Publication details

 

Maximum-uncertainty linear discrimination analysis of first-episode schizophrenia subjects

Basic information
Original title:Maximum-uncertainty linear discrimination analysis of first-episode schizophrenia subjects
Authors:Tomáš Kašpárek, Carlos Eduardo Thomaz, Joao Ricardo Sato, Daniel Schwarz, Eva Janoušová, Radek Mareček, Radovan Přikryl, Jiří Vaníček, Andre Fujita, Eva Češková
Further information
Citation:KAŠPÁREK, Tomáš, Carlos Eduardo THOMAZ, Joao Ricardo SATO, Daniel SCHWARZ, Eva JANOUŠOVÁ, Radek MAREČEK, Radovan PŘIKRYL, Jiří VANÍČEK, Andre FUJITA a Eva ČEŠKOVÁ. Maximum-uncertainty linear discrimination analysis of first-episode schizophrenia subjects. Psychiatry Research: Neuroimaging, 2011, roč. 191, č. 3, s. 174-181. ISSN 0925-4927. doi:10.1016/j.pscychresns.2010.09.016.Export BibTeX
@article{947134,
author = {Kašpárek, Tomáš and Thomaz, Carlos Eduardo and Sato, Joao Ricardo and Schwarz, Daniel and Janoušová, Eva and Mareček, Radek and Přikryl, Radovan and Vaníček, Jiří and Fujita, Andre and Češková, Eva},
article_number = {3},
doi = {http://dx.doi.org/10.1016/j.pscychresns.2010.09.016},
keywords = {Schizophrenia; First episode; Classification; Brain morphology},
language = {eng},
issn = {0925-4927},
journal = {Psychiatry Research: Neuroimaging},
title = {Maximum-uncertainty linear discrimination analysis of first-episode schizophrenia subjects},
volume = {191},
year = {2011}
}
Original language:English
Field:Neurology, neurosurgery, neurosciences
Type:Article in Periodical
Keywords:Schizophrenia; First episode; Classification; Brain morphology

Recent techniques of image analysis brought the possibility to recognize subjects based on discriminative image features. We performed a magnetic resonance imaging (MRI)-based classification study to assess its usefulness for outcome prediction of first-episode schizophrenia patients (FES). We included 39 FES patients and 39 healthy controls (HC) and performed the maximum-uncertainty linear discrimination analysis (MLDA) of MRI brain intensity images. The classification accuracy index (CA) was correlated with the Positive and Negative Syndrome Scale (PANSS) and the Global Assessment of Functioning scale (GAF) at 1-year follow-up. The rate of correct classifications of patients with poor and good outcomes was analyzed using chi-square tests. MLDA classification was significantly better than classification by chance. Leave-oneout accuracy was 72%. CA correlated significantly with PANSS and GAF scores at the 1-year follow-up. Moreover, significantly more patients with poor outcome than those with good outcome were classified correctly.MLDA of brain MR intensity features is, therefore, able to correctly classify a significant number of FES patients, and the discriminative features are clinically relevant for clinical presentation 1 year after the first episode of schizophrenia. The accuracy of the current approach is, however, insufficient to be used in clinical practice immediately. Severalmethodological issues need to be addressed to increase the usefulness of this classification approach.

Related projects: