Predicting Patient Outcomes from Time Series with Missing Data via a Semi-supervised Hidden Markov Model
This repository contains code for reproducing the experiments for the "Predicting Patient Outcomes from Time Series with Missing Data via a Semi-supervised Hidden Markov Model" paper. Experiments are segregated by dataset and contains code for data generation and running baselines:
- MIMIC-IV
- eICU
- Toy experiments
- Change directory to the experiment to reproduce
cd {experiment_name}
- Follow the readme in the individual experiments