Technologies used: R, Bash
In the field of digital health, there has been a growing interest in developing AI-
based models capable of incorporating dynamic mechanical ventilation (MV) data to predict various clinical
outcomes such as successful weaning in intubated patients. However to the best of our knowledge, no study
to date has investigated the use of real-time MV data to predict survival outcomes in COVID-19 ARDS patients.
We seek to develop a model capable of learning temporal patterns from combinations of dynamic
MV-derived features, e.g., tidal volume, plateau pressure, respiratory compliance,
oxygenation, etc., to identify CARDS patients at the highest risk of mortality in real-time.
This work can help assist clinicians in identifying which patients are to be prioritized in a
fast-paced intensive-care setting. This project is an MTERMS lab project.
Code
