Cabell Huntington Hospital is the first hospital in West Virginia to adopt InSight, a machine learning algorithm for sepsis prediction.
Sepsis, a potentially life-threatening complication, occurs when the body's response to infection causes inflammation to tissues and organs. This inflammation can trigger a cascade of changes that can damage multiple organ systems, causing them to fail. Early treatment of sepsis, usually with antibiotics and large amounts of intravenous fluids, improves chances for survival, as mortality rates increase by up to eight percent for each hour treatment is delayed.
Developed by Dascena, Inc., InSight analyzes routinely collected data in the electronic health record to forecast sepsis and provide nurses and physicians with several hours of lead time for sepsis treatment. In a recent randomized clinical trial, mortality decreased by 12.4 percentage points with InSight, a relative reduction of 58%. CHH has reduced its sepsis-related in-hospital mortality by 33.5% and its sepsis-related hospital length of stay by 17.1%.
"Because the early clinical diagnosis of sepsis can be challenging and time is so critical, we turned to Insight to assist nurses and physicians with an earlier electronic alerting system. We are already seeing a positive impact for our patients through improved rates of survival," stated Hoyt J. Burdick, MD, Senior Vice President and Chief Medical Officer of CHH.
"We can now be one step ahead in diagnosing and treating sepsis, where hours and minutes can mean the difference between life and death," added Eduardo Pino, MD, Medical Director of the Hoops Family Children's Hospital at CHH.
"Cabell Huntington Hospital has a strong reputation of delivering exceptional quality patient care," said Ritankar Das, chief executive officer of Dascena. "We are excited to work with them on combating sepsis, a life-threatening condition that kills an American nearly every two minutes."
Dascena, Inc. is a science and technology company developing algorithms as predictive biomarkers for complex conditions in inpatient and emergency settings. Our NIH-funded machine learning and clinical research has led to our suite of AlgoDiagnostics™ for predicting acute decompensation, sepsis and acute kidney injury, resulting in several peer-reviewed publications. Providers across the country use our AlgoDiagnostics on tens of thousands of patients per year to make early, accurate, and often life-saving interventions.