Geisinger AI tool increases cardiac death risk prediction accuracy by 13%

Danville, Pa.-based Geisinger researchers developed a computer algorithm that scans cardiac imaging to predict mortality within a year, according to a recent study published in Nature Biomedical Engineering.

For the study, the researchers used computational hardware to train the machine learning model on 812,278 echocardiogram videos taken from 34,362 Geisinger patients over the last decade. The researchers then compared the results of the model to cardiologists' predictions based on multiple surveys.

When assisted by the algorithm, cardiologists' prediction accuracy improved by 13 percent, a subsequent survey found.

"Our goal is to develop computer algorithms to improve patient care," Alvaro Ulloa Cerna, PhD, study author and senior data scientist Geisinger, said in the Feb. 8 news release. "In this case, we're excited that our algorithm was able to help cardiologists improve their predictions about patients, since decisions about treatment and interventions are based on these types of clinical predictions."

More articles on artificial intelligence:
UPMC develops AI tool to predict mortality for patients facing hospital transfer
How Amazon algorithms are spreading vaccine misinformation
Google partners with medtech company to integrate AI into cervical cancer diagnostics

 

© Copyright ASC COMMUNICATIONS 2021. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Featured Whitepapers

Featured Webinars