Federated Learning: How This ML Model Helps Healthcare CIOs?



Federated learning can bring AI data with privacy to hospitals.

Healthcare organizations in the time of the COVID-19 crisis have been forced to deploy large-scale healthtech capabilities. Since the sector deals with enormously large patient health data, it is the healthcare CIOs’ responsibility to secure them by capitalizing on advanced solutions. They must in search of unrivaled techniques and tools that can help them derive more value from data and drive revenue streams and innovation within their organizations. Ironically, today’s CIOs have the opportunity to integrate evolving technologies, and federated learning is one of them. It is a machine learning framework that lets AI algorithms to learn from data dispersed across multiple locations. 

Federated learning enables a network of participants to train algorithms collaboratively on data while keeping each stakeholder’s data within its home location. This machine learning technique can also ensure data privacy and security. Complying with HIPPA and GDPR requirements, federated learning keeps all data housed in healthcare organizations’ networks at all times. 

Federated Learning for Brain Imaging

Apart from addressing various medical issues and queries, federated learning can be helpful in brain imaging. As shown by Penn Medicine researchers, this approach is successful by being able to assess magnetic resonance imaging (MRI) scans of brain tumor patients and distinguish healthy brain tissue from cancerous areas. The health organization trained a model that can be scattered to hospitals worldwide. Doctors can then train on top of this shared model, by inputting their own patient brain scans. Subsequently, their new model will be transferred to a centralized server, and eventually be reconciled into a consensus model that has gained knowledge from each of the hospitals, and is therefore clinically useful.

Federated Learning Improves How AI Data is Managed

While federated learning works by training an algorithm across numerous decentralized edge devices, as opposed to running an analysis on data uploaded to one server, researchers believe it will be the next wave of AI. According to Rivka Colen, co-author of the Penn Medicine study and an associate professor of radiology at the University of Pittsburgh School of Medicine, federated learning will create more opportunities to use AI in healthcare. “AI will revolutionize this field, because, right now, as a radiologist, most of what we do is descriptive. With deep learning, we’re able to extract information that is hidden in this layer of digitized images, Colen said.

CIOs can use federated learning to license their organizations’ clinical data to germane researchers. This can contribute to healthcare innovation while paving ways for new revenue streams. This can also be used as operational machine learning when applied to clinical data. From a transactional perspective, federated learning can assist medical personal when interfacing with electronic health record (EHR) systems.