Although the adoption of EMRs has provided hospitals with a massive supply of medical data, this raw data alone cannot improve clinical decision making. The deluge of numbers is only as meaningful as the insights they yield. And while retrospective analysis of EMR data can help design new processes to improve patient care in the future, it does not do much good when it comes to preventing or treating infections that have already occurred, particularly sepsis, for which early intervention is critical.
"Efficient data analytics are linked to significantly reduced costs, increased business intelligence and improved clinical outcomes," Adam Klass, chief technology officer at VigiLanz, said at Becker's Hospital Review 7th Annual Meeting. These effects are particularly pertinent as the link between reimbursement and value strengthens, and clinical outcomes data becomes more closely entwined with the revenue cycle.
However, the value hospitals could potentially leverage from their EMR data largely goes unrealized. "The biggest challenges I'm seeing in hospitals is they have all of this data and don't know what to do with it," said Mr. Klass. "They don't know how to ask the interesting questions and build it into their workflows."
The key to unlocking value is deriving actionable insights from data in real time to automate processes and gain efficiencies. Systems that alert clinicians to pay attention to certain symptoms as they present and provide evidence-based, timelined rules for intervention are better positioned to stop infections before they progress or, ideally, before they even begin.
VigiLanz's Business Intelligence Suite of services enables clinicians to do just that. The BI Suite provides VigiLanz's clients with access to its extensive and scalable data warehouse, predictive models and analytics to support the improvement of care quality in real time.
"We ingest that data, which is coming in 24/7, and do something with it that's truly actionable — predictive analytics," said Mr. Klass.
Using Temporalytics, VigiLanz's analytic methodology, the company's BI Suite helps clinicians identify the optimal time to deliver care by analyzing the outcomes of varied response times to clinical issues. Temporalytics uses advanced statistical models and machine learning to analyze data related to the timing of clinicians' actions and compare it to the response targets set in the VigiLanz system. The real-time analysis predicts scenarios where a change in the optimal response time or reduction in variability around an existing best practice can improve patient care, and ultimately improve the hospital's bottom line.
VigiLanz's BI Suite uses these insights to create predictive models tailored specifically to a given hospital's patient populations. The suite's risk-scoring protocols inform clinicians through alerts before the onset of a patient safety issue. Those models are then integrated into the VigiLanz Clinical Intelligence real-time workflow as part of a continuous learning cycle to help clinicians prioritize actions, optimize response times and improve care immediately. Importantly, Temporalytics' continuous monitoring helps the system "learn" more about the patient population over time, thereby constantly supporting providers’ effectiveness.
Temporalytics has proven especially effective in the monitoring and delivering of interventions for sepsis. In 2009, sepsis was the sixth most common principal diagnosis for hospitalization in the U.S., accounting for 836,000 stays or 2.1 percent of all hospitalizations, according to the most recent national discharge data reported by the Agency for Healthcare Research and Quality.
The need to improve processes that identify patients at risk for developing sepsis and provide the earliest intervention possible is clear. However, the general model for identifying sepsis — defined as systemic inflammatory response syndrome — only indicates the onset of severe sepsis after the patient has already developed it. This is clearly not an effective means of prevention and does not position clinicians to intervene as effectively as possible.
"The standard of care by the SIRS criteria is a great example" of the need for a prospective solution because "by the time someone meets the criteria, it doesn't change their outcome," said David Goldsteen, MD, CEO and chairman of VigiLanz. "Why have we settled for that as standard?"
With Temporalytics, hospitals have access to real-time data to identify opportunities to intervene before the onset of a safety issue. "This is the real promise of big data," said Dr. Goldsteen.
Using historical hospital data obtained from the target facility, VigiLanz's BI Suite identifies specific inputs that predict which populations within the hospital are at greater risk for developing sepsis. The system then creates a response profile to sepsis identification and treatment. Using a Temporalytics, VigiLanz uses the inputs to identify patients who fit this at-risk profile in real time. A scoring system computes an initial sepsis risk score for each patient in the cohort and flags those whose risk exceeds a pre-defined threshold. The VigiLanz Clinical Intelligence service then tracks this subset of the population over time with a set of diagnostic conditional branching rules, ensuring clinicians obtain specific sepsis diagnostics, while simultaneously monitoring clinical outputs, such as vital signs and diagnostic results.
This type of actionable data that can be used at the point of care and impact patient outcomes will be critical as hospitals continue to traverse from volume- to value-based care delivery, in which outcomes have a more significant impact on reimbursement. Sepsis alone presents great opportunity for healthcare organizations to improve outcomes and lower costs. After all, sepsis was the single most expensive condition treated in hospitals in 2009, and aggregate costs for stays with a principal diagnosis of sepsis totaled nearly $15.4 billion, or 4.3 percent of all hospital costs.
"This capability to identify and intervene at the earliest signs of sepsis will make the difference between organizations that thrive and those that struggle," said Dr. Goldsteen.