Communications of the ACM
Machine Learning Method Allows Hospitals to Share Patient Data Privately
Penn Medicine researchers used federated learning to train an algorithm to analyze magnetic resonance imaging scans of brain tumor patients to distinguish healthy brain tissue from cancerous regions.
Credit: Penn Medicine News
Researchers at the University of Pennsylvania's Perelman School of Medicine, in conjunction with the University of Texas MD Anderson Cancer Center, Washington University, and the Hillman Cancer Center at the University of Pittsburgh, have developed a machine learning method that can facilitate the sharing of patient data without compromising privacy.
The model uses the federated learning approach that trains an algorithm across multiple decentralized devices or servers containing local data samples without exchanging them.
The researchers found the approach to be successful in analyzing magnetic resonance imaging (MRI) scans and distinguishing between healthy brain tissue and cancerous regions.
The model could allow doctors in hospitals worldwide to input their own patient brain scans, which would support the development of a concensus model that would be clinically useful.
From Penn Medicine News
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found