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

J 2011

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

KAŠPÁREK, Tomáš, Carlos Eduardo THOMAZ, Joao Ricardo SATO, Daniel SCHWARZ, Eva JANOUŠOVÁ et. al.

Basic information

Original name

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

Authors

KAŠPÁREK, Tomáš (203 Czech Republic, guarantor, belonging to the institution), Carlos Eduardo THOMAZ (76 Brazil), Joao Ricardo SATO (76 Brazil), Daniel SCHWARZ (203 Czech Republic, belonging to the institution), Eva JANOUŠOVÁ (203 Czech Republic, belonging to the institution), Radek MAREČEK (203 Czech Republic, belonging to the institution), Radovan PŘIKRYL (203 Czech Republic, belonging to the institution), Jiří VANÍČEK (203 Czech Republic, belonging to the institution), Andre FUJITA (392 Japan) and Eva ČEŠKOVÁ (203 Czech Republic, belonging to the institution)

Edition

Psychiatry Research: Neuroimaging, 2011, 0925-4927

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

30000 3. Medical and Health Sciences

Country of publisher

Ireland

Confidentiality degree

není předmětem státního či obchodního tajemství

Impact factor

Impact factor: 2.964

RIV identification code

RIV/00216224:14110/11:00052818

Organization unit

Faculty of Medicine

DOI

http://dx.doi.org/10.1016/j.pscychresns.2010.09.016

UT WoS

000288728500004

Keywords in English

Schizophrenia; First episode; Classification; Brain morphology

Abstract

V originále

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.

Links

MSM0021622404, plan (intention)

Name: Vnitřní organizace a neurobiologické mechanismy funkčních systémů CNS

Investor: Ministry of Education, Youth and Sports of the CR, The internal organisation and neurobiological mechanisms of functional CNS systems under normal and pathological conditions.

NS10347, research and development project

Name: Moderní metody rozpoznávání pro analýzu obrazových dat v neuropsychiatrickém výzkumu

Investor: Ministry of Health of the CR

NS9893, research and development project

Name: Predikce průběhu iniciálních fází schizofrenie pomocí morfologie mozku

Investor: Ministry of Health of the CR

Citovat

KAŠPÁREK, Tomáš, Carlos Eduardo THOMAZ, Joao Ricardo SATO, Daniel SCHWARZ, Eva JANOUŠOVÁ, Radek MAREČEK, Radovan PŘIKRYL, Jiří VANÍČEK, Andre FUJITA and Eva ČEŠKOVÁ. Maximum-uncertainty linear discrimination analysis of first-episode schizophrenia subjects. Psychiatry Research: Neuroimaging. 2011, vol. 191, No 3, p. 174-181. ISSN 0925-4927. Available from: https://dx.doi.org/10.1016/j.pscychresns.2010.09.016.

@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}
}

TY  - JOUR
ID  - 947134
AU  - Kašpárek, Tomáš - Thomaz, Carlos Eduardo - Sato, Joao Ricardo - Schwarz, Daniel - Janoušová, Eva - Mareček, Radek - Přikryl, Radovan - Vaníček, Jiří - Fujita, Andre - Češková, Eva
PY  - 2011
TI  - Maximum-uncertainty linear discrimination analysis of first-episode schizophrenia subjects
JF  - Psychiatry Research: Neuroimaging
VL  - 191
IS  - 3
SP  - 174-181
EP  - 174-181
SN  - 09254927
KW  - Schizophrenia
KW  - First episode
KW  - Classification
KW  - Brain morphology
N2  - 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.
ER  -

KAŠPÁREK, Tomáš, Carlos Eduardo THOMAZ, Joao Ricardo SATO, Daniel SCHWARZ, Eva JANOUŠOVÁ, Radek MAREČEK, Radovan PŘIKRYL, Jiří VANÍČEK, Andre FUJITA and Eva ČEŠKOVÁ. Maximum-uncertainty linear discrimination analysis of first-episode schizophrenia subjects. \textit{Psychiatry Research: Neuroimaging}. 2011, vol.~191, No~3, p.~174-181. ISSN~0925-4927. Available from: https://dx.doi.org/10.1016/j.pscychresns.2010.09.016.

Detailed Information on Publication Record