A machine learning model for real-time asynchronous breathing monitoring

The occurrence of asynchronous breathing (AB) during mechanical ventilation (MV) can have detrimental effect towards a patient's recovery. Hence, it is essential to develop an algorithm to automate AB detection in real-time. In this study, a method for AB detection using machine learning, in pa...

Full description

Bibliographic Details
Main Authors:	Loo, Nienloong, Chiew, Y. S., Tan, C. P., Arunachalam, Ganesaramachandran, Md Ralib, Azrina, Mat Nor, Mohd Basri
Format:	Article
Language:	English English
Published:	Elsevier B.V. 2018
Subjects:	R Medicine (General) RC Internal medicine RC803 Specialties of Internal Medicine-Diseases of The Digestive System. Gastroenterology RD81 Anesthesiology
Online Access:	http://irep.iium.edu.my/70025/ http://irep.iium.edu.my/70025/ http://irep.iium.edu.my/70025/ http://irep.iium.edu.my/70025/1/70025_A%20MACHINE%20LEARNING%20MODEL%20FOR%20REAL-TIME%20_article.pdf http://irep.iium.edu.my/70025/2/70025_A%20MACHINE%20LEARNING%20MODEL%20FOR%20REAL-TIME%20_scopus.pdf

id	iium-70025
recordtype	eprints
spelling	iium-700252019-01-23T07:37:38Z http://irep.iium.edu.my/70025/ A machine learning model for real-time asynchronous breathing monitoring Loo, Nienloong Chiew, Y. S. Tan, C. P. Arunachalam, Ganesaramachandran Md Ralib, Azrina Mat Nor, Mohd Basri R Medicine (General) RC Internal medicine RC803 Specialties of Internal Medicine-Diseases of The Digestive System. Gastroenterology RD81 Anesthesiology The occurrence of asynchronous breathing (AB) during mechanical ventilation (MV) can have detrimental effect towards a patient's recovery. Hence, it is essential to develop an algorithm to automate AB detection in real-time. In this study, a method for AB detection using machine learning, in particular, Convolutional Neural Network, (CNN), is presented and its performance in identifying AB when trained with different amount of training datasets and different types of training datasets is evaluated and compared between standard manual detection. A total of 486,200 breaths were analyzed in this study. It was found that the CNN algorithm achieved 69.4% sensitivity and 37.1% specificity when trained with 2000 AB cycles and 1000 normal breathing (NB) cycles; however, when it was trained with 5500 AB and 5500 NB, the CNN achieved 96.9% sensitivity and 63.7% specificity. The experimental results also indicate that the CNN was trained with modified images (region under the curve) CNN yielded sensitivity of 98.5% and specificity of 89.4% as opposed to sensitivity of 25.3% and 83.9% specificity when trained with line graph instead. Therefore the proposed method can potentially provide real-time assessment and information for the clinicians. Elsevier B.V. 2018 Article NonPeerReviewed application/pdf en http://irep.iium.edu.my/70025/1/70025_A%20MACHINE%20LEARNING%20MODEL%20FOR%20REAL-TIME%20_article.pdf application/pdf en http://irep.iium.edu.my/70025/2/70025_A%20MACHINE%20LEARNING%20MODEL%20FOR%20REAL-TIME%20_scopus.pdf Loo, Nienloong and Chiew, Y. S. and Tan, C. P. and Arunachalam, Ganesaramachandran and Md Ralib, Azrina and Mat Nor, Mohd Basri (2018) A machine learning model for real-time asynchronous breathing monitoring. IFAC-PapersOnLine, 51 (27). pp. 378-383. ISSN 2405-8963 https://reader.elsevier.com/reader/sd/pii/S2405896318333196?token=6A4211F58F309EFCB97F3CCDD97FD990729A8D8A00F3E9C219E972976D8AAC2FB4CCEADC4E650E2C68D6E8E822A41582 10.1016/j.ifacol.2018.11.610
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English English
topic	R Medicine (General) RC Internal medicine RC803 Specialties of Internal Medicine-Diseases of The Digestive System. Gastroenterology RD81 Anesthesiology
spellingShingle	R Medicine (General) RC Internal medicine RC803 Specialties of Internal Medicine-Diseases of The Digestive System. Gastroenterology RD81 Anesthesiology Loo, Nienloong Chiew, Y. S. Tan, C. P. Arunachalam, Ganesaramachandran Md Ralib, Azrina Mat Nor, Mohd Basri A machine learning model for real-time asynchronous breathing monitoring
description	The occurrence of asynchronous breathing (AB) during mechanical ventilation (MV) can have detrimental effect towards a patient's recovery. Hence, it is essential to develop an algorithm to automate AB detection in real-time. In this study, a method for AB detection using machine learning, in particular, Convolutional Neural Network, (CNN), is presented and its performance in identifying AB when trained with different amount of training datasets and different types of training datasets is evaluated and compared between standard manual detection. A total of 486,200 breaths were analyzed in this study. It was found that the CNN algorithm achieved 69.4% sensitivity and 37.1% specificity when trained with 2000 AB cycles and 1000 normal breathing (NB) cycles; however, when it was trained with 5500 AB and 5500 NB, the CNN achieved 96.9% sensitivity and 63.7% specificity. The experimental results also indicate that the CNN was trained with modified images (region under the curve) CNN yielded sensitivity of 98.5% and specificity of 89.4% as opposed to sensitivity of 25.3% and 83.9% specificity when trained with line graph instead. Therefore the proposed method can potentially provide real-time assessment and information for the clinicians.
format	Article
author	Loo, Nienloong Chiew, Y. S. Tan, C. P. Arunachalam, Ganesaramachandran Md Ralib, Azrina Mat Nor, Mohd Basri
author_facet	Loo, Nienloong Chiew, Y. S. Tan, C. P. Arunachalam, Ganesaramachandran Md Ralib, Azrina Mat Nor, Mohd Basri
author_sort	Loo, Nienloong
title	A machine learning model for real-time asynchronous breathing monitoring
title_short	A machine learning model for real-time asynchronous breathing monitoring
title_full	A machine learning model for real-time asynchronous breathing monitoring
title_fullStr	A machine learning model for real-time asynchronous breathing monitoring
title_full_unstemmed	A machine learning model for real-time asynchronous breathing monitoring
title_sort	machine learning model for real-time asynchronous breathing monitoring
publisher	Elsevier B.V.
publishDate	2018
url	http://irep.iium.edu.my/70025/ http://irep.iium.edu.my/70025/ http://irep.iium.edu.my/70025/ http://irep.iium.edu.my/70025/1/70025_A%20MACHINE%20LEARNING%20MODEL%20FOR%20REAL-TIME%20_article.pdf http://irep.iium.edu.my/70025/2/70025_A%20MACHINE%20LEARNING%20MODEL%20FOR%20REAL-TIME%20_scopus.pdf
first_indexed	2023-09-18T21:39:25Z
last_indexed	2023-09-18T21:39:25Z
_version_	1777413039192014848

A machine learning model for real-time asynchronous breathing monitoring

Similar Items