To address out-of-hospital cardiac arrest, researchers at Osaka Metropolitan University have developed a new scoring method that uses only available data from prehospital resuscitation to accurately predict neurological outcome and allow clinicians to make more informed decisions when patients arrive at the hospital.
WHY IT MATTERS
Following patient transport, OHCA patients face adverse neurological outcomes ranging from disability to death.
Developed by researchers from Osaka Metropolitan University, the new model, R-EDByUS, is named after the five key variables it is based on – age, time to return of spontaneous circulation or time to hospital, absence of bystanders performing CPR, whether the cardiac arrest was witnessed, and initial heart rhythm.
According to research published in this month’s issue of the journal, the model accurately predicted the neurological prognosis of cardiac OHCA on admission. resuscitation.
“We hypothesized that a scoring model that included only prehospital factors in the algorithm would be easy to use and could predict prognosis at the earliest stages of the medical care process,” the researchers said.
They took advantage of the disadvantages of the American Heart Association’s algorithm:
- Arrest without witnesses.
- The initial beat cannot be shocked.
- No bystanders performed CPR.
- Time to ROSC > 30 minutes.
- Artificial respiration is being performed.
- Blood pH < 7.2, 7.
- Lactate concentration > 7 mmol/l.
- Age > 85.
- End stage renal disease.
- Cardiac causes in cardiac arrest patients.
They used OHCA data collected from 2005 to 2019 from the All-Japan Utstein Registry for 942,891 adults with presumed cardiac origin. They classified patients into two groups – those who achieved ROSC before arriving at the hospital or those who were still receiving CPR upon arrival. They then used detailed and simplified regression models to calculate the R-EDByUS score for each group.
They excluded patients under 18 years of age, patients who received CPR from bystanders, and several other factors.
In the prehospital ROSC group, 70.0% had an unfavorable neurological outcome while 55.7% died. For those who received continued CPR by EMS upon arrival at the hospital, 99.4% had an unfavorable neurological outcome and 98.2% died.
“Our prediction model helps identify patients who are likely to benefit from intensive care while reducing the unnecessary burden on patients with poor prognosis,” said Takenobu Shimada, a professor of medicine at Osaka Metropolitan University Graduate School of Medicine and lead author of the study. MSN last week.
The paper asserts that the scoring model will become a valuable tool for healthcare providers, helping to rapidly assess and manage critically ill patients.
Researchers have developed an online calculator that they say is easy to use in a clinical setting and has the potential to be validated in the future.
THE BIGGER TREND
AI patient triage has the potential to create tailored care channels, improve patient outcomes and experiences, and optimize resource utilization, but requires regulatory rigor to evaluate, according to Piotr Orzechowski, founder and CEO of Infermedica, an AI healthcare company focused on early symptom analysis and digital triage.
“AI tools are not allowed to diagnose patients,” Orzechowski said. Healthcare IT News in December in a conversation about how healthcare intersects with AI.
“Despite the significant advances in generative AI, we must remain cautious about their practical applications in healthcare,” he said.
ON THE RECORD
“Using this free calculator, the predicted probability of adverse neurological outcomes and mortality can be easily estimated by examining each variable online rather than calculating using a graph,” the researchers said.
Andrea Fox is senior editor of Healthcare IT News.
Email: [email protected]
Healthcare IT News is a publication of HIMSS Media.
The HIMSS Healthcare AI Forum is scheduled for September 5-6 in Boston. Learn more and register.
