PMID- 37989268
OWN - NLM
STAT- MEDLINE
DCOM- 20240301
LR  - 20240301
IS  - 2093-5978 (Electronic)
IS  - 2093-596X (Print)
IS  - 2093-596X (Linking)
VI  - 39
IP  - 1
DP  - 2024 Feb
TI  - Prediction of Cardiovascular Complication in Patients with Newly Diagnosed Type 2 
      Diabetes Using an XGBoost/GRU-ODE-Bayes-Based Machine-Learning Algorithm.
PG  - 176-185
LID - 10.3803/EnM.2023.1739 [doi]
AB  - BACKGRUOUND: Cardiovascular disease is life-threatening yet preventable for 
      patients with type 2 diabetes mellitus (T2DM). Because each patient with T2DM has 
      a different risk of developing cardiovascular complications, the accurate 
      stratification of cardiovascular risk is critical. In this study, we proposed 
      cardiovascular risk engines based on machine-learning algorithms for newly 
      diagnosed T2DM patients in Korea. METHODS: To develop the machine-learning-based 
      cardiovascular disease engines, we retrospectively analyzed 26,166 newly 
      diagnosed T2DM patients who visited Seoul St. Mary's Hospital between July 2009 
      and April 2019. To accurately measure diabetes-related cardiovascular events, we 
      designed a buffer (1 year), an observation (1 year), and an outcome period (5 
      years). The entire dataset was split into training and testing sets in an 8:2 
      ratio, and this procedure was repeated 100 times. The area under the receiver 
      operating characteristic curve (AUROC) was calculated by 10-fold cross-validation 
      on the training dataset. RESULTS: The machine-learning-based risk engines (AUROC 
      XGBoost=0.781+/-0.014 and AUROC gated recurrent unit [GRU]-ordinary differential 
      equation [ODE]-Bayes=0.812+/-0.016) outperformed the conventional regression-based 
      model (AUROC=0.723+/- 0.036). CONCLUSION: GRU-ODE-Bayes-based cardiovascular risk 
      engine is highly accurate, easily applicable, and can provide valuable 
      information for the individualized treatment of Korean patients with newly 
      diagnosed T2DM.
FAU - Lee, Joonyub
AU  - Lee J
AD  - Division of Endocrinology and Metabolism, Department of Internal Medicine, Seoul 
      St. Mary's Hospital, College of Medicine, The Catholic University of Korea, 
      Seoul, Korea.
FAU - Choi, Yera
AU  - Choi Y
AD  - NAVER CLOVA AI Lab, Seongnam, Korea.
FAU - Ko, Taehoon
AU  - Ko T
AD  - Department of Medical Informatics, College of Medicine, The Catholic University 
      of Korea, Seoul, Korea.
FAU - Lee, Kanghyuck
AU  - Lee K
AD  - Department of Medical Informatics, College of Medicine, The Catholic University 
      of Korea, Seoul, Korea.
AD  - Department of Biomedicine and Health Sciences, College of Medicine, The Catholic 
      University of Korea, Seoul, Korea.
FAU - Shin, Juyoung
AU  - Shin J
AD  - Division of Endocrinology and Metabolism, Department of Internal Medicine, Seoul 
      St. Mary's Hospital, College of Medicine, The Catholic University of Korea, 
      Seoul, Korea.
AD  - Department of Medical Informatics, College of Medicine, The Catholic University 
      of Korea, Seoul, Korea.
AD  - Health Promotion Center, Seoul St. Mary's Hospital, Seoul, Korea.
FAU - Kim, Hun-Sung
AU  - Kim HS
AD  - Division of Endocrinology and Metabolism, Department of Internal Medicine, Seoul 
      St. Mary's Hospital, College of Medicine, The Catholic University of Korea, 
      Seoul, Korea.
AD  - Department of Medical Informatics, College of Medicine, The Catholic University 
      of Korea, Seoul, Korea.
LA  - eng
PT  - Journal Article
DEP - 20231121
PL  - Korea (South)
TA  - Endocrinol Metab (Seoul)
JT  - Endocrinology and metabolism (Seoul, Korea)
JID - 101554139
SB  - IM
MH  - Humans
MH  - *Cardiovascular Diseases/diagnosis/etiology
MH  - *Diabetes Mellitus, Type 2/complications
MH  - Bayes Theorem
MH  - Retrospective Studies
MH  - Algorithms
MH  - Machine Learning
PMC - PMC10901655
OTO - NOTNLM
OT  - Cardiovascular diseases
OT  - Diabetes mellitus, type 2
OT  - Korea
OT  - Machine learning
COIS- CONFLICTS OF INTEREST This study was supported by the Daewoong Pharmaceutical 
      company. The opinions expressed in this paper are those of the authors and do not 
      necessarily represent those of Daewoong Pharmaceutical company. While this study 
      received technical guidance from NAVER CLOVA AI Lab for the development of an AI 
      prediction model, it had no effect on the research outcomes.
EDAT- 2023/11/22 00:42
MHDA- 2024/03/01 06:44
PMCR- 2024/02/01
CRDT- 2023/11/21 19:46
PHST- 2023/05/16 00:00 [received]
PHST- 2023/08/09 00:00 [accepted]
PHST- 2024/03/01 06:44 [medline]
PHST- 2023/11/22 00:42 [pubmed]
PHST- 2023/11/21 19:46 [entrez]
PHST- 2024/02/01 00:00 [pmc-release]
AID - EnM.2023.1739 [pii]
AID - enm-2023-1739 [pii]
AID - 10.3803/EnM.2023.1739 [doi]
PST - ppublish
SO  - Endocrinol Metab (Seoul). 2024 Feb;39(1):176-185. doi: 10.3803/EnM.2023.1739. 
      Epub 2023 Nov 21.