Naslov
Exploratory clustering for patient subpopulation discovery

Autori
Gamberger, Dragan ; Ženko, Bernard ; Lavrač, Nada

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Informatics for Health: Connected Citizen-Led Wellness and Population Health / Randell, Rebecca ; Cornet, Ronald ; McCowan, Colin ; Peek, Niels ; Scott, Philip J. ; - : IOS Press, 2017, 101-105

ISBN
978-1-61499-752-8

Skup
Informatics for Health 2017

Mjesto i datum
Manchester, Ujedinjeno Kraljevstvo, 24.04.2017. - 26.04.2017

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Data clustering ; Biomarkers ; Alzheimer's disease

Sažetak
Exploratory Clustering is a novel general purpose clustering tool which is especially appropriate for medical domains in which we need to identify subpopulations that are similar in two different data layers. The tool implements the multi-layer clustering algorithm in a framework that enables iterative experiments by the user in his search for relevant patient subpopulations. A unique property of the tool is integration of clustering and feature selection algorithms. Differences in values of most relevant attributes are used to demonstrate decisive properties of constructed clusters. Usefulness of the tool is illustrated on a task of discovering groups of patients with similar cognitive impairment.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA