Computer Program Helps Detect Kidney Injury
January 3rd, 2018
A computer program that automatically monitors blood test results can detect acute kidney injury earlier, reducing severity and improving survival, according to new research from the University of Pittsburgh and UPMC. Acute kidney injury, which is a sudden episode of kidney failure or damage, is common in hospitalized patients and particularly prevalent in older adults and those in intensive care units. When the kidneys do not function properly, waste products build up in the blood and can affect other organs, including the brain, heart and lungs. Unfortunately, acute kidney failure is often missed by healthcare providers using standard monitoring. Failure to recognize and manage acute kidney injury can lead to permanent kidney damage or even death. In addition to the health implications, kidney problems also lead to increased healthcare costs due to the need for dialysis, longer hospital stays, and long-term care.
As part of the study, researchers released a computer program within the electronic health record system across 14 UPMC hospitals. The program monitored levels of blood creatinine, a standard measure of kidney function, over time and analyzed changes in those levels. If the levels rose too high or too fast, the program immediately sent an alert through the patient’s electronic health record informing doctors that acute kidney injury could be present.
To determine the effect of the computer program on physician behavior and patient outcomes, lead author John Kellum, MD, and his colleagues analyzed records from more than half a million patients admitted to UPMC. After the program was deployed, patients with acute kidney injury had a small decrease in hospital death rates of 0.8 percent, 0.3-day shorter length of stay, and a decrease of 2.7 percent in dialysis rates. While the changes sound small, given the annual frequency of acute kidney injury in hospitalized patients in the United States of about 12 percent – or 2.2 million people – these results would translate into more than 17,000 lives and $1.2 billion saved per year. “Acute kidney injury strikes one in eight hospitalized patients and, if unchecked, it can lead to serious complications, including the need for dialysis and even death,” said Dr. Kellum. “Our analysis shows that implementation of a clinical decision support system was associated with lower mortality, less need for dialysis and reduced length of hospital stay for patients diagnosed with acute kidney injury, among other benefits.”