Derivation, Validation, and Potential Treatment of Clinical Phenotypes for Kidney Failure with Machine Learning

data science and Machine Learning Diplomarbeiten (never - cancelled)

Betreuer

Arne Peine, Anke Schmeink,

Abstract

Acute kidney failure is a life-threatening condition classically defined as a sustained decrease in kidney function. There is growing evidence that there are different phenotypes (clinical representations) of kidney failure, leading to substantially different patient treatment. In this Master Thesis you will apply and assess classical clustering techniques, e.g. k-means, DBSCAN or Expectation–Maximization Clustering using Gaussian Mixture Models versus state-of-art techniques regarding the representation and identification of new phenotypes in kidney failure in large-scale medical databases.

⤓

Download information as pdf.