Machine learning approach in mortality rate prediction for hemodialysis patients.

Journal: Computer methods in biomechanics and biomedical engineering
Published Date:

Abstract

Kernel support vector machine algorithm and -means clustering algorithm are used to determine the expected mortality rate for hemodialysis patients. The national nephrology database of Montenegro has been used to conduct this research. Mortality rate prediction is realized with accuracy up to 94.12% and up to 96.77%, when a complete database is observed and when a reduced database (that contains data for the three most common basic diseases) is observed, respectively. Additionally, it is shown that just a few parameters, most of which are collected during the sole patient examination, are enough for satisfying results.

Authors

  • Nevena Radović
    Electrical Engineering Department, University of Montenegro, Podgorica, Montenegro.
  • Vladimir Prelević
    Clinic for Nephrology, Clinical Center of Montenegro, Podgorica, Montenegro.
  • Milena Erceg
    Electrical Engineering Department, University of Montenegro, Podgorica, Montenegro.
  • Tanja Antunović
    Center for Laboratory Diagnostics, Clinical Center of Montenegro, Podgorica, Montenegro.