Patient-centered yes/no prognosis using learning machines

Inke R. König, James D. Malley, Sinisa Pajevic, Christian Weimar, Hans Christoph Diener, Andreas Ziegler*

*Corresponding author for this work
26 Citations (Scopus)


In the last 15 years several machine learning approaches have been developed for classification and regression. In an intuitive manner we introduce the main ideas of classification and regression trees, support vector machines, bagging, boosting and random forests. We discuss differences in the use of machine learning in the biomedical community and the computer sciences. We propose methods for comparing machines on a sound statistical basis. Data from the German Stroke Study Collaboration is used for illustration. We compare the results from learning machines to those obtained by a published logistic regression and discuss similarities and differences.

Original languageEnglish
JournalInternational Journal of Data Mining and Bioinformatics
Issue number4
Pages (from-to)289-341
Number of pages53
Publication statusPublished - 2008


Dive into the research topics of 'Patient-centered yes/no prognosis using learning machines'. Together they form a unique fingerprint.

Cite this