PMID- 29784893
OWN - NLM
STAT- MEDLINE
DCOM- 20181023
LR  - 20181023
IS  - 2228-7809 (Electronic)
IS  - 2228-7795 (Linking)
VI  - 18
IP  - 2
DP  - 2018 Apr 24
TI  - A Comparison between Decision Tree and Random Forest in Determining the Risk 
      Factors Associated with Type 2 Diabetes.
PG  - e00412
AB  - BACKGROUND: We aimed to identify the associated risk factors of type 2 diabetes 
      mellitus (T2DM) using data mining approach, decision tree and random forest 
      techniques using the Mashhad Stroke and Heart Atherosclerotic Disorders (MASHAD) 
      Study program. STUDY DESIGN: A cross-sectional study. METHODS: The MASHAD study 
      started in 2010 and will continue until 2020. Two data mining tools, namely 
      decision trees, and random forests, are used for predicting T2DM when some other 
      characteristics are observed on 9528 subjects recruited from MASHAD database. 
      This paper makes a comparison between these two models in terms of accuracy, 
      sensitivity, specificity and the area under ROC curve. RESULTS: The prevalence 
      rate of T2DM was 14% among these subjects. The decision tree model has 64.9% 
      accuracy, 64.5% sensitivity, 66.8% specificity, and area under the ROC curve 
      measuring 68.6%, while the random forest model has 71.1% accuracy, 71.3% 
      sensitivity, 69.9% specificity, and area under the ROC curve measuring 77.3% 
      respectively. CONCLUSIONS: The random forest model, when used with demographic, 
      clinical, and anthropometric and biochemical measurements, can provide a simple 
      tool to identify associated risk factors for type 2 diabetes. Such identification 
      can substantially use for managing the health policy to reduce the number of 
      subjects with T2DM .
FAU - Esmaily, Habibollah
AU  - Esmaily H
AD  - Social Determinants of Health Research Center, Mashhad University of Medical 
      Sciences, Mashhad, Iran.
FAU - Tayefi, Maryam
AU  - Tayefi M
AD  - Clinical Research Unit, Mashhad university of Medical Sciences, Mashhad, Iran.
FAU - Doosti, Hassan
AU  - Doosti H
AD  - Department of Statistics, Macquarie University, Sydney, NSW, Australia.
FAU - Ghayour-Mobarhan, Majid
AU  - Ghayour-Mobarhan M
AD  - Biochemistry of Nutrition Research Center, School of Medicine, Mashhad University 
      of Medical Sciences, Mashhad, Iran.
FAU - Nezami, Hossein
AU  - Nezami H
AD  - Department of Basic Sciences, Faculty of Medicine, Gonabad University of Medical 
      Sciences, Gonabad, Iran.
FAU - Amirabadizadeh, Alireza
AU  - Amirabadizadeh A
AD  - Medical Toxicology and Drug Abuse Research Center (MTDRC), Birjand University of 
      Medical Sciences, Moallem Avenue, Birjand, Iran. amirabadiza921@gmail.com.
LA  - eng
PT  - Comparative Study
PT  - Journal Article
DEP - 20180424
PL  - Iran
TA  - J Res Health Sci
JT  - Journal of research in health sciences
JID - 101480094
SB  - IM
MH  - Aged
MH  - Cross-Sectional Studies
MH  - Data Mining/*methods
MH  - Decision Trees
MH  - Diabetes Mellitus, Type 2/*etiology
MH  - Female
MH  - Humans
MH  - Iran
MH  - Male
MH  - Mass Screening/methods
MH  - Middle Aged
MH  - ROC Curve
MH  - Risk Factors
MH  - Sensitivity and Specificity
OTO - NOTNLM
OT  - Decision tree
OT  - Diabetes mellitus
OT  - Iran
OT  - Random forest
OT  - data mining
EDAT- 2018/05/23 06:00
MHDA- 2018/10/24 06:00
CRDT- 2018/05/23 06:00
PHST- 2017/12/24 00:00 [received]
PHST- 2018/04/17 00:00 [accepted]
PHST- 2018/04/16 00:00 [revised]
PHST- 2018/05/23 06:00 [entrez]
PHST- 2018/05/23 06:00 [pubmed]
PHST- 2018/10/24 06:00 [medline]
AID - 3777 [pii]
PST - epublish
SO  - J Res Health Sci. 2018 Apr 24;18(2):e00412.