Eyeing the transition to value-based payment models, a midwestern health system reengineered its approach to data collection and analytics to provide clinicians with more actionable information.
Executives at Sanford Health, headquartered in Sioux Falls, South Dakota, refer to this revamped approach as “prescriptive analytics,” which goes beyond predicting health outcomes. Instead, the analytics team searches for specific clinical interventions that can improve care.
Making predictive analytics actionable is an issue that healthcare providers around the country have been focusing on, as more hospital executives believe analytics can improve patient care. Experts at Brigham and Women’s Hospital and Partners HealthCare have pointed out that predictive analytics tools often fail in the clinical environment because clinicians don’t understand their value.
Getting to that point required Sanford Health, which includes 45 medical centers and 289 clinics in predominately rural locations of South Dakota and North Dakota, to streamline its approach data collection and restructure its analytics team, system executives wrote in NEJM Catalyst.
To create a single data repository, the organization folded together existing IT divisions to create a centralized analytics team, which also pulled together the disparate data sets utilized throughout the system. A new committee created a data governance structure to standardize metrics and collection methodology.
That restructuring has led to a new perspective in which analytics can identify impactful interventions. For example, a physician can do nothing to change the fact that a patient’s age increases their risk for readmission, but a missed clinic appointment might be within their control.
“Once analytics help determine those actions, we must communicate these data-driven insights to clinicians and help them incorporate the resulting changes in a way that improves care while minimizing disruption to the current patterns of practice,” Sanford Health executives wrote.