Assessing the Asynchrony Event Based on the Ventilation Mode for Mechanically Ventilated Patients in ICU

Sauki, Nur Sa’adah Muhamad; Damanhuri, Nor Salwa; Othman, Nor Azlan; Meng, Belinda Chong Chiew; Chiew, Yeong Shiong; Nor, Mohd Basri Mat

doi:10.3390/bioengineering8120222

Cited by 6 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BubbleVent, a mechanical ventilator, was manufactured and tested for effective mechanical ventilation and was able to deliver stable PIP and PEEP levels [ 31 ]. For accurate monitoring of respiratory mechanics, a study was successfully completed on a model-based assessment of asynchrony events for mechanically ventilated patients [ 32 ]. A machine learning model was applied and tested with success for parameter estimation for mechanical ventilation [ 33 ].…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study on Predication of Appropriate Mechanical Ventilation Mode through Machine Learning Approach

et al. 2023

View full text Add to dashboard Cite

Ventilation mode is one of the most crucial ventilator settings, selected and set by knowledgeable critical care therapists in a critical care unit. The application of a particular ventilation mode must be patient-specific and patient-interactive. The main aim of this study is to provide a detailed outline regarding ventilation mode settings and determine the best machine learning method to create a deployable model for the appropriate selection of ventilation mode on a per breath basis. Per-breath patient data is utilized, preprocessed and finally a data frame is created consisting of five feature columns (inspiratory and expiratory tidal volume, minimum pressure, positive end-expiratory pressure, and previous positive end-expiratory pressure) and one output column (output column consisted of modes to be predicted). The data frame has been split into training and testing datasets with a test size of 30%. Six machine learning algorithms were trained and compared for performance, based on the accuracy, F1 score, sensitivity, and precision. The output shows that the Random-Forest Algorithm was the most precise and accurate in predicting all ventilation modes correctly, out of the all the machine learning algorithms trained. Thus, the Random-Forest machine learning technique can be utilized for predicting optimal ventilation mode setting, if it is properly trained with the help of the most relevant data. Aside from ventilation mode, control parameter settings, alarm settings and other settings may also be adjusted for the mechanical ventilation process utilizing appropriate machine learning, particularly deep learning approaches.

show abstract

Section: Introductionmentioning

confidence: 99%

A Comparative Study on Predication of Appropriate Mechanical Ventilation Mode through Machine Learning Approach

et al. 2023

View full text Add to dashboard Cite

show abstract

Estimation of Asynchrony Events with Negative Elastance in Spontaneously Breathing Mechanically Ventilated Patients in ICU

Sauki

Damanhuri

Othman

et al. 2022

2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)

View full text Add to dashboard Cite

Classification Type of Asynchrony Breathing Image Using 2-Dimensional Convolutional Neural Network

Muhamad Sauki,

Damanhuri,

Othman

et al. 2023

2023 9th International Conference on Control, Decision and Information Technologies (CoDIT)

View full text Add to dashboard Cite

Asynchrony breathing (AB) refers to a situation where the patient's breathing does not align with the mechanical ventilator (MV), which can have a detrimental effect on the patient's recovery. A few types of AB make it difficult for clinicians to identify and manage MV properly. Hence, there is a need to develop a method that can classify the type of AB in MV patients. In this study, a 2-dimensional (2D) convolutional neural network (CNN) method is presented to classify the type of AB based on the input image of the airway pressure. A total of 866 images of airway pressure were analysed in this study, and 4 types of AB were classified: 1) double triggering (DT); 2) reverse triggering (RT); 3) delayed triggering (DC); and 4) premature cycling (PC). Two types of activation functions for classification purposes, SoftMax and Sigmoid, were compared based on performances. Results show SoftMax produced a higher accuracy of 98.5% with a training dataset of 70% and a testing dataset of 30% of the data. In contrast, the Sigmoid function produced an accuracy of 98.1 % when trained and tested with the same dataset. Furthermore, this 2D-CNN model produced a range of accuracy between 89% and 96% in classifying the type of AB, with the highest accuracy of 96% in classifying DT. Overall, the developed CNN model, based on the input image of airway pressure, accurately extracts critical and unique features to precisely classify various types of AB, which could help clinicians in managing MV patients.

show abstract

Assessing the Asynchrony Event Based on the Ventilation Mode for Mechanically Ventilated Patients in ICU

Cited by 6 publications

References 28 publications

A Comparative Study on Predication of Appropriate Mechanical Ventilation Mode through Machine Learning Approach

A Comparative Study on Predication of Appropriate Mechanical Ventilation Mode through Machine Learning Approach

Estimation of Asynchrony Events with Negative Elastance in Spontaneously Breathing Mechanically Ventilated Patients in ICU

Classification Type of Asynchrony Breathing Image Using 2-Dimensional Convolutional Neural Network

Contact Info

Product

Resources

About