Evaluation of Machine Learning Methods for the Long-Term Prediction of Cardiac 
Diseases

Schlemmer, Alexander; Zwirnmann, Henning; Zabel, Markus; Parlitz, Ulrich; Luther, Stefan

doi:10.1109/ESGCO.2014.6847567

Datensatz

DATENSATZ AKTIONENEXPORT

Zur Ablage hinzufügen

Lokale TagsFreigabegeschichteDetailsÜbersicht

Freigegeben

Konferenzbeitrag

Evaluation of Machine Learning Methods for the Long-Term Prediction of Cardiac Diseases

MPG-Autoren

/persons/resource/persons182785

Schlemmer, Alexander
Research Group Biomedical Physics, Max Planck Institute for Dynamics and Self-Organization, Max Planck Society;

/persons/resource/persons182787

Zwirnmann, Henning
Research Group Biomedical Physics, Max Planck Institute for Dynamics and Self-Organization, Max Planck Society;

/persons/resource/persons173613

Parlitz, Ulrich
Research Group Biomedical Physics, Max Planck Institute for Dynamics and Self-Organization, Max Planck Society;

/persons/resource/persons173583

Luther, Stefan
Research Group Biomedical Physics, Max Planck Institute for Dynamics and Self-Organization, Max Planck Society;

Externe Ressourcen

Es sind keine externen Ressourcen hinterlegt

Volltexte (beschränkter Zugriff)

Für Ihren IP-Bereich sind aktuell keine Volltexte freigegeben.

Volltexte (frei zugänglich)

Es sind keine frei zugänglichen Volltexte in PuRe verfügbar

Ergänzendes Material (frei zugänglich)

Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar

Zitation

Schlemmer, A., Zwirnmann, H., Zabel, M., Parlitz, U., & Luther, S. (2014). Evaluation of Machine Learning Methods for the Long-Term Prediction of Cardiac Diseases. In 8th Conference of the ESGCO (pp. 157-158). IEEE.

Zitierlink: https://hdl.handle.net/11858/00-001M-0000-0029-0F7B-2

Zusammenfassung

We evaluate several machine learning algorithms in the context of long-term prediction of cardiac diseases. Results from applying K Nearest Neighbors Classifiers (KNN), Support Vector Machines (SVM) and Random Forests (RF) to data from a cardiological long-term study suggests that multivariate methods can significantly improve classification results. SVMs were found to yield the best results in Matthews Correlation Coefficient and are most stable with respect to a varying number of features.