David Ledbetter, data scientist at the Children’s Hospital Los Angeles, shares how his team is using TITAN X GPUs and deep learning to help provide better recommendations of drug treatments for children in their pediatric intensive care unit.
To train their models, 13,000 patient snapshots were created from ten years of electronic health records at the hospital to understand the interactions between a patient’s vital state, heart rate, blood pressure and the treatments they were given. By understanding the most important relationships in the data, they are then able to generate the probability of survival predictions for the patients moving forward as well as physiology predictions in order to simulate augmented treatments.
David presented his research poster “Dr. TED: Deep Learning Recommendation of Treatment from Electronic Data” at the 2016 GPU Technology Conference.
Share your GPU-accelerated science with us at http://nvda.ly/Vpjxr and with the world on #ShareYourScience.
Watch more scientists and researchers share how accelerated computing is benefiting their work at http://nvda.ly/X7WpH
Share Your Science: Leveraging Deep Learning for Personalized Drug Treatment Recommendations
Apr 15, 2016
Discuss (0)

Related resources
- GTC session: Scaling Deep Learning for Drug Development with an AI Factory and MONAI (Spring 2023)
- GTC session: Fast and Scalable Training of Deep Learning Recommendation Models (Spring 2023)
- GTC session: DeepRec: Toward High-Performance Recommendation Deep Learning Framework with GPU Acceleration. (Spring 2023)
- Webinar: Bringing AI into Biomedicine
- Webinar: Kipoi: Model Zoo for Genomics
- Webinar: Reshaping Pharma: How AI, Big Data, and Technology are Revolutionizing Drug Discovery