MAHCProf. Weichung Wangs “MeDA Lab” team participated in NVIDIAs EXAM (EMR CXR AI Model)Initiative
Summary To develop an AI model that doctors trustthat generalizes to as many hospitals as possible, NVIDIAMass General Brigham embarked on an initiative called strongEXAM/strong (strongE/strongMR CstrongX/strongR strongA/strongI strongM/strongodel) the largest, most diverse federated learning initiative with 20 hospitalsresearch institutions from around the world. In just two weeks, the global collaboration achieved a model with .94 area under the curve (with an AUC goal of 1.0), resulting in excellent prediction for the level of oxygen required by incoming patients.
  Using NVIDIA Clara Federated Learning Framework, researchers at individual hospitals were able to use a chest X-ray, patient vitalslab values to train a local modelshare only a subset of model weights back with the global model in a privacy-preserving technique called federated learning. The ultimate goal of this model is to predict the likelihood that a person showing up in the emergency room will need supplemental oxygen, which can aid physicians in determining the appropriate level of care for patients, including ICU placement.
Among the 20 hospitalsresearch institutions, Most All Vista Healthcare Center (MAHC) teamed up with National Taiwan University MeDA Lab (PI: Prof. Weichung Wang)Taiwan National Health Insurance Administrationto join this global collaboration.
Keyword Multi-domain Joint Learning Artificial Intelligence COVID-19
Research Project
Research Team
More like this
Provide the latest information of AI research centers and applied industries