PMID- 35743691
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20220716
IS  - 2075-4426 (Print)
IS  - 2075-4426 (Electronic)
IS  - 2075-4426 (Linking)
VI  - 12
IP  - 6
DP  - 2022 May 31
TI  - Predicting the Risk of Incident Type 2 Diabetes Mellitus in Chinese Elderly Using 
      Machine Learning Techniques.
LID - 10.3390/jpm12060905 [doi]
LID - 905
AB  - Early identification of individuals at high risk of diabetes is crucial for 
      implementing early intervention strategies. However, algorithms specific to 
      elderly Chinese adults are lacking. The aim of this study is to build effective 
      prediction models based on machine learning (ML) for the risk of type 2 diabetes 
      mellitus (T2DM) in Chinese elderly. A retrospective cohort study was conducted 
      using the health screening data of adults older than 65 years in Wuhan, China 
      from 2018 to 2020. With a strict data filtration, 127,031 records from the 
      eligible participants were utilized. Overall, 8298 participants were diagnosed 
      with incident T2DM during the 2-year follow-up (2019-2020). The dataset was 
      randomly split into training set (n = 101,625) and test set (n = 25,406). We 
      developed prediction models based on four ML algorithms: logistic regression 
      (LR), decision tree (DT), random forest (RF), and extreme gradient boosting 
      (XGBoost). Using LASSO regression, 21 prediction features were selected. The 
      Random under-sampling (RUS) was applied to address the class imbalance, and the 
      Shapley Additive Explanations (SHAP) was used to calculate and visualize feature 
      importance. Model performance was evaluated by the area under the receiver 
      operating characteristic curve (AUC), sensitivity, specificity, and accuracy. The 
      XGBoost model achieved the best performance (AUC = 0.7805, sensitivity = 0.6452, 
      specificity = 0.7577, accuracy = 0.7503). Fasting plasma glucose (FPG), 
      education, exercise, gender, and waist circumference (WC) were the top five 
      important predictors. This study showed that XGBoost model can be applied to 
      screen individuals at high risk of T2DM in the early phrase, which has the strong 
      potential for intelligent prevention and control of diabetes. The key features 
      could also be useful for developing targeted diabetes prevention interventions.
FAU - Liu, Qing
AU  - Liu Q
AUID- ORCID: 0000-0003-2028-973X
AD  - Department of Epidemiology, School of Public Health, Wuhan University, Wuhan 
      430071, China.
FAU - Zhang, Miao
AU  - Zhang M
AUID- ORCID: 0000-0002-8200-1933
AD  - Department of Epidemiology, School of Public Health, Wuhan University, Wuhan 
      430071, China.
FAU - He, Yifeng
AU  - He Y
AD  - School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China.
FAU - Zhang, Lei
AU  - Zhang L
AD  - School of Mathematics and Statistics, Wuhan University, Wuhan 430070, China.
FAU - Zou, Jingui
AU  - Zou J
AD  - School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China.
FAU - Yan, Yaqiong
AU  - Yan Y
AD  - Wuhan Center for Disease Control and Prevention, Wuhan 430015, China.
FAU - Guo, Yan
AU  - Guo Y
AD  - Wuhan Center for Disease Control and Prevention, Wuhan 430015, China.
LA  - eng
GR  - K20-1602-011/Wuhan Center for Disease Control and Prevention/
GR  - WJ2021M137/Health Commission of Hubei Province/
PT  - Journal Article
DEP - 20220531
PL  - Switzerland
TA  - J Pers Med
JT  - Journal of personalized medicine
JID - 101602269
PMC - PMC9224915
OTO - NOTNLM
OT  - Chinese elderly
OT  - machine learning
OT  - prediction model
OT  - type 2 diabetes mellitus (T2DM)
COIS- The authors declare no conflict of interest.
EDAT- 2022/06/25 06:00
MHDA- 2022/06/25 06:01
PMCR- 2022/05/31
CRDT- 2022/06/24 01:26
PHST- 2022/04/09 00:00 [received]
PHST- 2022/05/21 00:00 [revised]
PHST- 2022/05/27 00:00 [accepted]
PHST- 2022/06/24 01:26 [entrez]
PHST- 2022/06/25 06:00 [pubmed]
PHST- 2022/06/25 06:01 [medline]
PHST- 2022/05/31 00:00 [pmc-release]
AID - jpm12060905 [pii]
AID - jpm-12-00905 [pii]
AID - 10.3390/jpm12060905 [doi]
PST - epublish
SO  - J Pers Med. 2022 May 31;12(6):905. doi: 10.3390/jpm12060905.