How can we better understand what our models are telling us?
Data files are the building materials we work with every day, all day. Working with them should be effortless.
Have you ever tried to reproduce someone else’s analysis and got different results?
To help patients find high quality health information online, we developed a Deep Learning system that evaluates the quality of online health articles. The system implements the DISCERN criteria, which checks for references, balanced writing, and more.
We conclude that data from patient timelines improve 30 day readmission prediction, that a logistic regression with LASSO has equal performance to the best neural network model and that the use of administrative data result in competitive performance compared to published approaches based on richer clinical datasets.
Our collaborators at the USZ Institute of Intensive Care Medicine, specialising in recovery after neurosurgery are looking for Master students in ML for respiratory failure prediction and prevention.
Check out the call on their website For questions and for applying you can turn to Una Pale.