Journal
JOURNAL OF CLINICAL MONITORING AND COMPUTING
Volume 36, Issue 6, Pages 1739-1752Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s10877-022-00822-4
Keywords
Patient-ventilator interactions; Asynchronies; mechanical ventilation; Model based methods; Machine learning
Categories
Ask authors/readers for more resources
Asynchronies during pressure support ventilation can lead to discomfort and increased mortality. This study proposes a method for generating a large, realistic, and labeled synthetic dataset to train machine learning algorithms for detecting different types of asynchronies. The model-based approach was able to reproduce basic lung mechanics parameters, and the machine learning trained on both clinical and simulated data showed comparable detection performance.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available