Washington, D.C.-based Children's National Hospital is moving forward on five artificial intelligence projects.
Children's National is collaborating on the work with Blacksburg-based Virginia Tech, with a conference planned in September at Children's National Research & Innovation Campus.
"The rapid evolution of AI technology is unlocking unprecedented possibilities to transform pediatric healthcare," said Marius George Linguraru, PhD, Connor Family Professor and endowed chair of research and innovation at Children's National, in an Aug. 26 statement. "AI's potential to offer life-changing solutions for children with rare medical conditions is immense, and it's essential that we collaborate with clinicians, AI scientists and partner organizations to tap into this potential."
The AI projects include:
1. Forecasting emergency department surges.
2. Collaboratively training a large deep-learning model without sharing patients' individual data.
3. Automatically extracting clinical variables from documents, radiology reports and pediatric ED provider notes to better predict sepsis risk.
4. Generating facial images to simulate disease traits and better detect and classify genetic syndromes.
5. Predicting how single cells respond to genetic changes in pediatric development disorders.