PMID- 37401435
OWN - NLM
STAT- MEDLINE
DCOM- 20230705
LR  - 20230705
IS  - 1522-6662 (Electronic)
IS  - 1098-3511 (Linking)
VI  - 26
IP  - 3
DP  - 2023 Jun 14
TI  - Application of Machine Learning Algorithms to Predict New-Onset Postoperative 
      Atrial Fibrillation and Identify Risk Factors Following Isolated Valve Surgery.
PG  - E255-E263
LID - 10.1532/hsf.5341 [doi]
AB  - BACKGROUND: New-onset postoperative atrial fibrillation (POAF) is the most common 
      complication after valvular surgery, but its etiology and risk factors are 
      incompletely understood. This study investigates the benefits of machine learning 
      methods in risk prediction and in identifying relative perioperative variables 
      for POAF after valve surgery. METHODS: This retrospective study involved 847 
      patients, who underwent isolated valve surgery from January 2018 to September 
      2021 in our institution. We used machine learning algorithms to predict new-onset 
      postoperative atrial fibrillation and to select relatively important variables 
      from a set of 123 preoperative characteristics and intraoperative information. 
      RESULTS: The support vector machine (SVM) model demonstrated the best area under 
      the receiver operating characteristic (AUC) value of 0.786, followed by logistic 
      regression (AUC = 0.745) and the Complement Naive Bayes (CNB) model (AUC = 
      0.672). Left atrium diameter, age, estimated glomerular filtration rate (eGFR), 
      duration of cardiopulmonary bypass, New York Heart Association (NYHA) class 
      III-IV, and preoperative hemoglobin were high-ranked variables. CONCLUSIONS: Risk 
      models based on machine learning algorithms may be superior to traditional 
      models, which were primarily based on logistic algorithms to predict the 
      occurrence of POAF after valve surgery. Further prospective multicenter studies 
      are needed to confirm the performance of SVM in predicting POAF.
FAU - Zhu, Siming
AU  - Zhu S
AD  - Medical School of Chinese PLA, 100853 Beijing, China. 1440994567@qq.com.
FAU - Che, Hebin
AU  - Che H
AD  - Department of Cardiovascular Surgery, The First Medical Center of Chinese PLA 
      General Hospital, 100853 Beijing, China. maravich07@126.com.
FAU - Fan, Yunlong
AU  - Fan Y
AD  - Medical School of Chinese PLA, 100853 Beijing, China. zhaoxiaoli15@163.com.
FAU - Jiang, Shengli
AU  - Jiang S
AD  - Medical School of Chinese PLA, 100853 Beijing, China; Department of 
      Cardiovascular Surgery, The First Medical Center of Chinese PLA General Hospital, 
      100853 Beijing, China. jiangsl301@sina.com.
LA  - eng
PT  - Journal Article
DEP - 20230614
PL  - United States
TA  - Heart Surg Forum
JT  - The heart surgery forum
JID - 100891112
SB  - IM
MH  - Humans
MH  - *Atrial Fibrillation/diagnosis/etiology
MH  - Retrospective Studies
MH  - Bayes Theorem
MH  - Predictive Value of Tests
MH  - Risk Factors
MH  - Postoperative Complications/epidemiology
EDAT- 2023/07/04 06:42
MHDA- 2023/07/05 06:42
CRDT- 2023/07/04 04:32
PHST- 2022/12/01 00:00 [received]
PHST- 2023/01/30 00:00 [accepted]
PHST- 2023/07/05 06:42 [medline]
PHST- 2023/07/04 06:42 [pubmed]
PHST- 2023/07/04 04:32 [entrez]
AID - 10.1532/hsf.5341 [doi]
PST - epublish
SO  - Heart Surg Forum. 2023 Jun 14;26(3):E255-E263. doi: 10.1532/hsf.5341.