Background & Problem Summary

Heart failure is a major public health issue, and it presents a considerable burden to society, diminishing patients’ quality of life and raising healthcare costs. Organizations choose to focus on heart failure to address these impacts and because they see:

  • Significant variation in care, despite well established guidelines. Unwarranted practice variation typically signals an improvement opportunity.
  • Opportunity to affect care across the continuum. Well documented initiatives have been shown to reduce hospital admissions, lower costs, and improve quality of patient care.

Accelerator Overview

Brings together disparate data to illuminate areas for improvement—helping organizations improve heart failure care across the continuum.

The Heart Failure Analytic Accelerator supports a disciplined, data-driven approach to the evaluation and care of heart-failure patients, helping to drive and sustain significant improvement in clinical and financial outcomes. Typical implementations focus on readmission risk stratification, adherence to guideline-directed medical therapy (GDMT), and care transitions—areas where getting it right is especially meaningful to improve quality and cost.

Benefits and Features

Gain an at-a-glance, near real-time view of quality of care and its impact.

The application dashboard visualizes outcome and process metrics in an easy-to-consume, one-page summary. This allows you to see trends as they develop—and take timely action to address issues. The Risk Stratification Dashboard presents daily reports showing each patient’s risk of returning so you can provide appropriate interventions to prevent readmission.

Start faster with meaningful, scalable clinical definitions.

The cohorts, definitions, and process measures that come with the accelerator are clinically relevant, standard, and meaningful across domains, ready for customization or adoption in your organization. Instead of spending months building the cohort of heart failure patients or debating definitions of heart failure severity, your teams can quickly begin improvement work. (Note that in cases where necessary data is not available discretely, acquiring this element may be the focus of early work with the application.) What’s more, the work is scalable: you have only one source of truth to maintain as definitions change.

Drive focus on what matters most.

Outcome metrics typically include mortality, readmission rate, LOS, and cost per case. Typical process metrics include documentation of ejection fraction and compliance with care protocols related to GDMT and care transitions. The result? Your team understands the priorities and can help solve problems that stand in the way of improvement.

Access and share insights.

Detailed analytics of each bundle provide dynamic data exploration, real-time filtering, and drill-down to patient-level detail. A Comorbidities tab enriches understanding of the patient and the appropriateness of the care they receive. The application also provides export and print capability for patient list, metric performance, etc. so you can share and follow up.

Continually refine your ability to recognize risk and improve treatment.

For organizations implementing the Heart Failure Analytic Accelerator with machine learning and closed-loop capabilities, these capabilities will drive: Stratified risk based on population-specific variables and optimized care process algorithms. LOS and readmission prediction for your heart failure patients.

Use Cases

  • The executive team in a large hospital system observes that the heart-failure readmission rate has been creeping upward over the previous three quarters. What are the drivers of this disturbing trend? They use the Heart Failure Analytic Accelerator to explore performance and guide a plan to intervene.
  • The Chief Medical Officer understands that efforts to lower the LOS of heart failure patients can sometimes increase readmission rate. Would sending patients to a nurse practitioner-run heart failure clinic help lower readmissions and improve patient satisfaction? Which patients would most benefit from the clinic? As improvement efforts are implemented, the CMO and colleagues use the application to monitor these outcomes, understand the factors that affect these results, and adjust local processes and interventions for best results.
  • A guidance team is trying to identify their next area of focus for continuous improvement of their heart failure outcomes. They use the application to gauge the effectiveness of their current risk-stratification process. How accurately have they been identifying high-risk patients? What is the best-performing unit doing—and what might widespread adoption of their processes mean for the organization?

Key Measures

  • Mortality
  • Readmission rate
  • Length of Stay (LOS), readmission LOS (days between readmit and readmit discharge)
  • ER utilization
  • Observation stay
  • Cost per case
  • Discharge to home with home health or self care
  • Patient satisfaction
  • Health-related quality of life (HRQOL)
  • Follow-up appointments (timeliness, appropriateness, cancellation rates)