• Politics
  • Diversity, equity and inclusion
  • Financial Decision Making
  • Telehealth
  • Patient Experience
  • Leadership
  • Point of Care Tools
  • Product Solutions
  • Management
  • Technology
  • Healthcare Transformation
  • Data + Technology
  • Safer Hospitals
  • Business
  • Providers in Practice
  • Mergers and Acquisitions
  • AI & Data Analytics
  • Cybersecurity
  • Interoperability & EHRs
  • Medical Devices
  • Pop Health Tech
  • Precision Medicine
  • Virtual Care
  • Health equity

Risk Score Helps Predict Life Expectancy in Patients with Heart Failure


Using AI and EHR data, researchers developed a risk score that achieved an AUC of 0.88.


An artificial intelligence (AI) tool had an 88% success rate in predicting life expectancy in patients with heart failure, researchers at UC San Diego Health reported in the European Journal of Heart Failure.

Using a machine-learning algorithm, researchers developed a mortality risk score in patients with heart failure. The risk score had an area under the curve of 0.88 and was predictive across the full spectrum of risk, study authors wrote.

The results support the use of the AI to evaluate patients with heart failure and in other settings where predicting risk has been challenging, reported the authors.

“This tool gives us insight, for example, on the probability that a given patient will die from heart failure in the next three months or a year,” said Eric Adler, M.D., cardiologist and director of cardiac transplant and mechanical circulatory support at the Cardiovascular Institute at UC San Diego Health. “This is incredibly valuable. It allows us to make informed decisions based on a proven methodology and not have to look into a crystal ball.”

The machine-learning model could be used to alert patients and their families about the severity of the illness, study authors added.

Researchers at UC San Diego Health — including cardiologists, physicists and a patient who received a heart transplant due to heart failure — developed a machine-learning algorithm from de-identified electronic health records data of more than 5,800 hospitalized or ambulatory patients with heart failure at the health system.

After building the AI model, a risk score was built to determine the risk of death by identify eight variables collected for many patients with heart failure:

  • Diastolic blood pressure
  • Creatine
  • Blood urine nitrogen
  • Hemoglobin
  • White blood cell count
  • Platelets
  • Albumin
  • Red blood cell distribution

The risk score had an area under the curve of 0.88 and was validated in two separate heart failure populations with area under the curves of 0.84 and 0.81.

“The development of the risk score marks an important step forward for us,” said Barry Greenberg, M.D., professor of medicine at UC San Diego School of Medicine and director of the advanced heart failure treatment program. “Not only did we demonstrate that we could accurately predict outcomes in heart failure patients, we were able to generate the score from the patient electronic medical record data base at UC San Diego Health. We now know how to utilize this data base to address other questions that are of vital importance to our patients.”

Get the best insights in digital health directly to your inbox.


AI-Enabled ECG Accurate in Detecting A-Fib, Mayo Clinic Study Finds

AI Accurately Predicts Risk of A-Fib, Mortality from ECGs

AI in Tandem with Radiologists More Accurately Identified Breast Cancer

Related Videos
Image: Ron Southwick, Chief Healthcare Executive
George Van Antwerp, MBA
Edmondo Robinson, MD
Craig Newman
Related Content
© 2024 MJH Life Sciences

All rights reserved.