Long-term single-lead electrocardiogram monitoring to detect new-onset postoperative atrial fibrillation in patients after cardiac surgery

Abstract

BackgroundPostoperative atrial fibrillation (POAF) is often associated with serious complications. In this study, we collected long-term single-lead electrocardiograms (ECGs) of patients with preoperative sinus rhythm to build statistical models and machine learning models to predict POAF.MethodsAll patients with preoperative sinus rhythm who underwent cardiac surgery were enrolled and we collected long-term ECG data 24 h before surgery and 7 days after surgery by single-lead ECG. The patients were divided into a POAF group a no-POAF group. A clinical model and a clinical + ECG model were constructed. The ECG parameters were designed and support vector machine (SVM) was selected to build a machine learning model and evaluate its prediction efficiency.ResultsA total of 100 patients were included. The detection rate of POAF in long-term ECG monitoring was 31% and that in conventional monitoring was 19%. We calculated 7 P-wave parameters, Pmax (167 ± 31 ms vs. 184 ± 37 ms, P = 0.018), Pstd (15 ± 7 vs. 19 ± 11, P = 0.031), and PWd (62 ± 28 ms vs. 80 ± 35 ms, P = 0.008) were significantly different. The AUC of the clinical model (sex, age, LA diameter, GFR, mechanical ventilation time) was 0.86. Clinical + ECG model (sex, age, LA diameter, GFR, mechanical ventilation time, Pmax, Pstd, PWd), AUC was 0.89. In the machine learning model, the accuracy (Ac) of the train set and test set was above 80 and 60%, respectively.ConclusionLong-term ECG monitoring could significantly improve the detection rate of POAF. The clinical + ECG model and the machine learning model based on P-wave parameters can predict POAF.

Algorithms for automated diagnosis of cardiovascular diseases based on ECG data: A comprehensive systematic review

“…The analysis of ECG variables in the current study focused only on those parameters that are easily assessed in clinical practice; thus, some important but less frequently used variables might have been omitted. The proposed model showed high sensitivity for HCM screening, at the cost of a high false-positive rate He et al [ 43 ] The results of this study showed that long-term ECG monitoring could significantly improve the detection rate of postoperative atrial fibrillation. The model combining P wave parameters and clinical data performed better in predicting postoperative atrial fibrillation.…”

“…He et al [ 43 ] collected long-term ECG data 24 h before surgery and 7 days after surgery by single-lead ECG from 100 patients with preoperative sinus rhythm who underwent cardiac surgery. The patients were divided into a Postoperative atrial fibrillation (POAF) group and a no-POAF group.…”

“… 12-Lead ECG CNN, SHAP Patient-independent Cardiovascular diseases Geweid et al [ 40 ] 2022 Michigan (USA) Journal article 2017 Physionet/CinC challenge dataset [ 41 ] (8258 recordings) A method based on a Hybrid Approach of Dual Support Vector Machine is used for the detection of atrial fibrillation 1-Lead ECG SVM Patient-independent Atrial Fibrillation Guo et al [ 42 ] 2022 Xian (China) Journal article 423 subjects from the International Cooperation Center for Hypertrophic Cardiomyopathy of Xijing Hospital This work aimed to develop a pragmatic prediction model based on the most common ECG features to screen for Hypertrophic cardiomyopathy (HCM). 12-Lead ECG LASSO, MLR Patient-independent Hypertrophic Cardiomyopathy He et al [ 43 ] 2022 Chengdu (China) Journal article 100 patients from Department of Cardiovascular, West China Hospital of Sichuan University This study aimed to build statistical models and machine learning models based on P-wave parameters to predict Postoperative Atrial Fibrillation (POAF). 12-Lead ECG SVM Patient-independent Postoperative Atrial Fibrillation Hsu et al [ 44 ] 2022 Hualien (Taiwan) Journal article A population of 2,206 military males were obtained from the cardiorespiratory health in eastern armed forces study (CHIEF Heart Study) [ 45 , 46 ] This study proposed a machine learning method for electrocardiographic features to identify Left Atrial Enlargement in young adults.…”

Artificial intelligence for atrial fibrillation detection, prediction, and treatment: A systematic review of the last decade (2013–2023)

“…Most ML models used ECG input signal for AF detection (Agliari et al, 2020; Alhusseini et al, 2020; Buscema et al, 2020; Domazetoski et al, 2022; K. He et al, 2022; Huang et al, 2021; Nickelsen et al, 2017; Pérez‐Valero et al, 2019; Rad et al, 2021; Rouhi et al, 2021; Schaefer et al, 2014; Wesselius et al, 2022; Yao et al, 2021). Abdul‐Kadir et al (2016) developed an AF recognition method based on dynamic ECG features extracted using the concept of a second‐order dynamic system.…”

“…Most ML models used ECG input signal for AF detection (Agliari et al, 2020;Alhusseini et al, 2020;Buscema et al, 2020;Domazetoski et al, 2022;K. He et al, 2022;Huang et al, 2021;Nickelsen et al, 2017;Pérez-Valero et al, 2019;Rad et al, 2021;Rouhi et al, 2021;Schaefer et al, 2014;Wesselius et al, 2022;Yao et al, 2021).…”