AI-powered risk score predicts how heart failure patients will respond to loop diuretics

Researchers have used artificial intelligence to develop and validate a new risk score designed to guide the treatment of patients with acute decompensated heart failure (ADHF), sharing their findings in JACC: Heart Failure.[1]

ADHF is associated with an increased risk of hospitalization and high healthcare costs. While many patients presenting with ADHF are prescribed diuretic drugs, determining the best dose remains a challenge for healthcare providers everywhere. The perfect dose for one patient may fall short of making an impact on another.

The study’s authors added that up to 50% of all hospitalized patients have a “poor response” to initial IV diuretic therapy. Taking too long to identify this delayed response could increase that patient’s risk of a poor clinical outcome.

“Inefficient diuretic response in hospitalized patients can hinder treatment progress and increase the risk of post-discharge rehospitalization and mortality,” co-author Matthew Segar, MD, a third-year fellow with The Texas Heart Institute, said in a statement. “It’s crucial to identify individuals with low diuretic efficiency early on to tailor decongestion strategies and improve clinical outcomes.”

The group explored data from a wide variety of clinical trials and registries, using machine learning to group ADHF patients based on how they respond to diuretic therapy. Diuretic efficiency was defined as the patient’s cumulative urine output divided by the cumulative diuretic dose for 72 hours after treatment.

Tracking these responses helped the research team develop the BAN-ADHF risk score, and validation helped confirm the risk score was accurate and effective. For example, patients with the highest BAN-ADHF risk scores were linked to “significantly lower global well-being, higher natriuretic peptide levels on discharge, a longer in-hospital stay and a higher risk of in-hospital mortality.”

Segar et al. appear to just be getting started. They hope to put this new risk score to the test and evaluate its potential impact on patient care.

“Now we must take this medical knowledge and conduct a clinical study to evaluate whether implementing the BAN-ADHF score in our care protocols improves outcomes for patients hospitalized with acute decompensated heart failure,” Segar said.

Click here for the full analysis.

Michael Walter
Michael Walter, Managing Editor

Michael has more than 18 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.

Around the web

Ron Blankstein, MD, professor of radiology, Harvard Medical School, explains the use of artificial intelligence to detect heart disease in non-cardiac CT exams.

Eleven medical societies have signed on to a consensus statement aimed at standardizing imaging for suspected cardiovascular infections.

Kate Hanneman, MD, explains why many vendors and hospitals want to lower radiology's impact on the environment. "Taking steps to reduce the carbon footprint in healthcare isn’t just an opportunity," she said. "It’s also a responsibility."