Marijn van Wingerden
Predicting 120-day hospital readmission using medical administrative patient data
We used administrative patient data from 21 common Care Trajectories, in combination with demographic information to predict hospital readmission, reaching up to 73.8% recall. These types of models can be used to inform contracting and pricing negotiations between these hospitals and healthcare insurers.
Dr. van Wingerden is a neuroscientist by training, working in the field of computational psychiatry. His interests are in applying ML to predictions for mental health.