New research shows that patients are 20% less likely to die of sepsis if a new artificial intelligence system catches their symptoms hours earlier than traditional methods.
The system looks at medical records and clinical notes to identify patients who are at risk of life threatening injuries. The work could cut patient mortality from one of the top causes of hospital deaths worldwide.
The first instance where artificial intelligence is implemented at the bedside is where we are seeing lives saved.
Thousands of sepsis patients will be saved each year because of this leap. The approach is being used to improve outcomes in other areas.
There is a chain reaction when there is an infectious disease. Organ damage and organ failure can be caused by inflammation. More than 100,000 people die from sepsis in the US every year.
Saria says that it's easy to miss Sepsis because it's common in other diseases. Patients have better chances of survival if it is caught quickly.
One of the most effective ways of improving outcomes is early detection and giving the right treatments in a timely manner, but historically this has been a difficult challenge due to lack of systems for accurate early identification.
The targeted real-time early warning system was developed by Saria and colleagues. The machine-learning system shows clinicians when someone is at risk for sepsis and suggests treatment protocols, such as starting antibiotics.
Critical information isn't overlooked even if staff changes or a patient moves to a different department thanks to the artificial intelligence that tracks patients from when they arrive in the hospital through discharge.
More than 4,000 clinicians from five hospitals used the artificial intelligence to treat more than half a million patients. The previous patient cases were reviewed as well.
The artificial intelligence was accurate in 40% of the cases. The accuracy of previous attempts to use electronic tools to detect sepsis was 2% to 5% of the time. 30% of people who develop sepsis die because of the current standard of care.
In the most severe sepsis cases, where an hour delay is the difference between life and death, the artificial intelligence was able to detect it six hours earlier than traditional methods.
Albert Wu is an internist and director of the center for health services and outcomes research. Most of these systems have guessed wrong more often than they've gotten it right. Confidence is undermined by false alarms.
Doctors are able to see why the tool is making specific recommendations with the system.
Saria's nephew died of sepsis and the work is very personal to her.
In my nephew's case, separation developed very quickly. He was already dead when doctors found it.
The deployment was led and managed by the company that was spun off from the University of Baltimore. The team worked with the two largest electronic health record system providers to make sure that the tool could be used at other hospitals.
Patients at risk for pressure injuries, commonly known as bed sores, and those at risk for sudden deterioration caused by bleeding, acute respiratory failure, and cardiac arrest have been identified by the team.
The approach used here is different. The diversity of the patient population, the unique ways in which doctors and nurses deliver care across different sites, and the unique characteristics of each health system allow it to be significantly more accurate.
The University of California, San Francisco, Howard County General Hospital, and Suburban Hospital are additional coauthors.
The Gordon and Betty Moore Foundation, the National Science Foundation Future of Work at the Human- technology Frontier, and the Alfred P.
The source is the university.
All Rights Reserved © 2024
