Performance of a neuro-fuzzy model in predicting weight changes of chronic schizophrenic patients exposed to antipsychotics

T. H. Lan, E. W. Loh, M. S. Wu, T. M. Hu, P. Chou, T. Y. Lan, H. J. Chiu

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Artificial intelligence has become a possible solution to resolve the problem of loss of information when complexity of a disease increases. Obesity phenotypes are observable clinical features of drug-naive schizophrenic patients. In addition, atypical antipsychotic medications may cause these unwanted effects. Here we examined the performance of neuro-fuzzy modeling (NFM) in predicting weight changes in chronic schizophrenic patients exposed to antipsychotics. Two hundred and twenty inpatients meeting DSMIV diagnosis of schizophrenia, treated with antipsychotics, either typical or atypical, for more than 2 years, were recruited. All subjects were assessed in the same study period between mid-November 2003 and mid-April 2004. The baseline and first visit's physical data including weight, height and circumference were used in this study. Clinical information (Clinical Global Impression and Life Style Survey) and genotype data of five single nucleotide polymorphisms were also included as predictors. The subjects were randomly assigned into the first group (105 subjects) and second group (115 subjects), and NFM was performed by using the FuzzyTECH 5.54 software package, with a network-type structure constructed in the rule block. A complete learned model trained from merged data of the first and second groups demonstrates that, at a prediction error of 5, 93% subjects with weight gain were identified. Our study suggests that NFM is a feasible prediction tool for obesity in schizophrenic patients exposed to antipsychotics, with further improvements required.

Original languageEnglish
Pages (from-to)1129-1137
Number of pages9
JournalMolecular Psychiatry
Volume13
Issue number12
DOIs
Publication statusPublished - Dec 1 2008
Externally publishedYes

Fingerprint

Antipsychotic Agents
Weights and Measures
Obesity
Artificial Intelligence
Weight Gain
Single Nucleotide Polymorphism
Life Style
Inpatients
Schizophrenia
Software
Genotype
Phenotype
Pharmaceutical Preparations

Keywords

  • Antipsychotics
  • Neuro-fuzzy modeling
  • Schizophrenia
  • Weight gain

ASJC Scopus subject areas

  • Molecular Biology
  • Psychiatry and Mental health
  • Cellular and Molecular Neuroscience

Cite this

Performance of a neuro-fuzzy model in predicting weight changes of chronic schizophrenic patients exposed to antipsychotics. / Lan, T. H.; Loh, E. W.; Wu, M. S.; Hu, T. M.; Chou, P.; Lan, T. Y.; Chiu, H. J.

In: Molecular Psychiatry, Vol. 13, No. 12, 01.12.2008, p. 1129-1137.

Research output: Contribution to journalArticle

Lan, T. H. ; Loh, E. W. ; Wu, M. S. ; Hu, T. M. ; Chou, P. ; Lan, T. Y. ; Chiu, H. J. / Performance of a neuro-fuzzy model in predicting weight changes of chronic schizophrenic patients exposed to antipsychotics. In: Molecular Psychiatry. 2008 ; Vol. 13, No. 12. pp. 1129-1137.
@article{886df22f8c41456199d630cd9a93a144,
title = "Performance of a neuro-fuzzy model in predicting weight changes of chronic schizophrenic patients exposed to antipsychotics",
abstract = "Artificial intelligence has become a possible solution to resolve the problem of loss of information when complexity of a disease increases. Obesity phenotypes are observable clinical features of drug-naive schizophrenic patients. In addition, atypical antipsychotic medications may cause these unwanted effects. Here we examined the performance of neuro-fuzzy modeling (NFM) in predicting weight changes in chronic schizophrenic patients exposed to antipsychotics. Two hundred and twenty inpatients meeting DSMIV diagnosis of schizophrenia, treated with antipsychotics, either typical or atypical, for more than 2 years, were recruited. All subjects were assessed in the same study period between mid-November 2003 and mid-April 2004. The baseline and first visit's physical data including weight, height and circumference were used in this study. Clinical information (Clinical Global Impression and Life Style Survey) and genotype data of five single nucleotide polymorphisms were also included as predictors. The subjects were randomly assigned into the first group (105 subjects) and second group (115 subjects), and NFM was performed by using the FuzzyTECH 5.54 software package, with a network-type structure constructed in the rule block. A complete learned model trained from merged data of the first and second groups demonstrates that, at a prediction error of 5, 93{\%} subjects with weight gain were identified. Our study suggests that NFM is a feasible prediction tool for obesity in schizophrenic patients exposed to antipsychotics, with further improvements required.",
keywords = "Antipsychotics, Neuro-fuzzy modeling, Schizophrenia, Weight gain",
author = "Lan, {T. H.} and Loh, {E. W.} and Wu, {M. S.} and Hu, {T. M.} and P. Chou and Lan, {T. Y.} and Chiu, {H. J.}",
year = "2008",
month = "12",
day = "1",
doi = "10.1038/sj.mp.4002128",
language = "English",
volume = "13",
pages = "1129--1137",
journal = "Molecular Psychiatry",
issn = "1359-4184",
publisher = "Nature Publishing Group",
number = "12",

}

TY - JOUR

T1 - Performance of a neuro-fuzzy model in predicting weight changes of chronic schizophrenic patients exposed to antipsychotics

AU - Lan, T. H.

AU - Loh, E. W.

AU - Wu, M. S.

AU - Hu, T. M.

AU - Chou, P.

AU - Lan, T. Y.

AU - Chiu, H. J.

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Artificial intelligence has become a possible solution to resolve the problem of loss of information when complexity of a disease increases. Obesity phenotypes are observable clinical features of drug-naive schizophrenic patients. In addition, atypical antipsychotic medications may cause these unwanted effects. Here we examined the performance of neuro-fuzzy modeling (NFM) in predicting weight changes in chronic schizophrenic patients exposed to antipsychotics. Two hundred and twenty inpatients meeting DSMIV diagnosis of schizophrenia, treated with antipsychotics, either typical or atypical, for more than 2 years, were recruited. All subjects were assessed in the same study period between mid-November 2003 and mid-April 2004. The baseline and first visit's physical data including weight, height and circumference were used in this study. Clinical information (Clinical Global Impression and Life Style Survey) and genotype data of five single nucleotide polymorphisms were also included as predictors. The subjects were randomly assigned into the first group (105 subjects) and second group (115 subjects), and NFM was performed by using the FuzzyTECH 5.54 software package, with a network-type structure constructed in the rule block. A complete learned model trained from merged data of the first and second groups demonstrates that, at a prediction error of 5, 93% subjects with weight gain were identified. Our study suggests that NFM is a feasible prediction tool for obesity in schizophrenic patients exposed to antipsychotics, with further improvements required.

AB - Artificial intelligence has become a possible solution to resolve the problem of loss of information when complexity of a disease increases. Obesity phenotypes are observable clinical features of drug-naive schizophrenic patients. In addition, atypical antipsychotic medications may cause these unwanted effects. Here we examined the performance of neuro-fuzzy modeling (NFM) in predicting weight changes in chronic schizophrenic patients exposed to antipsychotics. Two hundred and twenty inpatients meeting DSMIV diagnosis of schizophrenia, treated with antipsychotics, either typical or atypical, for more than 2 years, were recruited. All subjects were assessed in the same study period between mid-November 2003 and mid-April 2004. The baseline and first visit's physical data including weight, height and circumference were used in this study. Clinical information (Clinical Global Impression and Life Style Survey) and genotype data of five single nucleotide polymorphisms were also included as predictors. The subjects were randomly assigned into the first group (105 subjects) and second group (115 subjects), and NFM was performed by using the FuzzyTECH 5.54 software package, with a network-type structure constructed in the rule block. A complete learned model trained from merged data of the first and second groups demonstrates that, at a prediction error of 5, 93% subjects with weight gain were identified. Our study suggests that NFM is a feasible prediction tool for obesity in schizophrenic patients exposed to antipsychotics, with further improvements required.

KW - Antipsychotics

KW - Neuro-fuzzy modeling

KW - Schizophrenia

KW - Weight gain

UR - http://www.scopus.com/inward/record.url?scp=56449127168&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56449127168&partnerID=8YFLogxK

U2 - 10.1038/sj.mp.4002128

DO - 10.1038/sj.mp.4002128

M3 - Article

VL - 13

SP - 1129

EP - 1137

JO - Molecular Psychiatry

JF - Molecular Psychiatry

SN - 1359-4184

IS - 12

ER -