PMID- 35340868
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20220329
IS  - 1792-1015 (Electronic)
IS  - 1792-0981 (Print)
IS  - 1792-0981 (Linking)
VI  - 23
IP  - 4
DP  - 2022 Apr
TI  - Application of machine learning tools: Potential and useful approach for the 
      prediction of type 2 diabetes mellitus based on the gut microbiome profile.
PG  - 305
LID - 10.3892/etm.2022.11234 [doi]
LID - 305
AB  - The gut microbiota plays an important role in the regulation of the immune system 
      and the metabolism of the host. The aim of the present study was to characterize 
      the gut microbiota of patients with type 2 diabetes mellitus (T2DM). A total of 
      118 participants with newly diagnosed T2DM and 89 control subjects were recruited 
      in the present study; six clinical parameters were collected and the quantity of 
      10 different types of bacteria was assessed in the fecal samples using 
      quantitative PCR. Taking into consideration the six clinical variables and the 
      quantity of the 10 different bacteria, 3 predictive models were established in 
      the training set and test set, and evaluated using a confusion matrix, area under 
      the receiver operating characteristic curve (AUC) values, sensitivity (recall), 
      specificity, accuracy, positive predictive value and negative predictive value 
      (npv). The abundance of Bacteroides, Eubacterium rectale and Roseburia 
      inulinivorans was significantly lower in the T2DM group compared with the control 
      group. However, the abundance of Enterococcus was significantly higher in the 
      T2DM group compared with the control group. In addition, Faecalibacterium 
      prausnitzii, Enterococcus and Roseburia inulinivorans were significantly 
      associated with sex status while Bacteroides, Bifidobacterium, Enterococcus and 
      Roseburia inulinivorans were significantly associated with older age. In the 
      training set, among the three models, support vector machine (SVM) and XGboost 
      models obtained AUC values of 0.72 and 0.70, respectively. In the test set, only 
      SVM obtained an AUC value of 0.77, and the precision and specificity were both 
      above 0.77, whereas the accuracy, recall and npv were above 0.60. Furthermore, 
      Bifidobacterium, age and Roseburia inulinivorans played pivotal roles in the 
      model. In conclusion, the SVM model exhibited the highest overall predictive 
      power, thus the combined use of machine learning tools with gut microbiome 
      profiling may be a promising approach for improving early prediction of T2DM in 
      the near feature.
CI  - Copyright: (c) Ge et al.
FAU - Ge, Xiaochun
AU  - Ge X
AD  - Department of Endocrinology, Affiliated Hospital of Chengde Medical University, 
      Chengde, Hebei 067000, P.R. China.
FAU - Zhang, Aimin
AU  - Zhang A
AD  - Department of Endocrinology, Affiliated Hospital of Chengde Medical University, 
      Chengde, Hebei 067000, P.R. China.
FAU - Li, Lihui
AU  - Li L
AD  - Department of Endocrinology, Affiliated Hospital of Chengde Medical University, 
      Chengde, Hebei 067000, P.R. China.
FAU - Sun, Qitian
AU  - Sun Q
AD  - Department of Endocrinology, Affiliated Hospital of Chengde Medical University, 
      Chengde, Hebei 067000, P.R. China.
FAU - He, Jianqiu
AU  - He J
AD  - Department of Endocrinology, Affiliated Hospital of Chengde Medical University, 
      Chengde, Hebei 067000, P.R. China.
FAU - Wu, Yu
AU  - Wu Y
AD  - Shanghai Biotecan Pharmaceuticals Co., Ltd., Shanghai 201204, P.R. China.
AD  - Shanghai Zhangjiang Institute of Medical Innovation, Shanghai 201204, P.R. China.
FAU - Tan, Rundong
AU  - Tan R
AD  - Shanghai Biotecan Pharmaceuticals Co., Ltd., Shanghai 201204, P.R. China.
AD  - Shanghai Zhangjiang Institute of Medical Innovation, Shanghai 201204, P.R. China.
FAU - Pan, Yingxia
AU  - Pan Y
AD  - Shanghai Biotecan Pharmaceuticals Co., Ltd., Shanghai 201204, P.R. China.
AD  - Shanghai Zhangjiang Institute of Medical Innovation, Shanghai 201204, P.R. China.
FAU - Zhao, Jiangman
AU  - Zhao J
AD  - Shanghai Biotecan Pharmaceuticals Co., Ltd., Shanghai 201204, P.R. China.
AD  - Shanghai Zhangjiang Institute of Medical Innovation, Shanghai 201204, P.R. China.
FAU - Xu, Yue
AU  - Xu Y
AD  - Shanghai Biotecan Pharmaceuticals Co., Ltd., Shanghai 201204, P.R. China.
AD  - Shanghai Zhangjiang Institute of Medical Innovation, Shanghai 201204, P.R. China.
FAU - Tang, Hui
AU  - Tang H
AD  - Shanghai Biotecan Pharmaceuticals Co., Ltd., Shanghai 201204, P.R. China.
AD  - Shanghai Zhangjiang Institute of Medical Innovation, Shanghai 201204, P.R. China.
FAU - Gao, Yu
AU  - Gao Y
AD  - Department of Endocrinology, Affiliated Hospital of Chengde Medical University, 
      Chengde, Hebei 067000, P.R. China.
LA  - eng
PT  - Journal Article
DEP - 20220223
PL  - Greece
TA  - Exp Ther Med
JT  - Experimental and therapeutic medicine
JID - 101531947
PMC - PMC8931625
OTO - NOTNLM
OT  - Bifidobacterium
OT  - Roseburiainulinivorans
OT  - gut microbiome
OT  - machine learning tools
OT  - type 2 diabetes mellitus
COIS- The authors declare that they have no competing interests.
EDAT- 2022/03/29 06:00
MHDA- 2022/03/29 06:01
PMCR- 2022/02/23
CRDT- 2022/03/28 05:18
PHST- 2021/10/11 00:00 [received]
PHST- 2022/02/09 00:00 [accepted]
PHST- 2022/03/28 05:18 [entrez]
PHST- 2022/03/29 06:00 [pubmed]
PHST- 2022/03/29 06:01 [medline]
PHST- 2022/02/23 00:00 [pmc-release]
AID - ETM-23-4-11234 [pii]
AID - 10.3892/etm.2022.11234 [doi]
PST - ppublish
SO  - Exp Ther Med. 2022 Apr;23(4):305. doi: 10.3892/etm.2022.11234. Epub 2022 Feb 23.