Automated surveillance and real-time analysis led to a significant reduction in sepsis mortality at Alabama’s Huntsville Hospital, according to research recently published in the Journal of the American Medical Informatics Association (JAMIA).
A study by researchers Sharad Manaktala, M.D., Ph.D., and others examines how clinicians at Alabama’s Huntsville Hospital decreased sepsis-related deaths by 53 percent during a 10-month period using a combination of clinical change management and electronic alerting from POC Advisor, clinical decision support (CDS) software from Philadelphia-based Wolters Kluwer’s health division.
The system’s alerts detect sepsis early and helps guide clinicians to deliver the appropriate treatment, resulting in “a breakthrough in alert accuracy, reaching 95 percent sensitivity and 82 percent specificity during the study period,” according to officials.
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.
But by 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, according to officials.
“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, M.D. “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.”