PMID- 34073854
OWN - NLM
STAT- MEDLINE
DCOM- 20210701
LR  - 20210701
IS  - 1660-4601 (Electronic)
IS  - 1661-7827 (Print)
IS  - 1660-4601 (Linking)
VI  - 18
IP  - 11
DP  - 2021 May 24
TI  - Classification and Prediction on the Effects of Nutritional Intake on 
      Overweight/Obesity, Dyslipidemia, Hypertension and Type 2 Diabetes Mellitus Using 
      Deep Learning Model: 4-7th Korea National Health and Nutrition Examination 
      Survey.
LID - 10.3390/ijerph18115597 [doi]
LID - 5597
AB  - Few studies have been conducted to classify and predict the influence of 
      nutritional intake on overweight/obesity, dyslipidemia, hypertension and type 2 
      diabetes mellitus (T2DM) based on deep learning such as deep neural network 
      (DNN). The present study aims to classify and predict associations between 
      nutritional intake and risk of overweight/obesity, dyslipidemia, hypertension and 
      T2DM by developing a DNN model, and to compare a DNN model with the most popular 
      machine learning models such as logistic regression and decision tree. Subjects 
      aged from 40 to 69 years in the 4-7th (from 2007 through 2018) Korea National 
      Health and Nutrition Examination Survey (KNHANES) were included. Diagnostic 
      criteria of dyslipidemia (n = 10,731), hypertension (n = 10,991), T2DM (n = 3889) 
      and overweight/obesity (n = 10,980) were set as dependent variables. Nutritional 
      intakes were set as independent variables. A DNN model comprising one input layer 
      with 7 nodes, three hidden layers with 30 nodes, 12 nodes, 8 nodes in each layer 
      and one output layer with one node were implemented in Python programming 
      language using Keras with tensorflow backend. In DNN, binary cross-entropy loss 
      function for binary classification was used with Adam optimizer. For avoiding 
      overfitting, dropout was applied to each hidden layer. Structural equation 
      modelling (SEM) was also performed to simultaneously estimate multivariate causal 
      association between nutritional intake and overweight/obesity, dyslipidemia, 
      hypertension and T2DM. The DNN model showed the higher prediction accuracy with 
      0.58654 for dyslipidemia, 0.79958 for hypertension, 0.80896 for T2DM and 0.62496 
      for overweight/obesity compared with two other machine leaning models with 
      five-folds cross-validation. Prediction accuracy for dyslipidemia, hypertension, 
      T2DM and overweight/obesity were 0.58448, 0.79929, 0.80818 and 0.62486, 
      respectively, when analyzed by a logistic regression, also were 0.52148, 0.66773, 
      0.71587 and 0.54026, respectively, when analyzed by a decision tree. This study 
      observed a DNN model with three hidden layers with 30 nodes, 12 nodes, 8 nodes in 
      each layer had better prediction accuracy than two conventional machine learning 
      models of a logistic regression and decision tree.
FAU - Kim, Hyerim
AU  - Kim H
AD  - Department of Food and Nutrition, Gyeongsang National University, Jinju 52828, 
      Gyeongnam, Korea.
FAU - Lim, Dong Hoon
AU  - Lim DH
AD  - Department of Information & Statistics, Department of Bio & Medical Big Data 
      (BK21 Four Program) and RINS, Gyeongsang National University, Jinju 52828, 
      Gyeongnam, Korea.
FAU - Kim, Yoona
AU  - Kim Y
AUID- ORCID: 0000-0002-3924-8543
AD  - Department of Food and Nutrition, Institute of Agriculture and Life Science, 
      Gyeongsang National University, Jinju 52828, Gyeongnam, Korea.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20210524
PL  - Switzerland
TA  - Int J Environ Res Public Health
JT  - International journal of environmental research and public health
JID - 101238455
SB  - IM
MH  - *Deep Learning
MH  - *Diabetes Mellitus, Type 2/epidemiology/etiology
MH  - *Dyslipidemias/epidemiology/etiology
MH  - Eating
MH  - Humans
MH  - *Hypertension/epidemiology/etiology
MH  - Nutrition Surveys
MH  - Obesity/epidemiology
MH  - Overweight/epidemiology
MH  - Republic of Korea/epidemiology
PMC - PMC8197245
OTO - NOTNLM
OT  - deep neural network
OT  - dyslipidemia
OT  - hypertension
OT  - nutritional intake
OT  - overweight/obesity
OT  - prediction
OT  - type 2 diabetes mellitus
COIS- The authors declare no conflict of interest.
EDAT- 2021/06/03 06:00
MHDA- 2021/07/02 06:00
PMCR- 2021/05/24
CRDT- 2021/06/02 01:39
PHST- 2021/03/31 00:00 [received]
PHST- 2021/05/17 00:00 [revised]
PHST- 2021/05/21 00:00 [accepted]
PHST- 2021/06/02 01:39 [entrez]
PHST- 2021/06/03 06:00 [pubmed]
PHST- 2021/07/02 06:00 [medline]
PHST- 2021/05/24 00:00 [pmc-release]
AID - ijerph18115597 [pii]
AID - ijerph-18-05597 [pii]
AID - 10.3390/ijerph18115597 [doi]
PST - epublish
SO  - Int J Environ Res Public Health. 2021 May 24;18(11):5597. doi: 
      10.3390/ijerph18115597.