A machine learning method for automatic detection and classification of patient-ventilator asynchrony

Bakkes, Tom; Montree, Roel J. H.; Mischi, Massimo; Mojoli, Francesco; Turco, Simona

doi:10.1109/embc44109.2020.9175796

Cited by 13 publications

(13 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to check whether this approach is successful, we perform several tests on the synthetic data: (1) We check whether the lung model is able to replicate the measured lung mechanics parameters of the different lung conditions; (2) whether the waveforms correspond to clinical data; (3) whether experienced clinicians are able to distinguish the simulations and clinical data; (4) we perform several tests with a machine learning algorithm that had a high performance on clinical data [5].…”

Section: Methodsmentioning

confidence: 99%

“…To classify whether a breath is an asynchrony or a regular breath, the time between the start of patient inspiration and ventilator triggering (start-inspiration delay) and the end of patient inspiration and ventilator cycling (end-inspiration delay) need to fall into certain margins. We employ the same margins as Bakkes et al [5]:…”

Section: Asynchroniesmentioning

confidence: 99%

“…As a last test, we apply the neural network trained on clinical data proposed in Bakkes et al [5] to the synthetic dataset. In the orignal paper [5], the machine learning algorithm was trained and tested on the same (small) labeled clinical dataset. It is therefore not known how well this algorithm generalizes when applied to a different dataset.…”

Section: Validationmentioning

confidence: 99%

“…The algorithm is a one-dimensional version of the U-net architecture and detects the start and end of patient inspiration in unlabeled pressure, flow, and volume waveforms when esophageal pressure is not available. The network consists of four contracting and expanding layers and is trained using the adam optimizer in conjuction with categorical crossentropy as a loss function [5]. 4275 labeled clinical breaths were used to train the network using 300 epochs.…”

Section: Validationmentioning

confidence: 99%

“…Studies have already been conducted on the automated detection of asynchronies [19]. Especially neural networks provide an interesting opportunity to develop algorithms for real-time detection of a wide variety of asynchronies [5,39], however, there are also studies that take a model-based approach [12]. A bottleneck for studies is the amount of available labeled clinical data to improve the training, testing, and comparing these machine learning algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A model-based approach to generating annotated pressure support waveforms

Diepen

Bakkes

Bie

et al. 2022

J Clin Monit Comput

Self Cite

View full text Add to dashboard Cite

Large numbers of asynchronies during pressure support ventilation cause discomfort and higher work of breathing in the patient, and are associated with an increased mortality. There is a need for real-time decision support to detect asynchronies and assist the clinician towards lung-protective ventilation. Machine learning techniques have been proposed to detect asynchronies, but they require large datasets with sufficient data diversity, sample size, and quality for training purposes. In this work, we propose a method for generating a large, realistic and labeled, synthetic dataset for training and validating machine learning algorithms to detect a wide variety of asynchrony types. We take a model-based approach in which we adapt a non-linear lung-airway model for use in a diverse patient group and add a first-order ventilator model to generate labeled pressure, flow, and volume waveforms of pressure support ventilation. The model was able to reproduce basic measured lung mechanics parameters. Experienced clinicians were not able to differentiate between the simulated waveforms and clinical data (P = 0.44 by Fisher’s exact test). The detection performance of the machine learning trained on clinical data gave an overall comparable true positive rate on clinical data and on simulated data (an overall true positive rate of 94.3% and positive predictive value of 93.5% on simulated data and a true positive rate of 98% and positive predictive value of 98% on clinical data). Our findings demonstrate that it is possible to generate labeled pressure and flow waveforms with different types of asynchronies.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Asynchroniesmentioning

confidence: 99%

Section: Validationmentioning

confidence: 99%

Section: Validationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A model-based approach to generating annotated pressure support waveforms

Diepen

Bakkes

Bie

et al. 2022

J Clin Monit Comput

Self Cite

View full text Add to dashboard Cite

show abstract

A Software Tool for Anomaly Detection and Labeling of Ventilator Waveforms

Chen,

Wang,

Chen

et al. 2024

IFMBE Proceedings

View full text Add to dashboard Cite

Uncertainty-aware non-invasive patient–ventilator asynchrony detection using latent Gaussian mixture generative classifier with noisy label correction

Wang,

Luo,

Aickelin

et al. 2024

Int J Data Sci Anal

View full text Add to dashboard Cite

Patient–ventilator asynchrony (PVA) refers to instances where a mechanical ventilator’s cycles are desynchronised from the patient’s breathing efforts, and may result in patient discomfort and potential ineffective ventilation. Typically, they are identified with constant monitoring by trained clinicians. Such expertise is often limited; therefore, it is desirable to automate PVA detection with machine learning methods. However, there are three major challenges to applying machine learning to the problem: data collected from non-invasive ventilation are often noisy, there exists high variability between patients or between setting changes, and manual annotations of PVA events are not always consistent. To produce meaningful inference from such noisy data, a model needs to not only provide a measure of uncertainty, but also take into account potential inconsistencies in the training signal it is based on. In this work, we propose a conditional latent Gaussian mixture generative classifier with noisy label correction, which is capable of capturing variations within and between classes, providing well-calibrated class probabilities, detecting unlikely input instances that deviates from training data, while also taking into account possible mislabelling of event classes. We show that our model is able to match the performance of a well-tuned gradient boosting classifier, but also produce better calibrated predictions and smaller performance variability between patients.

show abstract

A machine learning method for automatic detection and classification of patient-ventilator asynchrony

Cited by 13 publications

References 11 publications

A model-based approach to generating annotated pressure support waveforms

A model-based approach to generating annotated pressure support waveforms

A Software Tool for Anomaly Detection and Labeling of Ventilator Waveforms

Uncertainty-aware non-invasive patient–ventilator asynchrony detection using latent Gaussian mixture generative classifier with noisy label correction

Contact Info

Product

Resources

About