Feature selection and transformation by machine learning reduce variable numbers and improve prediction for heart failure readmission or death.
Saqib E AwanMohammed BennamounFerdous SohelFrank M SanfilippoBenjamin J ChowGirish DwivediPublished in: PloS one (2019)
A small set of variables selected using ML matched the performance of the model that used the full set of 47 variables for predicting 30-day readmission or death in HF patients. Model performance can be further significantly improved by transforming the original variables using ML methods.