Sepsis is the deadliest and most expensive condition treated in hospital critical care units, with septic shock carrying a 34% mortality rate. Early sepsis detection is critical to saving lives and decreasing the cost of care.
In absolute terms, hospital admissions for sepsis outnumber admissions for stroke, acute myocardial infarction and trauma combined, so creating more integrated sepsis and infection-prevention programs is an ever-present challenge.
As with many hospitals, for Tift Regional Medical Center in Tifton, Georgia, the incidence of sepsis is much higher in the intensive care unit and the emergency department than in other parts of the hospital. The hospital needed to find a way to re-energize its attack on sepsis in these areas in order to improve its nurse protocols and overall bundle compliance, and reduce the human and financial costs.
“Our goal is to improve the care and outcomes of patients with sepsis,” said Dr. Cameron Nixon, chief transformation officer at Tift Regional Medical Center. “To do so, our organization sought a solution that uses natural language processing to analyze EHR patient data and unstructured text such as those in clinical notes.”
This is critical for accurate identification of patients that need attention, and to ensure the hospital’s clinical team can respond consistently with the right care to the right patient at the right time, he added.
“Wolters Kluwer created a system using a triad of change management, electronic surveillance and algorithms to detect sepsis and deliver highly sensitive and specific decision support to the point of care using a centralized monitor, mobile device or our EHR,” he explained.
“If hospitals can leverage these tools to help them focus on their sepsis improvement efforts, they’ll be able to better identify evidence-based blind spots, implement effective change management policies that garner clinician buy-in and integrate a proven surveillance monitoring system into their EHR.”
Dr. Cameron Nixon, Tift Regional Medical Center
The system, called POC Advisor, was the missing puzzle piece to help Tift Regional complete the picture – adding smarter, advanced sepsis detection into the clinical workflow, he said. By using artificial intelligence, the system accounts for more than 4,000 comorbidities, and its evidence-based algorithms dramatically reduce false positives for conditions that mimic sepsis, he said. It also detects the condition six hours earlier than EHR alerts, he noted.
MEETING THE CHALLENGE
Tift Regional Medical Center clinicians, including nurses, doctors and advanced practice providers, receive alerts with evidence-based protocols at the point of care. The POC Advisor’s dashboards also showcase CMS quality performance metrics to reduce practice variation by identifying gaps in CMS SEP-1 bundle compliance.
Additionally, the alert response dashboard provides staff with a comprehensive view of clinician actions to promote improvement, educate staff and reduce unwarranted care variations.
Nixon says it’s too early to report results at Tift Regional, but that he was sold on the results in medical literature.
“POC Advisor offers the opportunity to improve sepsis alert accuracy to 99% sensitivity and 97% specificity,” he said. “Further, a Journal of the American Medical Informatics Association study found that POC Advisor helped reduce sepsis-related mortality by 53%.
“These findings were further supported by another peer-reviewed study from the Journal of Patient Safety, which took a systematic review of the impact of automated patient monitoring systems on sepsis recognition and outcomes,” he continued.
“The meta-analysis of six studies found POC Advisor to be the only solution that significantly improves mortality, and is proven to have the highest accuracy among all electronic tools. In one study, risk of death was nearly 50% lower in patients screened using the system.”
ADVICE FOR OTHERS
Electronic tools can recognize and capture abnormal variables and activate an alert in real time.
“If hospitals can leverage these tools to help them focus on their sepsis improvement efforts, they’ll be able to better identify evidence-based blind spots – such as patients in limbo in the ED and those in the medical-surgical units – implement effective change management policies that garner clinician buy-in, and integrate a proven surveillance monitoring system into their EHR that can realize significant cost savings and, more important, save many lives,” Nixon advised.