Automated detection and quantification of reverse triggering effort under mechanical ventilation

Reverse triggering ? a novel or previously missed phenomenon?

BACKGROUND

Reverse triggering (RT) was described in 2013 as a form of patient-ventilator asynchrony, where patient's respiratory effort follows mechanical insufflation. Diagnosis requires esophageal pressure (Pes) or diaphragmatic electrical activity (EAdi), but RT can also be diagnosed using standard ventilator waveforms.

HYPOTHESIS

We wondered (1) how frequently RT would be present but undetected in the figures from literature, especially before 2013; (2) whether it would be more prevalent in the era of small tidal volumes after 2000.

METHODS

We searched PubMed, EMBASE, and the Cochrane Central Register of Controlled Trials, from 1950 to 2017, with key words related to asynchrony to identify papers with figures including ventilator waveforms expected to display RT if present. Experts labelled waveforms. 'Definite' RT was identified when Pes or EAdi were in the tracing, and 'possible' RT when only flow and pressure waveforms were present. Expert assessment was compared to the author's descriptions of waveforms.

RESULTS

We found 65 appropriate papers published from 1977 to now, containing 181 ventilator waveforms. 21 cases of 'possible' RT and 25 cases of 'definite' RT were identified by the experts. 18.8% of waveforms prior to 2013 had evidence of RT. Most cases were published after 2000 (1 before vs. 45 after, p = 0.03). 54% of RT cases were attributed to different phenomena. A few cases of identified RT were already described prior to 2013 using different terminology (earliest in 1997). While RT cases attributed to different phenomena decreased after 2013, 60% of 'possible' RT remained missed.

CONCLUSION

RT has been present in the literature as early as 1997, but most cases were found after the introduction of low tidal volume ventilation in 2000. Following 2013, the number of undetected cases decreased, but RT are still commonly missed. Reverse Triggering, A Missed Phenomenon in the Literature. Critical Care Canada Forum 2019 Abstracts. Can J Anesth/J Can Anesth 67 (Suppl 1), 1-162 (2020). https://doi-org.myaccess.library.utoronto.ca/ https://doi.org/10.1007/s12630-019-01552-z .

Flow-Limited and Reverse-Triggered Ventilator Dyssynchrony Are Associated With Increased Tidal and Dynamic Transpulmonary Pressure

OBJECTIVES

Ventilator dyssynchrony may be associated with increased delivered tidal volumes (V t s) and dynamic transpulmonary pressure (ΔP L,dyn ), surrogate markers of lung stress and strain, despite low V t ventilation. However, it is unknown which types of ventilator dyssynchrony are most likely to increase these metrics or if specific ventilation or sedation strategies can mitigate this potential.

DESIGN

A prospective cohort analysis to delineate the association between ten types of breaths and delivered V t , ΔP L,dyn , and transpulmonary mechanical energy.

SETTING

Patients admitted to the medical ICU.

PATIENTS

Over 580,000 breaths from 35 patients with acute respiratory distress syndrome (ARDS) or ARDS risk factors.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Patients received continuous esophageal manometry. Ventilator dyssynchrony was identified using a machine learning algorithm. Mixed-effect models predicted V t , ΔP L,dyn , and transpulmonary mechanical energy for each type of ventilator dyssynchrony while controlling for repeated measures. Finally, we described how V t , positive end-expiratory pressure (PEEP), and sedation (Richmond Agitation-Sedation Scale) strategies modify ventilator dyssynchrony's association with these surrogate markers of lung stress and strain. Double-triggered breaths were associated with the most significant increase in V t , ΔP L,dyn , and transpulmonary mechanical energy. However, flow-limited, early reverse-triggered, and early ventilator-terminated breaths were also associated with significant increases in V t , ΔP L,dyn , and energy. The potential of a ventilator dyssynchrony type to increase V t , ΔP L,dyn , or energy clustered similarly. Increasing set V t may be associated with a disproportionate increase in high-volume and high-energy ventilation from double-triggered breaths, but PEEP and sedation do not clinically modify the interaction between ventilator dyssynchrony and surrogate markers of lung stress and strain.

CONCLUSIONS

Double-triggered, flow-limited, early reverse-triggered, and early ventilator-terminated breaths are associated with increases in V t , ΔP L,dyn , and energy. As flow-limited breaths are more than twice as common as double-triggered breaths, further work is needed to determine the interaction of ventilator dyssynchrony frequency to cause clinically meaningful changes in patient outcomes.

Respiratory entrainment related reverse triggering in mechanically ventilated children

BACKGROUND

The underlying pathophysiological pathways how reverse triggering is being caused are not fully understood. Respiratory entrainment may be one of these mechanisms, but both terms are used interchangeably. We sought to characterize reverse triggering and the relationship with respiratory entrainment among mechanically ventilated children with and without acute lung injury.

METHODS

We performed a secondary phyiology analysis of two previously published data sets of invasively mechanically ventilated children < 18 years with and without lung injury mechanically ventilated in a continuous or intermittent mandatory ventilation mode. Ventilator waveforms, electrical activity of the diaphragm measured with surface electromyography and oesophageal tracings were analyzed for entrained and non-entrained reverse triggered breaths.

RESULTS

In total 102 measurements (3110 min) from 67 patients (median age 4.9 [1.8 ; 19,1] months) were analyzed. Entrained RT was identified in 12 (12%) and non-entrained RT in 39 (38%) recordings. Breathing variability for entrained RT breaths was lower compared to non-entrained RT breaths. We did not observe breath stacking during entrained RT. Double triggering often occurred during non-entrained RT and led to an increased tidal volume. Patients with respiratory entrainment related RT had a shorter duration of MV and length of PICU stay.

CONCLUSIONS

Reverse triggering is not one entity but a clinical spectrum with different mechanisms and consequences.

TRIAL REGISTRATION

Not applicable.

Flow starvation during square-flow assisted ventilation detected by supervised deep learning techniques

BACKGROUND

Flow starvation is a type of patient-ventilator asynchrony that occurs when gas delivery does not fully meet the patients' ventilatory demand due to an insufficient airflow and/or a high inspiratory effort, and it is usually identified by visual inspection of airway pressure waveform. Clinical diagnosis is cumbersome and prone to underdiagnosis, being an opportunity for artificial intelligence. Our objective is to develop a supervised artificial intelligence algorithm for identifying airway pressure deformation during square-flow assisted ventilation and patient-triggered breaths.

METHODS

Multicenter, observational study. Adult critically ill patients under mechanical ventilation > 24 h on square-flow assisted ventilation were included. As the reference, 5 intensive care experts classified airway pressure deformation severity. Convolutional neural network and recurrent neural network models were trained and evaluated using accuracy, precision, recall and F1 score. In a subgroup of patients with esophageal pressure measurement (ΔPes), we analyzed the association between the intensity of the inspiratory effort and the airway pressure deformation.

RESULTS

6428 breaths from 28 patients were analyzed, 42% were classified as having normal-mild, 23% moderate, and 34% severe airway pressure deformation. The accuracy of recurrent neural network algorithm and convolutional neural network were 87.9% [87.6-88.3], and 86.8% [86.6-87.4], respectively. Double triggering appeared in 8.8% of breaths, always in the presence of severe airway pressure deformation. The subgroup analysis demonstrated that 74.4% of breaths classified as severe airway pressure deformation had a ΔPes > 10 cmH2O and 37.2% a ΔPes > 15 cmH2O.

CONCLUSIONS

Recurrent neural network model appears excellent to identify airway pressure deformation due to flow starvation. It could be used as a real-time, 24-h bedside monitoring tool to minimize unrecognized periods of inappropriate patient-ventilator interaction.

The Development, Optimization, and Validation of Four Different Machine Learning Algorithms to Identify Ventilator Dyssynchrony

Invasive mechanical ventilation can worsen lung injury. Ventilator dyssynchrony (VD) may propagate ventilator-induced lung injury (VILI) and is challenging to detect and systematically monitor because each patient takes approximately 25,000 breaths a day yet some types of VD are rare, accounting for less than 1% of all breaths. Therefore, we sought to develop and validate accurate machine learning (ML) algorithms to detect multiple types of VD by leveraging esophageal pressure waveform data to quantify patient effort with airway pressure, flow, and volume data generated during mechanical ventilation, building a computational pipeline to facilitate the study of VD.

MATERIALS AND METHODS

We collected ventilator waveform and esophageal pressure data from 30 patients admitted to the ICU. Esophageal pressure allows the measurement of transpulmonary pressure and patient effort. Waveform data were cleaned, features considered essential to VD detection were calculated, and a set of 10,000 breaths were manually labeled. Four ML algorithms were trained to classify each type of VD: logistic regression, support vector classification, random forest, and XGBoost.

RESULTS

We trained ML models to detect different families and seven types of VD with high sensitivity (>90% and >80%, respectively). Three types of VD remained difficult for ML to classify because of their rarity and lack of sample size. XGBoost classified breaths with increased specificity compared to other ML algorithms.

DISCUSSION

We developed ML models to detect multiple types of VD accurately. The ability to accurately detect multiple VD types addresses one of the significant limitations in understanding the role of VD in affecting patient outcomes.

CONCLUSION

ML models identify multiple types of VD by utilizing esophageal pressure data and airway pressure, flow, and volume waveforms. The development of such computational pipelines will facilitate the identification of VD in a scalable fashion, allowing for the systematic study of VD and its impact on patient outcomes.

Reverse triggering during mechanical ventilation: Diagnosis and clinical implications

This review addresses the phenomenon of "reverse triggering", an asynchrony that occurs in deeply sedated patients or patients in transition from deep to light sedation. Reverse triggering has been reported to occur in 30-90% of all ventilated patients. The underlying pathophysiological mechanisms remain unclear, but "entrainment" is proposed as one of them. Detecting this asynchrony is crucial, and methods such as visual inspection, esophageal pressure, diaphragmatic ultrasound and automated methods have been used. Reverse triggering may have effects on lung and diaphragm function, probably mediated by the level of breathing effort and eccentric activation of the diaphragm. The optimal management of reverse triggering has not been established, but may include the adjustment of ventilatory parameters as well as of sedation level, and in extreme cases, neuromuscular block. It is important to understand the significance of this condition and its detection, but also to conduct dedicated research to improve its clinical management and potential effects in critically ill patients.

Automated evaluation of typical patient-ventilator asynchronies based on lung hysteretic responses

BACKGROUND

Patient-ventilator asynchrony is common during mechanical ventilation (MV) in intensive care unit (ICU), leading to worse MV care outcome. Identification of asynchrony is critical for optimizing MV settings to reduce or eliminate asynchrony, whilst current clinical visual inspection of all typical types of asynchronous breaths is difficult and inefficient. Patient asynchronies create a unique pattern of distortions in hysteresis respiratory behaviours presented in pressure-volume (PV) loop.

METHODS

Identification method based on hysteretic lung mechanics and hysteresis loop analysis is proposed to delineate the resulted changes of lung mechanics in PV loop during asynchronous breathing, offering detection of both its incidence and 7 major types. Performance is tested against clinical patient data with comparison to visual inspection conducted by clinical doctors.

RESULTS

The identification sensitivity and specificity of 11 patients with 500 breaths for each patient are above 89.5% and 96.8% for all 7 types, respectively. The average sensitivity and specificity across all cases are 94.6% and 99.3%, indicating a very good accuracy. The comparison of statistical analysis between identification and human inspection yields the essential same clinical judgement on patient asynchrony status for each patient, potentially leading to the same clinical decision for setting adjustment.

CONCLUSIONS

The overall results validate the accuracy and robustness of the identification method for a bedside monitoring, as well as its ability to provide a quantified metric for clinical decision of ventilator setting. Hence, the method shows its potential to assist a more consistent and objective assessment of asynchrony without undermining the efficacy of the current clinical practice.

The oesophageal balloon for respiratory monitoring in ventilated patients: updated clinical review and practical aspects

There is a well-recognised importance for personalising mechanical ventilation settings to protect the lungs and the diaphragm for each individual patient. Measurement of oesophageal pressure (P oes) as an estimate of pleural pressure allows assessment of partitioned respiratory mechanics and quantification of lung stress, which helps our understanding of the patient's respiratory physiology and could guide individualisation of ventilator settings. Oesophageal manometry also allows breathing effort quantification, which could contribute to improving settings during assisted ventilation and mechanical ventilation weaning. In parallel with technological improvements, P oes monitoring is now available for daily clinical practice. This review provides a fundamental understanding of the relevant physiological concepts that can be assessed using P oes measurements, both during spontaneous breathing and mechanical ventilation. We also present a practical approach for implementing oesophageal manometry at the bedside. While more clinical data are awaited to confirm the benefits of P oes-guided mechanical ventilation and to determine optimal targets under different conditions, we discuss potential practical approaches, including positive end-expiratory pressure setting in controlled ventilation and assessment of inspiratory effort during assisted modes.

Reverse Triggering during Controlled Ventilation: From Physiology to Clinical Management

Reverse triggering dyssynchrony is a frequent phenomenon recently recognized in sedated critically ill patients under controlled ventilation. It occurs in at least 30-55% of these patients and often occurs in the transition from fully passive to assisted mechanical ventilation. During reverse triggering, patient inspiratory efforts start after the passive insufflation by mechanical breaths. The most often referred mechanism is the entrainment of the patient's intrinsic respiratory rhythm from the brainstem respiratory centers to periodic mechanical insufflations from the ventilator. However, reverse triggering might also occur because of local reflexes without involving the respiratory rhythm generator in the brainstem. Reverse triggering is observed during the acute phase of the disease, when patients may be susceptible to potential deleterious consequences of injurious or asynchronous efforts. Diagnosing reverse triggering might be challenging and can easily be missed. Inspection of ventilator waveforms or more sophisticated methods, such as the electrical activity of the diaphragm or esophageal pressure, can be used for diagnosis. The occurrence of reverse triggering might have clinical consequences. On the basis of physiological data, reverse triggering might be beneficial or injurious for the diaphragm and the lung, depending on the magnitude of the inspiratory effort. Reverse triggering can cause breath-stacking and loss of protective lung ventilation when triggering a second cycle. Little is known about how to manage patients with reverse triggering; however, available evidence can guide management on the basis of physiological principles.

Reverse Triggering: An Introduction to Diagnosis, Management, and Pharmacologic Implications

Reverse triggering is an underdiagnosed form of patient-ventilator asynchrony in which a passive ventilator-delivered breath triggers a neural response resulting in involuntary patient effort and diaphragmatic contraction. Reverse triggering may significantly impact patient outcomes, and the unique physiology underscores critical potential implications for drug-device-patient interactions. The purpose of this review is to summarize what is known of reverse triggering and its pharmacotherapeutic consequences, with a particular focus on describing reported cases, physiology, historical context, epidemiology, and management. The PubMed database was searched for publications that reported patients presenting with reverse triggering. The current body of evidence suggests that deep sedation may predispose patients to episodes of reverse triggering; as such, providers may consider decreasing sedation or modifying ventilator settings in patients exhibiting ventilator asynchrony as an initial measure. Increased clinician awareness and research focus are necessary to understand appropriate management of reverse triggering and its association with patient outcomes.

Lung and diaphragm protective ventilation: a synthesis of recent data

INTRODUCTION

: To adhere to the Hippocratic Oath, to "first, do no harm", we need to make every effort to minimize the adverse effects of mechanical ventilation. Our understanding of the mechanisms of ventilator-induced lung injury (VILI) and ventilator-induced diaphragm dysfunction (VIDD) has increased in recent years. Research focuses now on methods to monitor lung stress and inhomogeneity and targets we should aim for when setting the ventilator. In parallel, efforts to promote early assisted ventilation to prevent VIDD have revealed new challenges, such as titrating inspiratory effort and synchronizing the mechanical with the patients' spontaneous breaths, while at the same time adhering to lung-protective targets.

AREAS COVERED

This is a narrative review of the key mechanisms contributing to VILI and VIDD and the methods currently available to evaluate and mitigate the risk of lung and diaphragm injury.

EXPERT OPINION

Implementing lung and diaphragm protective ventilation requires individualizing the ventilator settings, and this can only be accomplished by exploiting in everyday clinical practice the tools available to monitor lung stress and inhomogeneity, inspiratory effort, and patient-ventilator interaction.

Reconstructing asynchrony for mechanical ventilation using a hysteresis loop virtual patient model

BACKGROUND

Patient-specific lung mechanics during mechanical ventilation (MV) can be identified from measured waveforms of fully ventilated, sedated patients. However, asynchrony due to spontaneous breathing (SB) effort can be common, altering these waveforms and reducing the accuracy of identified, model-based, and patient-specific lung mechanics.

METHODS

Changes in patient-specific lung elastance over a pressure-volume (PV) loop, identified using hysteresis loop analysis (HLA), are used to detect the occurrence of asynchrony and identify its type and pattern. The identified HLA parameters are then combined with a nonlinear mechanics hysteresis loop model (HLM) to extract and reconstruct ventilated waveforms unaffected by asynchronous breaths. Asynchrony magnitude can then be quantified using an energy-dissipation metric, Easyn, comparing PV loop area between model-reconstructed and original, altered asynchronous breathing cycles. Performance is evaluated using both test-lung experimental data with a known ground truth and clinical data from four patients with varying levels of asynchrony.

RESULTS

Root mean square errors for reconstructed PV loops are within 5% for test-lung experimental data, and 10% for over 90% of clinical data. Easyn clearly matches known asynchrony magnitude for experimental data with RMS errors < 4.1%. Clinical data performance shows 57% breaths having Easyn > 50% for Patient 1 and 13% for Patient 2. Patient 3 only presents 20% breaths with Easyn > 10%. Patient 4 has Easyn = 0 for 96% breaths showing accuracy in a case without asynchrony.

CONCLUSIONS

Experimental test-lung validation demonstrates the method's reconstruction accuracy and generality in controlled scenarios. Clinical validation matches direct observations of asynchrony in incidence and quantifies magnitude, including cases without asynchrony, validating its robustness and potential efficacy as a clinical real-time asynchrony monitoring tool.

Timing of inspiratory muscle activity detected from airway pressure and flow during pressure support ventilation: the waveform method

Background

Whether respiratory efforts and their timing can be reliably detected during pressure support ventilation using standard ventilator waveforms is unclear. This would give the opportunity to assess and improve patient–ventilator interaction without the need of special equipment.

Methods

In 16 patients under invasive pressure support ventilation, flow and pressure waveforms were obtained from proximal sensors and analyzed by three trained physicians and one resident to assess patient’s spontaneous activity. A systematic method (the waveform method) based on explicit rules was adopted. Esophageal pressure tracings were analyzed independently and used as reference. Breaths were classified as assisted or auto-triggered, double-triggered or ineffective. For assisted breaths, trigger delay, early and late cycling (minor asynchronies) were diagnosed. The percentage of breaths with major asynchronies (asynchrony index) and total asynchrony time were computed.

Results

Out of 4426 analyzed breaths, 94.1% (70.4–99.4) were assisted, 0.0% (0.0–0.2) auto-triggered and 5.8% (0.4–29.6) ineffective. Asynchrony index was 5.9% (0.6–29.6). Total asynchrony time represented 22.4% (16.3–30.1) of recording time and was mainly due to minor asynchronies. Applying the waveform method resulted in an inter-operator agreement of 0.99 (0.98–0.99); 99.5% of efforts were detected on waveforms and agreement with the reference in detecting major asynchronies was 0.99 (0.98–0.99). Timing of respiratory efforts was accurately detected on waveforms: AUC for trigger delay, cycling delay and early cycling was 0.865 (0.853–0.876), 0.903 (0.892–0.914) and 0.983 (0.970–0.991), respectively.

Conclusions

Ventilator waveforms can be used alone to reliably assess patient’s spontaneous activity and patient–ventilator interaction provided that a systematic method is adopted.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13054-022-03895-4.

The physiological underpinnings of life-saving respiratory support

Treatment of respiratory failure has improved dramatically since the polio epidemic in the 1950s with the use of invasive techniques for respiratory support: mechanical ventilation and extracorporeal respiratory support. However, respiratory support is only a supportive therapy, designed to "buy time" while the disease causing respiratory failure abates. It ensures viable gas exchange and prevents cardiorespiratory collapse in the context of excessive loads. Because the use of invasive modalities of respiratory support is also associated with substantial harm, it remains the responsibility of the clinician to minimize such hazards. Direct iatrogenic consequences of mechanical ventilation include the risk to the lung (ventilator-induced lung injury) and the diaphragm (ventilator-induced diaphragm dysfunction and other forms of myotrauma). Adverse consequences on hemodynamics can also be significant. Indirect consequences (e.g., immobilization, sleep disruption) can have devastating long-term effects. Increasing awareness and understanding of these mechanisms of injury has led to a change in the philosophy of care with a shift from aiming to normalize gases toward minimizing harm. Lung (and more recently also diaphragm) protective ventilation strategies include the use of extracorporeal respiratory support when the risk of ventilation becomes excessive. This review provides an overview of the historical background of respiratory support, pathophysiology of respiratory failure and rationale for respiratory support, iatrogenic consequences from mechanical ventilation, specifics of the implementation of mechanical ventilation, and role of extracorporeal respiratory support. It highlights the need for appropriate monitoring to estimate risks and to individualize ventilation and sedation to provide safe respiratory support to each patient.

Impact of Reverse Triggering Dyssynchrony During Lung-Protective Ventilation on Diaphragm Function: An Experimental Model

RATIONALE

Reverse triggering is a patient-ventilator interaction where a respiratory muscle contraction is triggered by a passive mechanical insufflation. Its impact on diaphragm structure and function is unknown.

OBJECTIVE

To establish an animal model of reverse triggering with lung injury receiving lung-protective ventilation and to assess its impact on structure and function of the diaphragm.

METHODS

Lung injury was induced by surfactant depletion and high stress ventilation in 32 ventilated pigs. Animals were allocated to receive passive mechanical ventilation or a lung-protective strategy with adjustments facilitating the occurrence of reverse triggering for 3 hours. Diaphragm function (transdiaphragmatic pressure (Pdi) during phrenic nerve stimulation [Force/frequency curve]) and structure (biopsies) were assessed. The impact of reverse triggering on diaphragm function was analyzed according to the breathing effort.

RESULTS

Compared to passive ventilation, the protective ventilation group with reverse triggering received significantly lower tidal volume (7 vs 10 ml/kg) and higher respiratory rate (45 vs 31 bpm). An entrainment pattern of 1:1 was frequent. Breathing effort induced by reverse triggering was highly variable across animals. Reverse triggering with the lowest tercile of breathing effort was associated with 23% higher twitch Pdi compared to passive ventilation, whereas reverse triggering with high breathing effort was associated with a 10% lower twitch Pdi and a higher proportion of abnormal muscle fibers.

CONCLUSION

In a reproducible animal model of reverse triggering with variable levels of breathing effort and entrainment patterns, reverse triggering with high effort is associated with impaired diaphragm function whereas reverse triggering with low effort is associated with preserved diaphragm force.

Reliability of plateau pressure during patient-triggered assisted ventilation. Analysis of a multicentre database

PURPOSE

An inspiratory hold during patient-triggered assisted ventilation potentially allows to measure driving pressure and inspiratory effort. However, muscular activity can make this measurement unreliable. We aim to define the criteria for inspiratory holds reliability during patient-triggered breaths.

MATERIAL AND METHODS

Flow, airway and esophageal pressure recordings during patient-triggered breaths from a multicentre observational study (BEARDS, NCT03447288) were evaluated by six independent raters, to determine plateau pressure readability. Features of "readable" and "unreadable" holds were compared. Muscle pressure estimate from the hold was validated against other measures of inspiratory effort.

RESULTS

Ninety-two percent of the recordings were consistently judged as readable or unreadable by at least four raters. Plateau measurement showed a high consistency among raters. A short time from airway peak to plateau pressure and a stable and longer plateau characterized readable holds. Unreadable plateaus were associated with higher indexes of inspiratory effort. Muscular pressure computed from the hold showed a strong correlation with independent indexes of inspiratory effort.

CONCLUSION

The definition of objective parameters of plateau reliability during assisted-breath provides the clinician with a tool to target a safer assisted-ventilation and to detect the presence of high inspiratory effort.

An interpretable 1D convolutional neural network for detecting patient-ventilator asynchrony in mechanical ventilation

BACKGROUND AND OBJECTIVE

Patient-ventilator asynchrony (PVA) is the result of a mismatch between the need of patients and the assistance provided by the ventilator during mechanical ventilation. Because the poor interaction between the patient and the ventilator is associated with inferior clinical outcomes, effort should be made to identify and correct their occurrence. Deep learning has shown promising ability in PVA detection; however, lack of network interpretability hampers its application in clinic.

METHODS

We proposed an interpretable one-dimensional convolutional neural network (1DCNN) to detect four most manifestation types of PVA (double triggering, ineffective efforts during expiration, premature cycling and delayed cycling) under pressure control ventilation mode and pressure support ventilation mode. A global average pooling (GAP) layer was incorporated with the 1DCNN model to highlight the sections of the respiratory waveform the model focused on when making a classification. Dilation convolution and batch normalization were introduced to the 1DCNN model for compensating the reduction of performance caused by the GAP layer.

RESULTS

The proposed interpretable 1DCNN exhibited comparable performance with the state-of-the-art deep learning model in PVA detection. The F1 scores for the detection of four types of PVA under pressure control ventilation and pressure support ventilation modes were greater than 0.96. The critical sections of the waveform used to detect PVA were highlighted, and found to be well consistent with the understanding of the respective type of PVA by experts.

CONCLUSIONS

The findings suggest that the proposed 1DCNN can help detect PVA, and enhance the interpretability of the classification process to help clinicians better understand the results obtained from deep learning technology.