The University of California, San Francisco (UCSF) and Intel are using deep-learning techniques to power a scalable platform that will deliver clinical decision support and predictive analytics to healthcare professionals.
The platform will harness data collected for clinical care as well as big data from genomic sequencing, monitors, sensors, and wearables needed for acute clinical decision-making. A scalable "information commons" will integrate and store the massive amounts of data required for advanced data analytics and deep-learning algorithms. Intel technology will support the data management, curation, algorithm training, and testing processes. UCSF's deep-learning use cases will run in a distributed fashion on a central processing unit-based cluster.
The platform will be able to handle large datasets and scale for future use cases, including supporting convolutional neural network models, artificial networks patterned after living organisms, and large multidimensional datasets.
UCSF professor Michael Blum expects deep-learning capabilities will drive the transformation of healthcare. "Now that we have 'digitized' healthcare, we can begin utilizing the same technologies that have made the driverless car and virtual assistants possible and bring them to bear on vexing healthcare challenges such as predicting health risks, preventing hospital readmissions, analyzing complex medical images, and more," he says.
From UCSF News Center
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA