Modelling the prevalence of diabetes mellitus risk factors based on artificial neural network and multiple regression

被引:21
作者
Gholipour, Kamal [1 ,2 ]
Asghari-Jafarabadi, Mohammad [3 ,4 ]
Iezadi, Shabnam [5 ]
Jannati, Ali [1 ,2 ]
Keshavarz, Sina [6 ]
机构
[1] Tabriz Univ Med Sci, Sch Management & Med Informat, Iranian Ctr Excellence Hlth Management, Tabriz, Iran
[2] Tabriz Univ Med Sci, Tabriz Hlth Serv Management Res Ctr, Tabriz, Iran
[3] Tabriz Univ Med Sci, Hlth Management & Safety Promot Res Inst, Rd Traff Injury Res Ctr, Tabriz, Iran
[4] Tabriz Univ Med Sci, Fac Hlth, Dept Stat & Epidemiol, Tabriz, Iran
[5] Tabriz Univ Med Sci, Hlth Management & Safety Promot Res Inst, Social Determinants Hlth Res Ctr, Tabriz, Iran
[6] Univ Social Welf & Rehabil Sci, Publ Hlth & Prevent Med, Tehran, Iran
关键词
artificial neural network; diabetes mellitus; multiple regression; risk factors; LOGISTIC-REGRESSION; CHILDREN;
D O I
10.26719/emhj.18.012
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
Background: Type 2 diabetes mellitus (T2DM) is a metabolic disease with complex causes, manifestations, complications and management. Understanding the wide range of risk factors for T2DM can facilitate diagnosis, proper classification and cost-effective management of the disease. Aims: To compare the power of an artificial neural network (ANN) and logistic regression in identifying T2DM risk factors. Methods: This descriptive and analytical study was conducted in 2013. The study samples were all residents aged 15-64 years of rural and urban areas in East Azerbaijan, Islamic Republic of Iran, who consented to participate (n = 990). The latest data available were collected from the Noncommunicable Disease Surveillance System of East Azerbaijan Province (2007). Data were analysed using SPSS version 19. Results: Based on multiple logistic regression, age, family history of T2DM and residence were the most important risk factors for T2DM. Based on ANN, age, body mass index and current smoking were most important. To test for generalization, ANN and logistic regression were evaluated using the area under the receiver operating characteristic curve (AUC). The AUC was 0.726 (SE = 0.025) and 0.717 (SE = 0.026) for logistic regression and ANN, respectively (P < 0.001). Conclusions: The logistic regression model is better than ANN and it is clinically more comprehensible.
引用
收藏
页码:770 / 777
页数:8
相关论文
共 28 条
[1]   Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research [J].
Agatonovic-Kustrin, S ;
Beresford, R .
JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS, 2000, 22 (05) :717-727
[2]  
[Anonymous], 2003, SCREEN TYP 2 DIAB
[3]  
[Anonymous], WORLD APPL SCI J
[4]   Prevalence of diagnosed and undiagnosed diabetes mellitus and its risk factors in a population-based study of Qatar [J].
Bener, Abdulbari ;
Zirie, Mahmoud ;
Janahi, Ibrahim M. ;
Al-Hamaq, Abdulla O. A. A. ;
Musallam, Manal ;
Wareham, Nick J. .
DIABETES RESEARCH AND CLINICAL PRACTICE, 2009, 84 (01) :99-106
[5]  
Bonita R, 2003, GLOBAL BEHAVIORAL RISK FACTOR SURVEILLANCE, P9
[6]  
Copeland K.C., 2005, CLIN DIABETES, V23, P181, DOI DOI 10.2337/DIACLIN.23.4.181
[7]   Prevalence, risk factors and co-morbidities of diabetes among adults in rural Saskatchewan: the influence of farm residence and agriculture-related exposures [J].
Dyck, Roland ;
Karunanayake, Chandima ;
Pahwa, Punam ;
Hagel, Louise ;
Lawson, Josh ;
Rennie, Donna ;
Dosman, James .
BMC PUBLIC HEALTH, 2013, 13
[8]   Third national surveillance of risk factors of non-communicable diseases (SuRFNCD-2007) in Iran: methods and results on prevalence of diabetes, hypertension, obesity, central obesity, and dyslipidemia [J].
Esteghamati, Alireza ;
Meysamie, Alipasha ;
Khalilzadeh, Omid ;
Rashidi, Armin ;
Haghazali, Mehrdad ;
Asgari, Fereshteh ;
Kamgar, Mandana ;
Gouya, Mohammad Mehdi ;
Abbasi, Mehrshad .
BMC PUBLIC HEALTH, 2009, 9
[9]   An introduction to ROC analysis [J].
Fawcett, Tom .
PATTERN RECOGNITION LETTERS, 2006, 27 (08) :861-874
[10]   Artificial neural networks for predictive modeling in prostate cancer [J].
Gamito E.J. ;
Crawford E.D. .
Current Oncology Reports, 2004, 6 (3) :216-221