Predicting COVID-19-related Adverse Events using Chest X-rays and Deep Learning
There is a pressing need to identify deterioration amongst COVID-19 patients in order to avoid life-threatening adverse events. Chest radiographs are frequently collected from patients presenting with COVID-19 upon arrival to the emergency department since the disease primarily manifests as a respiratory illness. In this talk, I will discuss the AI system we developed at NYU to predict in-hospital deterioration defined as the occurrence of intubation, mortality, or ICU admission, using deep learning and routinely collected chest X-rays. Our system also offers interpretability to radiologists and can be easily deployed within existing infrastructure.
Farah Shamout is an Assistant Professor Emerging Scholar in Computer Engineering at NYU Abu Dhabi and a visiting research scholar at the NYU Center for Data Science. Her research expertise is in machine learning for healthcare, data analytics for large-scale multi-modal data, and model interpretability. Her projects focus on real-world clinical problems to inform decision-making, including diagnosis and prognosis using electronic health records and medical imaging. Previously, Farah completed her doctoral studies in Engineering Science at the University of Oxford as a Rhodes Scholar.