Electromyographic Diaphragm and Electrocardiographic Signal Analysis for Weaning Outcome Classification in Mechanically Ventilated Patients
Open Access
Abstract
Early prediction of weaning outcomes in mechanically ventilated patients has significant potential to influence the duration of treatment as well as associated morbidity and mortality. This study aimed to investigate the utility of signal analysis using electromyographic diaphragm (EMG) and electrocardiography (ECG) signals to classify the success or failure of weaning in mechanically ventilated patients. Electromyographic signals of 40 subjects were recorded using 5-channel surface electrodes placed around the diaphragm muscle, along with an ECG recording through a 3-lead Holter system during extubation. EMG and ECG signals were recorded from mechanically ventilated patients undergoing weaning trials. Linear and nonlinear signal analysis techniques were used to assess the interaction between diaphragm muscle activity and cardiac activity. Supervised machine learning algorithms were then used to classify the weaning outcomes. The study revealed clear differences in diaphragmatic and cardiac patterns between patients who succeeded and failed in the weaning trials. Successful weaning was characterised by a higher ECG-derived respiration amplitude, whereas failed weaning was characterised by an elevated EMG amplitude. Furthermore, successful weaning exhibited greater oscillations in diaphragmatic muscle activity. Spectral analysis and parameter extraction identified 320 parameters, of which 43 were significant predictors of weaning outcomes. Using seven of these parameters, the Naive Bayes classifier demonstrated high accuracy in classifying weaning outcomes. Surface electromyographic and electrocardiographic signal analyses can predict weaning outcomes in mechanically ventilated patients. This approach could facilitate the early identification of patients at risk of weaning failure, allowing for improved clinical management.Keywords
Funding Information
- Ministerio de Ciencia e Innovación (PID2021-126455OB-I00 MCIN/AEI/FEDER)
- Secretaria d’Universitats i Recerca de la Generalitat de Catalunya (GRC 2021 SGR 01390)
- CERCA Program/Generalitat de Catalunya
This publication has 50 references indexed in Scilit:
- Adherence to lung protective mechanical ventilation in patients admitted to a surgical intensive care unit and the associated increased mortalityHeliyon, 2024
- Integrating convolutional neural networks, kNN, and Bayesian optimization for efficient diagnosis of Alzheimer's disease in magnetic resonance imagesBiomedical Signal Processing and Control, 2022
- Bayesian optimization of multiclass SVM for efficient diagnosis of erythemato-squamous diseasesBiomedical Signal Processing and Control, 2022
- Adaptive thresholding technique based classification of red blood cell and sickle cell using Naïve Bayes Classifier and K-nearest neighbor classifierBiomedical Signal Processing and Control, 2021
- Surface electromyography based muscle fatigue detection using high-resolution time-frequency methods and machine learning algorithmsComputer Methods and Programs in Biomedicine, 2018
- Time-varying signal analysis to detect high-altitude periodic breathing in climbers ascending to extreme altitudeMedical & Biological Engineering & Computing, 2015
- Enhancement of low sampling frequency recordings for ECG biometric matching using interpolationComputer Methods and Programs in Biomedicine, 2013
- Diaphragm electromyographic activity as a predictor of weaning failureIntensive Care Medicine, 2012
- Classification of complete blood count and haemoglobin typing data by a C4.5 decision tree, a naïve Bayes classifier and a multilayer perceptron for thalassaemia screeningBiomedical Signal Processing and Control, 2012
- Surface EMG based muscle fatigue evaluation in biomechanicsClinical Biomechanics, 2009