Easy and low-cost identification of metabolic syndrome in patients treated with second-generation antipsychotics

Artificial neural network and logistic regression models

Chao Cheng Lin, Ya Mei Bai, Jen Yeu Chen, Tzung Jeng Hwang, Tzu Ting Chen, Hung Wen Chiu, Yu Chuan Li

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Objective: Metabolic syndrome (MetS) is an important side effect of second-generation anti- psychotics (SGAs). However, many SGA-treated patients with MetS remain undetected. In this study, we trained and validated artificial neural network (ANN) and multiple logistic regression models without biochemical parameters to rapidly identify MetS in patients with SGA treatment. Method: A total of 383 patients with a diagnosis of schizophrenia or schizoaffective disorder (DSM-IV criteria) with SGA treatment for more than 6 months were investigated to determine whether they met the MetS criteria according to the International Diabetes Federation. The data for these patients were collected between March 2005 and September 2005. The input variables of ANN and logistic regression were limited to demographic and anthropometric data only. All models were trained by randomly selecting two-thirds of the patient data and were Internally validated with the remaining one-third of the data. The models were then externally validated with data from 69 patients from another hospital, collected between March 2008 and June 2008. The area under the receiver operating characteristic curve (AUC) was used to measure the performance of all models. Results: Both the final ANN and logistic regression models had high accuracy (88.3% vs 83.6%), sensitivity (93.1% vs 86.2%), and specificity (86.9% vs 83.8%) to identify MetS in the internal validation set. The mean ± SD AUC was high for both the ANN and logistic regression models (0.934 ± 0.033 vs 0.922 ± 0.035, P= .63). During external validation, high AUC was still obtained for both models. Waist circumference and diastolic blood pressure were the common variables that were left in the final ANN and logistic regression models. Conclusion: Our study developed accurate ANN and logistic regression models to detect MetS in patients with SGA treatment. The models are likely to provide a noninvasive tool for large-scale screening of MetS in this group of patients.

Original languageEnglish
Pages (from-to)225-234
Number of pages10
JournalJournal of Clinical Psychiatry
Volume71
Issue number3
DOIs
Publication statusPublished - Mar 2010

Fingerprint

Antipsychotic Agents
Logistic Models
Costs and Cost Analysis
Area Under Curve
Blood Pressure
Cohort Effect
Waist Circumference
ROC Curve
Diagnostic and Statistical Manual of Mental Disorders
Psychotic Disorders
Schizophrenia
Therapeutics
Demography

ASJC Scopus subject areas

  • Psychiatry and Mental health

Cite this

Easy and low-cost identification of metabolic syndrome in patients treated with second-generation antipsychotics : Artificial neural network and logistic regression models. / Lin, Chao Cheng; Bai, Ya Mei; Chen, Jen Yeu; Hwang, Tzung Jeng; Chen, Tzu Ting; Chiu, Hung Wen; Li, Yu Chuan.

In: Journal of Clinical Psychiatry, Vol. 71, No. 3, 03.2010, p. 225-234.

Research output: Contribution to journalArticle

@article{fb400276def64f95862be9c8da1e991c,
title = "Easy and low-cost identification of metabolic syndrome in patients treated with second-generation antipsychotics: Artificial neural network and logistic regression models",
abstract = "Objective: Metabolic syndrome (MetS) is an important side effect of second-generation anti- psychotics (SGAs). However, many SGA-treated patients with MetS remain undetected. In this study, we trained and validated artificial neural network (ANN) and multiple logistic regression models without biochemical parameters to rapidly identify MetS in patients with SGA treatment. Method: A total of 383 patients with a diagnosis of schizophrenia or schizoaffective disorder (DSM-IV criteria) with SGA treatment for more than 6 months were investigated to determine whether they met the MetS criteria according to the International Diabetes Federation. The data for these patients were collected between March 2005 and September 2005. The input variables of ANN and logistic regression were limited to demographic and anthropometric data only. All models were trained by randomly selecting two-thirds of the patient data and were Internally validated with the remaining one-third of the data. The models were then externally validated with data from 69 patients from another hospital, collected between March 2008 and June 2008. The area under the receiver operating characteristic curve (AUC) was used to measure the performance of all models. Results: Both the final ANN and logistic regression models had high accuracy (88.3{\%} vs 83.6{\%}), sensitivity (93.1{\%} vs 86.2{\%}), and specificity (86.9{\%} vs 83.8{\%}) to identify MetS in the internal validation set. The mean ± SD AUC was high for both the ANN and logistic regression models (0.934 ± 0.033 vs 0.922 ± 0.035, P= .63). During external validation, high AUC was still obtained for both models. Waist circumference and diastolic blood pressure were the common variables that were left in the final ANN and logistic regression models. Conclusion: Our study developed accurate ANN and logistic regression models to detect MetS in patients with SGA treatment. The models are likely to provide a noninvasive tool for large-scale screening of MetS in this group of patients.",
author = "Lin, {Chao Cheng} and Bai, {Ya Mei} and Chen, {Jen Yeu} and Hwang, {Tzung Jeng} and Chen, {Tzu Ting} and Chiu, {Hung Wen} and Li, {Yu Chuan}",
year = "2010",
month = "3",
doi = "10.4088/JCP.08m04628yel",
language = "English",
volume = "71",
pages = "225--234",
journal = "Journal of Clinical Psychiatry",
issn = "0160-6689",
publisher = "Physicians Postgraduate Press Inc.",
number = "3",

}

TY - JOUR

T1 - Easy and low-cost identification of metabolic syndrome in patients treated with second-generation antipsychotics

T2 - Artificial neural network and logistic regression models

AU - Lin, Chao Cheng

AU - Bai, Ya Mei

AU - Chen, Jen Yeu

AU - Hwang, Tzung Jeng

AU - Chen, Tzu Ting

AU - Chiu, Hung Wen

AU - Li, Yu Chuan

PY - 2010/3

Y1 - 2010/3

N2 - Objective: Metabolic syndrome (MetS) is an important side effect of second-generation anti- psychotics (SGAs). However, many SGA-treated patients with MetS remain undetected. In this study, we trained and validated artificial neural network (ANN) and multiple logistic regression models without biochemical parameters to rapidly identify MetS in patients with SGA treatment. Method: A total of 383 patients with a diagnosis of schizophrenia or schizoaffective disorder (DSM-IV criteria) with SGA treatment for more than 6 months were investigated to determine whether they met the MetS criteria according to the International Diabetes Federation. The data for these patients were collected between March 2005 and September 2005. The input variables of ANN and logistic regression were limited to demographic and anthropometric data only. All models were trained by randomly selecting two-thirds of the patient data and were Internally validated with the remaining one-third of the data. The models were then externally validated with data from 69 patients from another hospital, collected between March 2008 and June 2008. The area under the receiver operating characteristic curve (AUC) was used to measure the performance of all models. Results: Both the final ANN and logistic regression models had high accuracy (88.3% vs 83.6%), sensitivity (93.1% vs 86.2%), and specificity (86.9% vs 83.8%) to identify MetS in the internal validation set. The mean ± SD AUC was high for both the ANN and logistic regression models (0.934 ± 0.033 vs 0.922 ± 0.035, P= .63). During external validation, high AUC was still obtained for both models. Waist circumference and diastolic blood pressure were the common variables that were left in the final ANN and logistic regression models. Conclusion: Our study developed accurate ANN and logistic regression models to detect MetS in patients with SGA treatment. The models are likely to provide a noninvasive tool for large-scale screening of MetS in this group of patients.

AB - Objective: Metabolic syndrome (MetS) is an important side effect of second-generation anti- psychotics (SGAs). However, many SGA-treated patients with MetS remain undetected. In this study, we trained and validated artificial neural network (ANN) and multiple logistic regression models without biochemical parameters to rapidly identify MetS in patients with SGA treatment. Method: A total of 383 patients with a diagnosis of schizophrenia or schizoaffective disorder (DSM-IV criteria) with SGA treatment for more than 6 months were investigated to determine whether they met the MetS criteria according to the International Diabetes Federation. The data for these patients were collected between March 2005 and September 2005. The input variables of ANN and logistic regression were limited to demographic and anthropometric data only. All models were trained by randomly selecting two-thirds of the patient data and were Internally validated with the remaining one-third of the data. The models were then externally validated with data from 69 patients from another hospital, collected between March 2008 and June 2008. The area under the receiver operating characteristic curve (AUC) was used to measure the performance of all models. Results: Both the final ANN and logistic regression models had high accuracy (88.3% vs 83.6%), sensitivity (93.1% vs 86.2%), and specificity (86.9% vs 83.8%) to identify MetS in the internal validation set. The mean ± SD AUC was high for both the ANN and logistic regression models (0.934 ± 0.033 vs 0.922 ± 0.035, P= .63). During external validation, high AUC was still obtained for both models. Waist circumference and diastolic blood pressure were the common variables that were left in the final ANN and logistic regression models. Conclusion: Our study developed accurate ANN and logistic regression models to detect MetS in patients with SGA treatment. The models are likely to provide a noninvasive tool for large-scale screening of MetS in this group of patients.

UR - http://www.scopus.com/inward/record.url?scp=77950326901&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950326901&partnerID=8YFLogxK

U2 - 10.4088/JCP.08m04628yel

DO - 10.4088/JCP.08m04628yel

M3 - Article

VL - 71

SP - 225

EP - 234

JO - Journal of Clinical Psychiatry

JF - Journal of Clinical Psychiatry

SN - 0160-6689

IS - 3

ER -