EHRs help identify patients at greatest risk of dying from sepsis
Drexel University researchers have developed an analytical model for detecting early warning signs of sepsis that can predict those patients at the greatest risk of dying from the life-threatening condition.
Leveraging EHR data from more than 210,000 hospital visits between 2013 and 2016, researchers have used their model to analyze the relationship between in-hospital mortality and sepsis symptoms with seven organ systems—cardiovascular, gastrointestinal, hematopoietic, metabolic, nervous, renal, and respiratory—in order to determine which organ dysfunctions resulted in deaths.
“The integration of analytics and clinical, translational research provides insight into developing smart and connected systems that support data-driven and personalized management of sepsis,” said Muge Capan, co-principal investigator of the study and an associate clinical professor at Drexel's LeBow College of Business.
“Now that we have the model in place, the idea is to take the algorithms and turn them into usable and shareable information,” added Capan.
Based on their work, researchers are looking to create a clinical decision support system to provide clinicians with real-time alerts about patients at high-risk for dying from sepsis. Currently, they are building a model that assigns different “weighted risk” to individual organ system dysfunctions that are observed simultaneously, enabling providers to enter combinations of symptoms and create a personalized picture for sepsis patients.
“Now, when a new patient walks into the hospital, we can use our math and analytic skills to match that patient’s fingerprint and really see: ‘What is that person’s individualized risk of in-hospital death?’ and ‘What is that person’s individual risk of developing septic shock?’ That is very useful, and very exciting," observed Capan.
Sepsis is a complex syndrome, caused by the body’s response to an infection, and is one of the most frequent causes of hospital deaths. Yet, there is no single confirmatory diagnostic test and the condition tends to be under-recognized by clinicians.
However, results of the Drexel study—published in the December 2018 issue of the journal Critical Care —demonstrated that impaired kidney function is one of the leading predictors of in-hospital mortality for patients with sepsis.
In the study, the highest mortality rate (17 percent) was found in patients with worsening kidney function—an increase in creatinine levels by 50 percent from baseline—with mechanical ventilation requirement (13 percent) recorded as the second highest incidents of death.
“We now have large-scale evidence that many of these organ system failures that are typically underappreciated—particularly the renal and respiratory systems—actually have the highest association with death,” said Ryan Arnold, MD, the study’s co-principal investigator and an emergency medicine doctor and faculty member at Drexel University College of Medicine.
“That means that symptoms related to these systems need to be raising a red flag for doctors,” added Arnold. “We’re saying, ‘Hey, this is the type of patient you need to be paying more attention to.’”
Surprisingly, patients with low blood pressure—a well-known symptom of sepsis—had the lowest mortality rate.
“That likely speaks more to the healthcare providers’ response to the symptom, than the low blood pressure itself actually being a protective factor,” noted Arnold. “With sepsis, patients generally don’t fall off of a cliff. Instead, it’s a day by day, gradual deterioration. Maybe someone has a small increase in creatinine today, and tomorrow it’s a little worse. Those subtle changes that don’t get detected, we found, lead to death.”