforts.

Machine Learning and Feature Selection for Population Health

Christiana Care Health System (CCHS) had used a machine learning model to inform population segmentation. The initial model used “black box” algorithms to predict risk that care managers didn’t have input on or understand. CCHS leaders and experts wanted an efficient model that they understood and trusted to predict 90-day inpatient admission. CCHS used a feature selection process to build the simplest model possible—and AI insight tools for selecting the best model, setting triggers for action, and explaining how the model worked.

Featured Outcomes

  • Feature selection reduced the model complexity from 236 data features to just 16 data features (7 percent of the original data set).
  • Both models, the one with 236 data features and the one with 16 data features, had an AUROC of 0.78 and an AUPR of 0.15, suggesting no degradation of predictive performance due to the lower number of features selected.
  • CCHS care managers have confidence in the predictive model, and they are successfully using the output of the machine learning tool to engage with an average of 857 distinct members each week, completing more than 2,520 tasks for those members.

Medically Integrated Wellness Program Reduces Modifiable Risk Factors

Thibodaux Regional Medical Center conducted a community health needs assessment (CHNA) as part of its vision for a healthier community. The CHNA reinforced the hospital’s identified need for a data-driven, medically integrated wellness program designed to benefit the health of the community by educating, advocating, and supporting healthy lifestyle changes to address modifiable health risks. Using a wellness analytics application, Thibodaux Regional is able to track program outcomes.

Featured Outcomes

  • 16.1 percent relative improvement between pre-and-post physical PROMIS scores.
  • 8.6 percent relative improvement between pre-and-post mental PROMIS scores.
  • 16 percent relative improvement between pre-and-post distances walked.
  • 2.1 percent relative reduction between pre-and-post weight—participants lost an average of 5.1 pounds.

Data-Driven Workflow Improves Diabetes Education Program Effectiveness

To optimize the impact of its diabetes self-management education program, Allina Health enhanced its service model, aligning resources to proactively meet patient demand, while also maintaining high-quality clinical outcomes. Utilizing analytics in the redesign process has allowed Allina Health to understand patient needs better and monitor the impact of planned changes to the program on patient outcomes.

Featured Outcomes

  • Sustained an average 13.4 percent reduction in HbA1c.
  • Completed 1,567 more visits.
  • $142,000 in new net revenue.
Loading Content...