Classification of adolescent psychotic disorders using linear discriminant analysis

Patricia J. Pardo, Apostolos P. Georgopoulos, John T. Kenny, Traci A. Stuve, Robert L Findling, S. Charles Schulz

Research output: Contribution to journalArticle

Abstract

Background: The differential diagnosis between schizophrenia and bipolar disorder during adolescence presents a major clinical problem. Can these two diagnoses be differentiated objectively early in the courses of illness? Methods: We used linear discrimination analysis (LDA) to classify 28 adolescent subjects into one of three diagnostic categories (healthy, N = 8; schizophrenia, N = 10; bipolar, N = 10) using subsets from a pool of 45 variables as potential predictors (22 neuropsychological test scores and 23 quantitative structural brain measurements). The predictor variables were adjusted for age, gender, race, and psychotropic medication. All possible subsets composed of k = 2-12 variables, from the set of 45 variables available, were evaluated using the robust leaving-one-subject-out method. Results: The highest correct classification (96%) of the 3 diagnostic categories was yielded by 9 sets of k = 12 predictors, comprising both neuropsychological and brain structural measures. Although each one of these sets misclassified one case, each set correctly classified (100%) at least one group, such that a fully correct diagnosis could be reached by a tree-type decision procedure. Conclusions: We conclude that LDA with 12 predictor variables can provide correct and robust classification of subjects into the three diagnostic categories above. This robust classification relies upon both neuropsychological and brain structural information. Our results demonstrate that, despite overlapping clinical symptoms, schizophrenia and bipolar disorder can be differentiated early in the course of disease. This finding has two important implications. Firstly, schizophrenia and bipolar disorder are different illnesses. If schizophrenia and bipolar are dissimilar clinical manifestations of the same disease, we would not be able to use non-clinical information to classify ('diagnose') schizophrenia and bipolar disorder. Secondly, if this study's findings are replicated, brain structure (MRI) and brain function (neuropsychological) used together may be useful in the diagnosis of new patients.

Original languageEnglish (US)
Pages (from-to)297-306
Number of pages10
JournalSchizophrenia Research
Volume87
Issue number1-3
DOIs
StatePublished - Oct 2006
Externally publishedYes

Fingerprint

Discriminant Analysis
Psychotic Disorders
Schizophrenia
Bipolar Disorder
Brain
Decision Trees
Neuropsychological Tests
Differential Diagnosis

Keywords

  • Bipolar disorder
  • Diagnosis
  • LDA
  • MRI
  • Neuropsychological
  • Schizophrenia

ASJC Scopus subject areas

  • Psychiatry and Mental health
  • Behavioral Neuroscience
  • Biological Psychiatry
  • Neurology
  • Psychology(all)

Cite this

Classification of adolescent psychotic disorders using linear discriminant analysis. / Pardo, Patricia J.; Georgopoulos, Apostolos P.; Kenny, John T.; Stuve, Traci A.; Findling, Robert L; Schulz, S. Charles.

In: Schizophrenia Research, Vol. 87, No. 1-3, 10.2006, p. 297-306.

Research output: Contribution to journalArticle

Pardo, Patricia J. ; Georgopoulos, Apostolos P. ; Kenny, John T. ; Stuve, Traci A. ; Findling, Robert L ; Schulz, S. Charles. / Classification of adolescent psychotic disorders using linear discriminant analysis. In: Schizophrenia Research. 2006 ; Vol. 87, No. 1-3. pp. 297-306.
@article{b4da6e998c95495ab91ea0c7f31d4cc9,
title = "Classification of adolescent psychotic disorders using linear discriminant analysis",
abstract = "Background: The differential diagnosis between schizophrenia and bipolar disorder during adolescence presents a major clinical problem. Can these two diagnoses be differentiated objectively early in the courses of illness? Methods: We used linear discrimination analysis (LDA) to classify 28 adolescent subjects into one of three diagnostic categories (healthy, N = 8; schizophrenia, N = 10; bipolar, N = 10) using subsets from a pool of 45 variables as potential predictors (22 neuropsychological test scores and 23 quantitative structural brain measurements). The predictor variables were adjusted for age, gender, race, and psychotropic medication. All possible subsets composed of k = 2-12 variables, from the set of 45 variables available, were evaluated using the robust leaving-one-subject-out method. Results: The highest correct classification (96{\%}) of the 3 diagnostic categories was yielded by 9 sets of k = 12 predictors, comprising both neuropsychological and brain structural measures. Although each one of these sets misclassified one case, each set correctly classified (100{\%}) at least one group, such that a fully correct diagnosis could be reached by a tree-type decision procedure. Conclusions: We conclude that LDA with 12 predictor variables can provide correct and robust classification of subjects into the three diagnostic categories above. This robust classification relies upon both neuropsychological and brain structural information. Our results demonstrate that, despite overlapping clinical symptoms, schizophrenia and bipolar disorder can be differentiated early in the course of disease. This finding has two important implications. Firstly, schizophrenia and bipolar disorder are different illnesses. If schizophrenia and bipolar are dissimilar clinical manifestations of the same disease, we would not be able to use non-clinical information to classify ('diagnose') schizophrenia and bipolar disorder. Secondly, if this study's findings are replicated, brain structure (MRI) and brain function (neuropsychological) used together may be useful in the diagnosis of new patients.",
keywords = "Bipolar disorder, Diagnosis, LDA, MRI, Neuropsychological, Schizophrenia",
author = "Pardo, {Patricia J.} and Georgopoulos, {Apostolos P.} and Kenny, {John T.} and Stuve, {Traci A.} and Findling, {Robert L} and Schulz, {S. Charles}",
year = "2006",
month = "10",
doi = "10.1016/j.schres.2006.05.007",
language = "English (US)",
volume = "87",
pages = "297--306",
journal = "Schizophrenia Research",
issn = "0920-9964",
publisher = "Elsevier",
number = "1-3",

}

TY - JOUR

T1 - Classification of adolescent psychotic disorders using linear discriminant analysis

AU - Pardo, Patricia J.

AU - Georgopoulos, Apostolos P.

AU - Kenny, John T.

AU - Stuve, Traci A.

AU - Findling, Robert L

AU - Schulz, S. Charles

PY - 2006/10

Y1 - 2006/10

N2 - Background: The differential diagnosis between schizophrenia and bipolar disorder during adolescence presents a major clinical problem. Can these two diagnoses be differentiated objectively early in the courses of illness? Methods: We used linear discrimination analysis (LDA) to classify 28 adolescent subjects into one of three diagnostic categories (healthy, N = 8; schizophrenia, N = 10; bipolar, N = 10) using subsets from a pool of 45 variables as potential predictors (22 neuropsychological test scores and 23 quantitative structural brain measurements). The predictor variables were adjusted for age, gender, race, and psychotropic medication. All possible subsets composed of k = 2-12 variables, from the set of 45 variables available, were evaluated using the robust leaving-one-subject-out method. Results: The highest correct classification (96%) of the 3 diagnostic categories was yielded by 9 sets of k = 12 predictors, comprising both neuropsychological and brain structural measures. Although each one of these sets misclassified one case, each set correctly classified (100%) at least one group, such that a fully correct diagnosis could be reached by a tree-type decision procedure. Conclusions: We conclude that LDA with 12 predictor variables can provide correct and robust classification of subjects into the three diagnostic categories above. This robust classification relies upon both neuropsychological and brain structural information. Our results demonstrate that, despite overlapping clinical symptoms, schizophrenia and bipolar disorder can be differentiated early in the course of disease. This finding has two important implications. Firstly, schizophrenia and bipolar disorder are different illnesses. If schizophrenia and bipolar are dissimilar clinical manifestations of the same disease, we would not be able to use non-clinical information to classify ('diagnose') schizophrenia and bipolar disorder. Secondly, if this study's findings are replicated, brain structure (MRI) and brain function (neuropsychological) used together may be useful in the diagnosis of new patients.

AB - Background: The differential diagnosis between schizophrenia and bipolar disorder during adolescence presents a major clinical problem. Can these two diagnoses be differentiated objectively early in the courses of illness? Methods: We used linear discrimination analysis (LDA) to classify 28 adolescent subjects into one of three diagnostic categories (healthy, N = 8; schizophrenia, N = 10; bipolar, N = 10) using subsets from a pool of 45 variables as potential predictors (22 neuropsychological test scores and 23 quantitative structural brain measurements). The predictor variables were adjusted for age, gender, race, and psychotropic medication. All possible subsets composed of k = 2-12 variables, from the set of 45 variables available, were evaluated using the robust leaving-one-subject-out method. Results: The highest correct classification (96%) of the 3 diagnostic categories was yielded by 9 sets of k = 12 predictors, comprising both neuropsychological and brain structural measures. Although each one of these sets misclassified one case, each set correctly classified (100%) at least one group, such that a fully correct diagnosis could be reached by a tree-type decision procedure. Conclusions: We conclude that LDA with 12 predictor variables can provide correct and robust classification of subjects into the three diagnostic categories above. This robust classification relies upon both neuropsychological and brain structural information. Our results demonstrate that, despite overlapping clinical symptoms, schizophrenia and bipolar disorder can be differentiated early in the course of disease. This finding has two important implications. Firstly, schizophrenia and bipolar disorder are different illnesses. If schizophrenia and bipolar are dissimilar clinical manifestations of the same disease, we would not be able to use non-clinical information to classify ('diagnose') schizophrenia and bipolar disorder. Secondly, if this study's findings are replicated, brain structure (MRI) and brain function (neuropsychological) used together may be useful in the diagnosis of new patients.

KW - Bipolar disorder

KW - Diagnosis

KW - LDA

KW - MRI

KW - Neuropsychological

KW - Schizophrenia

UR - http://www.scopus.com/inward/record.url?scp=33748892683&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33748892683&partnerID=8YFLogxK

U2 - 10.1016/j.schres.2006.05.007

DO - 10.1016/j.schres.2006.05.007

M3 - Article

C2 - 16797923

AN - SCOPUS:33748892683

VL - 87

SP - 297

EP - 306

JO - Schizophrenia Research

JF - Schizophrenia Research

SN - 0920-9964

IS - 1-3

ER -