The decision support software improved early diagnosis using automated data analysis and accurate alerts sent to mobile devices.
The Health division of Wolters Kluwer, a leading global provider of information and point of care solutions for the healthcare industry, announced today that The Journal of the American Medical Informatics Association (JAMIA) has published a study by researchers Sharad Manaktala, MD, PhD, et al. detailing a significant reduction in sepsis mortality using automated surveillance and real-time analysis. The study examines how clinicians at Alabama’s Huntsville Hospital decreased sepsis-related deaths by 53% during a 10-month period using a combination of clinical change management and electronic alerting from POC Advisor™, a highly-accurate clinical decision support (CDS) software. The system’s alerts detect sepsis early and guide clinicians to deliver the appropriate treatment, resulting in a breakthrough in alert accuracy, reaching 95% sensitivity and 82% specificity during the study period.
The study, “Evaluating the Impact of a Computerized Surveillance Algorithm and Decision Support System on Sepsis Mortality,” is currently available online and will appear in the June print edition of JAMIA.
Sepsis is the deadliest condition treated in hospital critical care units, claiming approximately 750,000 lives in U.S. hospitals every year. At an estimated $20 billion annually, it is also the country’s most expensive condition to treat. The risk of death increases significantly every hour sepsis goes untreated, yet early diagnosis has long been a struggle because many other acute medical conditions cause similar signs and symptoms.
Using an automated, real-time surveillance algorithm, POC Advisor aggregates, normalizes and analyzes patient data from disparate clinical systems and delivers early sepsis alerts and treatment advice to clinicians via mobile devices and portals. Hundreds of rules built into the platform account for variables specific to individual patients, including comorbidities and medication abnormalities, thereby maximizing the accuracy of alerts and advice.
“There is no single test to identify sepsis; it requires a clinical diagnosis. Delays in diagnosis are very common, resulting in delays in treatment,” said study co-author Stephen Claypool, MD. “Prior to this study, there hasn’t been a study of an electronic system that I’m aware of that has significantly improved mortality. That’s because most systems generate many false positive alerts, so they are ignored and outcomes are not improved. In this study, we used an electronic solution that takes into account existing patient co-morbidities and labs and adjusts the analysis on a patient-specific basis.
“This system is much more accurate, with a highly specific alerting system that minimizes alert fatigue,” added Dr. Claypool, Medical Director of Clinical Software Solutions at Wolters Kluwer. “In this study, Huntsville clinicians acted promptly on the alerting advice, so they were able to more effectively identify and treat sepsis well before a patient’s condition worsened. The end result was a dramatic improvement in mortality.”
The study also incorporated change management practices focused on sepsis education and process improvement for the clinical staff. The education program ensured that the nursing staff was properly trained to respond to sepsis alerts in a timely manner using the latest evidence-based practices.
“Efforts to develop similar CDS tools oftentimes fail because clinicians simply cannot trust the accuracy of the alerts. Either the system has low sensitivity and therefore does not identify all cases of sepsis, or low specificity, which leads to too many false positives resulting in ignored alerts,” said Sean Benson, Vice President and General Manager of POC Advisor at Wolters Kluwer Clinical Software Solutions. “If a tool is going to help doctors and nurses save lives, they have to trust that it works. Most CDS systems fail to achieve sensitivity and specificity levels higher than 50%. However, at the conclusion of our study, POC Advisor achieved alert sensitivity and specificity of 95% and 82%, respectively. That is unprecedented in published literature.”
The study’s publication in JAMIA follows the release of new definitions and clinical criteria for sepsis (Sepsis-3) from the Third International Consensus Definitions Task Force earlier this year. Dr. Claypool noted that while it more accurately defines the condition, Sepsis-3 does little to address the need for improved care.
“Currently, there is no medical evidence to suggest that the Sepsis-3 criteria will detect sepsis earlier than previous methods and in fact may lead to longer delays,” he said. “The reduction in sepsis mortality at Huntsville is a result of effective early alerts that allowed clinicians to treat the patients long before they suffered life-threatening organ dysfunction.”
