A Technique for Monitoring Mechanically Ventilated Patient Lung Conditions

Background: Mechanical ventilation is a critical but resource-intensive treatment. Automated tools are common in screening diagnostics, whereas real-time, continuous trend analysis in mechanical ventilation remains rare. Current techniques for monitoring lung conditions are often invasive, lack accu...

Full description

Saved in:
Bibliographic Details
Main Authors: Pieter Marx, Henri Marais
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/14/23/2616
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846124344078499840
author Pieter Marx
Henri Marais
author_facet Pieter Marx
Henri Marais
author_sort Pieter Marx
collection DOAJ
description Background: Mechanical ventilation is a critical but resource-intensive treatment. Automated tools are common in screening diagnostics, whereas real-time, continuous trend analysis in mechanical ventilation remains rare. Current techniques for monitoring lung conditions are often invasive, lack accuracy, and fail to isolate respiratory resistance—making them impractical for continuous monitoring and diagnosis. To address this challenge, we propose an automated, non-invasive condition monitoring method to support pulmonologists. Methods: Our method leverages ventilation waveform time-series data in controlled modes to monitor lung conditions automatically and non-invasively on a breath-by-breath basis while accurately isolating respiratory resistance. Results: Using statistical classification and regression models, the approach achieves 99.1% accuracy for ventilation mode classification, 97.5% accuracy for feature extraction, and 99.0% for predicting mechanical lung parameters. The models are both computationally efficient (720 K predictions per second per core) and lightweight (24.5 MB). Conclusions: By storing breath-by-breath predictions, pulmonologists can access a high-resolution trend of lung conditions, gaining clear insights into sudden changes without speculation and streamlining diagnosis and decision-making. The deployment of this solution could expand domain knowledge, enhance the understanding of patient conditions, and enable real-time dashboards for parallel monitoring, helping to prioritize patients and optimize resource use, which is especially valuable during pandemics.
format Article
id doaj-art-258d2c1bdbd24cdd815b6afd818d026c
institution Kabale University
issn 2075-4418
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-258d2c1bdbd24cdd815b6afd818d026c2024-12-13T16:24:24ZengMDPI AGDiagnostics2075-44182024-11-011423261610.3390/diagnostics14232616A Technique for Monitoring Mechanically Ventilated Patient Lung ConditionsPieter Marx0Henri Marais1Faculty of Engineering, North-West University, Potchefstroom 2531, South AfricaFaculty of Engineering, North-West University, Potchefstroom 2531, South AfricaBackground: Mechanical ventilation is a critical but resource-intensive treatment. Automated tools are common in screening diagnostics, whereas real-time, continuous trend analysis in mechanical ventilation remains rare. Current techniques for monitoring lung conditions are often invasive, lack accuracy, and fail to isolate respiratory resistance—making them impractical for continuous monitoring and diagnosis. To address this challenge, we propose an automated, non-invasive condition monitoring method to support pulmonologists. Methods: Our method leverages ventilation waveform time-series data in controlled modes to monitor lung conditions automatically and non-invasively on a breath-by-breath basis while accurately isolating respiratory resistance. Results: Using statistical classification and regression models, the approach achieves 99.1% accuracy for ventilation mode classification, 97.5% accuracy for feature extraction, and 99.0% for predicting mechanical lung parameters. The models are both computationally efficient (720 K predictions per second per core) and lightweight (24.5 MB). Conclusions: By storing breath-by-breath predictions, pulmonologists can access a high-resolution trend of lung conditions, gaining clear insights into sudden changes without speculation and streamlining diagnosis and decision-making. The deployment of this solution could expand domain knowledge, enhance the understanding of patient conditions, and enable real-time dashboards for parallel monitoring, helping to prioritize patients and optimize resource use, which is especially valuable during pandemics.https://www.mdpi.com/2075-4418/14/23/2616classification modelscondition monitoringlungmachine learningmechanical ventilationpulmonary diseases
spellingShingle Pieter Marx
Henri Marais
A Technique for Monitoring Mechanically Ventilated Patient Lung Conditions
Diagnostics
classification models
condition monitoring
lung
machine learning
mechanical ventilation
pulmonary diseases
title A Technique for Monitoring Mechanically Ventilated Patient Lung Conditions
title_full A Technique for Monitoring Mechanically Ventilated Patient Lung Conditions
title_fullStr A Technique for Monitoring Mechanically Ventilated Patient Lung Conditions
title_full_unstemmed A Technique for Monitoring Mechanically Ventilated Patient Lung Conditions
title_short A Technique for Monitoring Mechanically Ventilated Patient Lung Conditions
title_sort technique for monitoring mechanically ventilated patient lung conditions
topic classification models
condition monitoring
lung
machine learning
mechanical ventilation
pulmonary diseases
url https://www.mdpi.com/2075-4418/14/23/2616
work_keys_str_mv AT pietermarx atechniqueformonitoringmechanicallyventilatedpatientlungconditions
AT henrimarais atechniqueformonitoringmechanicallyventilatedpatientlungconditions
AT pietermarx techniqueformonitoringmechanicallyventilatedpatientlungconditions
AT henrimarais techniqueformonitoringmechanicallyventilatedpatientlungconditions