Automatic detection of patient-ventilator asynchrony by spectral analysis of airway flow

Patient-ventilator asynchrony classification in mechanically ventilated patients: Model-based or machine learning method?

BACKGROUND AND OBJECTIVE

Patient-ventilator asynchrony (PVA) is associated with poor clinical outcomes and remains under-monitored. Automated PVA detection would enable complete monitoring standard observational methods do not allow. While model-based and machine learning PVA approaches exist, they have variable performance and can miss specific PVA events. This study compares a model and rule-based algorithm with a machine learning PVA method by retrospectively validating both methods using an independent patient cohort.

METHODS

Hysteresis loop analysis (HLA) which is a rule-based method (RBM) and a tri-input convolutional neural network (TCNN) machine learning model are used to classify 7 different types of PVA, including: 1) flow asynchrony; 2) reverse triggering; 3) premature cycling; 4) double triggering; 5) delayed cycling; 6) ineffective efforts; and 7) auto triggering. Class activation mapping (CAM) heatmaps visualise sections of respiratory waveforms the TCNN model uses for decision making, improving result interpretability. Both PVA classification methods were used to classify incidence in an independent retrospective clinical cohort of 11 mechanically ventilated patients for validation and performance comparison.

RESULTS

Self-validation with the training dataset shows overall better HLA performance (accuracy, sensitivity, specificity: 97.5 %, 96.6 %, 98.1 %) compared to the TCNN model (accuracy, sensitivity, specificity: 89.5 %, 98.3 %, 83.9 %). In this study, the TCNN model demonstrates higher sensitivity in detecting PVA, but HLA was better at identifying non-PVA breathing cycles due to its rule-based nature. While the overall AI identified by both classification methods are very similar, the intra-patient distribution of each PVA type varies between HLA and TCNN.

CONCLUSION

The collective findings underscore the efficacy of both HLA and TCNN in PVA detection, indicating the potential for real-time continuous monitoring of PVA. While ML methods such as TCNN demonstrate good PVA identification performance, it is essential to ensure optimal model architecture and diversity in training data before widespread uptake as standard care. Moving forward, further validation and adoption of RBM methods, such as HLA, offers an effective approach to PVA detection while providing clear distinction into the underlying patterns of PVA, better aligning with clinical needs for transparency, explicability, adaptability and reliability of these emerging tools for clinical care.

A non-invasive method to monitor respiratory muscle effort during mechanical ventilation

PURPOSE

This study introduces a method to non-invasively and automatically quantify respiratory muscle effort (Pmus) during mechanical ventilation (MV). The methodology hinges on numerically solving the respiratory system's equation of motion, utilizing measurements of airway pressure (Paw) and airflow (Faw). To evaluate the technique's effectiveness, Pmus was correlated with expected physiological responses. In volume-control (VC) mode, where tidal volume (VT) is pre-determined, Pmus is expected to be linked to Paw fluctuations. In contrast, during pressure-control (PC) mode, where Paw is held constant, Pmus should correlate with VT variations.

METHODS

The study utilized data from 250 patients on invasive MV. The data included detailed recordings of Paw and Faw, sampled at 31.25 Hz and saved in 131.1-second epochs, each covering 34 to 41 breaths. The algorithm identified 51,268 epochs containing breaths on either VC or PC mode exclusively. In these epochs, Pmus and its pressure-time product (PmusPTP) were computed and correlated with Paw's pressure-time product (PawPTP) and VT, respectively.

RESULTS

There was a strong correlation of PmusPTP with PawPTP in VC mode (R² = 0.91 [0.76, 0.96]; n = 17,648 epochs) and with VT in PC mode (R² = 0.88 [0.74, 0.94]; n = 33,620 epochs), confirming the hypothesis. As expected, negligible correlations were observed between PmusPTP and VT in VC mode (R² = 0.03) and between PmusPTP and PawPTP in PC mode (R² = 0.06).

CONCLUSION

The study supports the feasibility of assessing respiratory effort during MV non-invasively through airway signal analysis. Further research is warranted to validate this method and investigate its clinical applications.

Quantifiable identification of flow-limited ventilator dyssynchrony with the deformed lung ventilator model

BACKGROUND

Ventilator dyssynchrony (VD) can worsen lung injury and is challenging to detect and quantify due to the complex variability in the dyssynchronous breaths. While machine learning (ML) approaches are useful for automating VD detection from the ventilator waveform data, scalable severity quantification and its association with pathogenesis and ventilator mechanics remain challenging.

OBJECTIVE

We develop a systematic framework to quantify pathophysiological features observed in ventilator waveform signals such that they can be used to create feature-based severity stratification of VD breaths.

METHODS

A mathematical model was developed to represent the pressure and volume waveforms of individual breaths in a feature-based parametric form. Model estimates of respiratory effort strength were used to assess the severity of flow-limited (FL)-VD breaths compared to normal breaths. A total of 93,007 breath waveforms from 13 patients were analyzed.

RESULTS

A novel model-defined continuous severity marker was developed and used to estimate breath phenotypes of FL-VD breaths. The phenotypes had a predictive accuracy of over 97% with respect to the previously developed ML-VD identification algorithm. To understand the incidence of FL-VD breaths and their association with the patient state, these phenotypes were further successfully correlated with ventilator-measured parameters and electronic health records.

CONCLUSION

This work provides a computational pipeline to identify and quantify the severity of FL-VD breaths and paves the way for a large-scale study of VD causes and effects. This approach has direct application to clinical practice and in meaningful knowledge extraction from the ventilator waveform data.

Advanced Respiratory Monitoring during Extracorporeal Membrane Oxygenation

Advanced respiratory monitoring encompasses a diverse range of mini- or noninvasive tools used to evaluate various aspects of respiratory function in patients experiencing acute respiratory failure, including those requiring extracorporeal membrane oxygenation (ECMO) support. Among these techniques, key modalities include esophageal pressure measurement (including derived pressures), lung and respiratory muscle ultrasounds, electrical impedance tomography, the monitoring of diaphragm electrical activity, and assessment of flow index. These tools play a critical role in assessing essential parameters such as lung recruitment and overdistention, lung aeration and morphology, ventilation/perfusion distribution, inspiratory effort, respiratory drive, respiratory muscle contraction, and patient-ventilator synchrony. In contrast to conventional methods, advanced respiratory monitoring offers a deeper understanding of pathological changes in lung aeration caused by underlying diseases. Moreover, it allows for meticulous tracking of responses to therapeutic interventions, aiding in the development of personalized respiratory support strategies aimed at preserving lung function and respiratory muscle integrity. The integration of advanced respiratory monitoring represents a significant advancement in the clinical management of acute respiratory failure. It serves as a cornerstone in scenarios where treatment strategies rely on tailored approaches, empowering clinicians to make informed decisions about intervention selection and adjustment. By enabling real-time assessment and modification of respiratory support, advanced monitoring not only optimizes care for patients with acute respiratory distress syndrome but also contributes to improved outcomes and enhanced patient safety.

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.

Specific Training Improves the Detection and Management of Patient-Ventilator Asynchrony

BACKGROUND

Patient-ventilator asynchrony is common in patients undergoing mechanical ventilation. The proportion of health-care professionals capable of identifying and effectively managing different types of patient-ventilator asynchronies is limited. A few studies have developed specific training programs, but they mainly focused on improving patient-ventilator asynchrony detection without assessing the ability of health-care professionals to determine the possible causes.

METHODS

We conducted a 36-h training program focused on patient-ventilator asynchrony detection and management for health-care professionals from 20 hospitals in Latin America and Spain. The training program included 6 h of a live online lesson during which 120 patient-ventilator asynchrony cases were presented. After the 6-h training lesson, health-care professionals were required to complete a 1-h training session per day for the subsequent 30 d. A 30-question assessment tool was developed and used to assess health-care professionals before training, immediately after the 6-h training lecture, and after the 30 d of training (1-month follow-up).

RESULTS

One hundred sixteen health-care professionals participated in the study. The median (interquartile range) of the total number of correct answers in the pre-training, post-training, and 1-month follow-up were significantly different (12 [8.75-15], 18 [13.75-22], and 18.5 [14-23], respectively). The percentages of correct answers also differed significantly between the time assessments. Study participants significantly improved their performance between pre-training and post-training (P < .001). This performance was maintained after a 1-month follow-up (P = .95) for the questions related to the detection, determination of cause, and management of patient-ventilator asynchrony.

CONCLUSIONS

A specific 36-h training program significantly improved the ability of health-care professionals to detect patient-ventilator asynchrony, determine the possible causes of patient-ventilator asynchrony, and properly manage different types of patient-ventilator asynchrony.

A Novel Application of Spectrograms with Machine Learning Can Detect Patient Ventilator Dyssynchrony

Patients in intensive care units are frequently supported by mechanical ventilation. There is increasing awareness of patient-ventilator dyssynchrony (PVD), a mismatch between patient respiratory effort and assistance provided by the ventilator, as a risk factor for infection, narcotic exposure, lung injury, and adverse neurocognitive effects. One of the most injurious consequences of PVD are double cycled (DC) breaths when two breaths are delivered by the ventilator instead of one. Prior efforts to identify PVD have limited efficacy. An automated method to identify PVD, independent of clinician expertise, acumen, or time, would potentially permit early, targeted treatment to avoid further harm. We performed secondary analyses of data from a clinical trial of children with acute respiratory distress syndrome. Waveforms of ventilator flow, airway pressure and esophageal manometry were annotated to identify DC breaths and underlying PVD subtypes. Spectrograms were generated from those waveforms to train Convolutional Neural Network (CNN) models in detecting DC and underlying PVD subtypes: Reverse Trigger (RT) and Inadequate Support (IS). The DC breath detection model yielded AUROC of 0.980, while the multi-target detection model for underlying dyssynchrony yielded AUROC of 0.980 (RT) and 0.976 (IS). When operating at 75% sensitivity, DC breath detection had a number needed to alert (NNA) 1.3 (99% specificity), while underlying PVD had a NNA 1.6 (98.5% specificity) for RT and NNA 4.0 (98.2% specificity) for IS. CNNs using spectrograms of ventilator waveforms can identify DC breaths and detect the underlying PVD for targeted clinical interventions.

A novel method to calculate compliance and airway resistance in ventilated patients

BACKGROUND

The respiratory system's static compliance (C_rs) and airway resistance (R_rs) are measured during an end-inspiratory hold on volume-controlled ventilation (static method). A numerical algorithm is presented to calculate C_rs and R_rs during volume-controlled ventilation on a breath-by-breath basis not requiring an end-inspiratory hold (dynamic method).

METHODS

The dynamic method combines a numerical solution of the equation of motion of the respiratory system with frequency analysis of airway signals. The method was validated experimentally with a one-liter test lung using 300 mL and 400 mL tidal volumes. It also was validated clinically using airway signals sampled at 32.25 Hz stored in a historical database as 131.1-s-long epochs. There were 15 patients in the database having epochs on volume-controlled ventilation with breaths displaying end-inspiratory holds. This allowed for the reliable calculation of paired C_rs and R_rs values using both static and dynamic methods. Epoch mean values for C_rs and R_rs were assessed by both methods and compared in aggregate form and individually for each patient in the study with Pearson's R² and Bland-Altman analysis. Figures are shown as median[IQR].

RESULTS

Experimental method differences in 880 simulated breaths were 0.3[0.2,0.4] mL·cmH₂O^-1 for C_rs and 0[- 0.2,0.2] cmH₂O·s· L^-1 for R_rs. Clinical testing included 78,371 breaths found in 3174 epochs meeting criteria with 24[21,30] breaths per epoch. For the aggregate data, Pearson's R² were 0.99 and 0.94 for C_rs and R_rs, respectively. Bias ± 95% limits of agreement (LOA) were 0.2 ± 1.6 mL·cmH₂O^-1 for C_rs and - 0.2 ± 1.5 cmH₂O·s· L^-1 for R_rs. Bias ± LOA median values for individual patients were 0.6[- 0.2, 1.4] ± 0.9[0.8, 1.2] mL·cmH₂O^-1 for C_rs and - 0.1[- 0.3, 0.2] ± 0.8[0.5, 1.2] cmH₂O·s· L^-1 for R_rs.

DISCUSSION

Experimental and clinical testing produced equivalent paired measurements of C_rs and R_rs by the dynamic and static methods under the conditions tested.

CONCLUSIONS

These findings support to the possibility of using the dynamic method in continuously monitoring respiratory system mechanics in patients on ventilatory support with volume-controlled ventilation.

Model-based patient matching for in-parallel pressure-controlled ventilation

BACKGROUND

Surges of COVID-19 infections have led to insufficient supply of mechanical ventilators (MV), resulting in rationing of MV care. In-parallel, co-mechanical ventilation (Co-MV) of multiple patients is a potential solution. However, due to lack of testing, there is currently no means to match ventilation requirements or patients, with no guidelines to date. In this research, we have developed a model-based method for patient matching for pressure control mode MV.

METHODS

The model-based method uses a single-compartment lung model (SCM) to simulate the resultant tidal volume of patient pairs at a set ventilation setting. If both patients meet specified safe ventilation criteria under similar ventilation settings, the actual mechanical ventilator settings for Co-MV are determined via simulation using a double-compartment lung model (DCM). This method allows clinicians to analyse Co-MV in silico, before clinical implementation.

RESULTS

The proposed method demonstrates successful patient matching and MV setting in a model-based simulation as well as good discrimination to avoid mismatched patient pairs. The pairing process is based on model-based, patient-specific respiratory mechanics identified from measured data to provide useful information for guiding care. Specifically, the matching is performed via estimation of MV delivered tidal volume (mL/kg) based on patient-specific respiratory mechanics. This information can provide insights for the clinicians to evaluate the subsequent effects of Co-MV. In addition, it was also found that Co-MV patients with highly restrictive respiratory mechanics and obese patients must be performed with extra care.

CONCLUSION

This approach allows clinicians to analyse patient matching in a virtual environment without patient risk. The approach is tested in simulation, but the results justify the necessary clinical validation in human trials.

Patient-Ventilator Synchronization During Non-invasive Ventilation: A Pilot Study of an Automated Analysis System

Background: Patient-ventilator synchronization during non-invasive ventilation (NIV) can be assessed by visual inspection of flow and pressure waveforms but it remains time consuming and there is a large inter-rater variability, even among expert physicians. SyncSmart™ software developed by Breas Medical (Mölnycke, Sweden) provides an automatic detection and scoring of patient-ventilator asynchrony to help physicians in their daily clinical practice. This study was designed to assess performance of the automatic scoring by the SyncSmart software using expert clinicians as a reference in patient with chronic respiratory failure receiving NIV.

Methods: From nine patients, 20 min data sets were analyzed automatically by SyncSmart software and reviewed by nine expert physicians who were asked to score auto-triggering (AT), double-triggering (DT), and ineffective efforts (IE). The study procedure was similar to the one commonly used for validating the automatic sleep scoring technique. For each patient, the asynchrony index was computed by automatic scoring and each expert, respectively. Considering successively each expert scoring as a reference, sensitivity, specificity, positive predictive value (PPV), κ-coefficients, and agreement were calculated.

Results: The asynchrony index assessed by SynSmart was not significantly different from the one assessed by the experts (18.9 ± 17.7 vs. 12.8 ± 9.4, p = 0.19). When compared to an expert, the sensitivity and specificity provided by SyncSmart for DT, AT, and IE were significantly greater than those provided by an expert when compared to another expert.

Conclusions:SyncSmart software is able to score asynchrony events within the inter-rater variability. When the breathing frequency is not too high (<24), it therefore provides a reliable assessment of patient-ventilator asynchrony; AT is over detected otherwise.

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.

Use of Machine Learning to Screen for Acute Respiratory Distress Syndrome Using Raw Ventilator Waveform Data

To develop and characterize a machine learning algorithm to discriminate acute respiratory distress syndrome from other causes of respiratory failure using only ventilator waveform data.

Design

Retrospective, observational cohort study.

Setting

Academic medical center ICU.

Patients

Adults admitted to the ICU requiring invasive mechanical ventilation, including 50 patients with acute respiratory distress syndrome and 50 patients with primary indications for mechanical ventilation other than hypoxemic respiratory failure.

Interventions

None.

Measurements and Main Results

Pressure and flow time series data from mechanical ventilation during the first 24-hours after meeting acute respiratory distress syndrome criteria (or first 24-hr of mechanical ventilation for non-acute respiratory distress syndrome patients) were processed to extract nine physiologic features. A random forest machine learning algorithm was trained to discriminate between the patients with and without acute respiratory distress syndrome. Model performance was assessed using the area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value. Analyses examined performance when the model was trained using data from the first 24 hours and tested using withheld data from either the first 24 hours (24/24 model) or 6 hours (24/6 model). Area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value were 0.88, 0.90, 0.71, 0.77, and 0.90 (24/24); and 0.89, 0.90, 0.75, 0.83, and 0.83 (24/6).

Conclusions

Use of machine learning and physiologic information derived from raw ventilator waveform data may enable acute respiratory distress syndrome screening at early time points after intubation. This approach, combined with traditional diagnostic criteria, could improve timely acute respiratory distress syndrome recognition and enable automated clinical decision support, especially in settings with limited availability of conventional diagnostic tests and electronic health records.

Computational analysis of neonatal ventilator waveforms and loops

BACKGROUND

Modern neonatal ventilators allow the downloading of their data with a high sampling rate. We wanted to develop an algorithm that automatically recognises and characterises ventilator inflations from ventilator pressure and flow data.

METHODS

We downloaded airway pressure and flow data with 100 Hz sampling rate from Dräger Babylog VN500 ventilators ventilating critically ill infants. We developed an open source Python package, Ventiliser, that includes a rule-based algorithm to automatically discretise ventilator data into a sequence of flow and pressure states and to recognise ventilator inflations and an information gain approach to identify inflation phases (inspiration, expiration) and sub-phases (pressure rise, pressure plateau, inspiratory hold etc.).

RESULTS

Ventiliser runs on a personal computer and analyses 24 h of ventilation in 2 min. With longer recordings, the processing time increases linearly. It generates a table reporting indices of each breath and its sub-phases. Ventiliser also allows visualisation of individual inflations as waveforms or loops. Ventiliser identified >97% of ventilator inflations and their sub-phases in an out-of-sample validation of manually annotated data. We also present detailed quantitative analysis and comparison of two 1-hour-long ventilation periods.

CONCLUSIONS

Ventiliser can analyse ventilation patterns and ventilator-patient interactions over long periods of mechanical ventilation.

IMPACT

We have developed a computational method to recognize and analyse ventilator inflations from raw data downloaded from ventilators of preterm and critically ill infants. There have been no previous reports on the computational analysis of neonatal ventilator data. We have made our program, Ventiliser, freely available. Clinicians and researchers can use Ventiliser to analyse ventilator inflations, waveforms and loops over long periods. Ventiliser can also be used to study ventilator-patient interactions.

Ventilator dyssynchrony - Detection, pathophysiology, and clinical relevance: A Narrative review

Mortality associated with the acute respiratory distress syndrome remains unacceptably high due in part to ventilator-induced lung injury (VILI). Ventilator dyssynchrony is defined as the inappropriate timing and delivery of a mechanical breath in response to patient effort and may cause VILI. Such deleterious patient–ventilator interactions have recently been termed patient self-inflicted lung injury. This narrative review outlines the detection and frequency of several different types of ventilator dyssynchrony, delineates the different mechanisms by which ventilator dyssynchrony may propagate VILI, and reviews the potential clinical impact of ventilator dyssynchrony. Until recently, identifying ventilator dyssynchrony required the manual interpretation of ventilator pressure and flow waveforms. However, computerized interpretation of ventilator waive forms can detect ventilator dyssynchrony with an area under the receiver operating curve of >0.80. Using such algorithms, ventilator dyssynchrony occurs in 3%–34% of all breaths, depending on the patient population. Moreover, two types of ventilator dyssynchrony, double-triggered and flow-limited breaths, are associated with the more frequent delivery of large tidal volumes >10 mL/kg when compared with synchronous breaths (54% [95% confidence interval (CI), 47%–61%] and 11% [95% CI, 7%–15%]) compared with 0.9% (95% CI, 0.0%–1.9%), suggesting a role in propagating VILI. Finally, a recent study associated frequent dyssynchrony-defined as >10% of all breaths-with an increase in hospital mortality (67 vs. 23%, P = 0.04). However, the clinical significance of ventilator dyssynchrony remains an area of active investigation and more research is needed to guide optimal ventilator dyssynchrony management.

Patient-ventilator asynchrony in conventional ventilation modes during short-term mechanical ventilation after cardiac surgery: randomized clinical trial

INTRODUCTION AND AIM

Studies regarding asynchrony in patients in the cardiac postoperative period are still only a few. The main objective of our study was to compare asynchronies incidence and its index (AI) in 3 different modes of ventilation (volume-controlled ventilation [VCV], pressure-controlled ventilation [PCV] and pressure-support ventilation [PSV]) after ICU admission for postoperative care.

METHODS

A prospective parallel randomised trialin the setting of a non-profitable hospital in Brazil. The participants were patients scheduled for cardiac surgery. Patients were randomly allocated to VCV or PCV modes of ventilation and later both groups were transitioned to PSV mode.

RESULTS

All data were recorded for 5 minutes in each of the three different phases: T1) in assisted breath, T2) initial spontaneous breath and T3) final spontaneous breath, a marking point prior to extubation. Asynchronies were detected and counted by visual inspection method by two independent investigators. Reliability, inter-rater agreement of asynchronies, asynchronies incidence, total and specific asynchrony indexes (AIt and AIspecific) and odds of AI ≥10% weighted by total asynchrony were analysed. A total of 17 patients randomly allocated to the VCV (n=9) or PCV (n=8) group completed the study. High inter-rated agreement for AIt (ICC 0.978; IC95%, 0,963-0.987) and good reliability (r=0.945; p<0.001) were found. Eighty-two % of patients presented asynchronies, although only 7% of their total breathing cycles were asynchronous. Early cycling and double triggering had the highest rates of asynchrony with no difference between groups. The highest odds of AI ≥10% were observed in VCV regardless the phase: OR 2.79 (1.36-5.73) in T1 vs T2, p=0.005; OR 2.61 (1.27-5.37) in T1 vs T3, p=0.009 and OR 4.99 (2.37-10.37) in T2 vs T3, p<0.001.

CONCLUSIONS

There was a high incidence of breathing asynchrony in postoperative cardiac patients, especially when initially ventilated in VCV. VCV group had a higher chance of AI ≥10% and this chance remained high in the following PSV phases.

Mechanically ventilated premature babies have sex differences in specific elastance: A pilot study

OBJECTIVES

A pilot study to compare pulmonary mechanics in a neonatal intensive care unit (NICU) cohort, specifically, comparing lung elastance between male and female infants in the NICU.

HYPOTHESIS

Anecdotally, male infants are harder to ventilate than females. We hypothesize that males have higher model-based elastance (converse: lower specific compliance) compared to females, reflecting underlying stiffer lungs.

STUDY DESIGN

A clinically validated, single-compartment model is used to identify specific elastance (inverse of specific compliance) and resistance for each breath. Specific elastance accounts for weight differences when comparing male and female infants. Relative percent breath-to-breath variability (%ΔE) in specific elastance is also compared. Level of asynchrony was also determined.

PATIENT-SUBJECT SELECTION

Ten invasively mechanically ventilated patients from Christchurch Women's Hospital.

METHODOLOGY

Airway pressure and flow data from 10 invasive mechanical ventilation (MV) infants from Christchurch Women's Hospital Neonatal Intensive Care Unit, New Zealand was prospectively recorded under standard MV care. Model-based specific elastance and resistance are identified for each breath, as well as relative percent breath-to-breath variability (%ΔE) in specific elastance.

RESULTS

Male infants overall had higher specific elastance compared to females infants (P ≤ .01), with median (interquartile range) for males of 1.91 (1.33-2.48) cmH₂ O·kg/mL compared to 1.31 (0.86-2.02) cmH₂ O·kg/mL in females. Male infants had lower variability with %ΔE of -0.03 (-7.56 to 8.01)% vs female infants of -0.59 (12.56-12.86)%. Males had 14.75% asynchronous breaths whereas females had 17.54%.

CONCLUSION

Overall, males had higher specific elastance and correspondingly lower breath-to-breath variability. These results indicate male and female infants may require different MV settings, mode, and monitoring.

Breathing variability predicts the suggested need for corrective intervention due to the perceived severity of patient-ventilator asynchrony during NIV

Patient-ventilator asynchrony is associated with intolerance to noninvasive ventilation (NIV) and worsened outcomes. Our goal was to develop a tool to determine a patient needs for  intervention by a practitioner due to the presence of patient-ventilator asynchrony. We postulated that a clinician can determine when a patient needs corrective intervention due to the perceived severity of patient-ventilator asynchrony. We hypothesized a new measure, patient breathing variability, would indicate when corrective intervention is suggested by a bedside practitioner due to the perceived severity of patient-ventilator asynchrony. With IRB approval data was collected on 78 NIV patients. A panel of experts reviewed retrospective data from a development set of 10 NIV patients to categorize them into one of the three categories. The three categories were; "No to mild asynchrony-no intervention needed", "moderate asynchrony-non-emergent corrective intervention required", and "severe asynchrony-immediate intervention required". A stepwise regression with a F-test forward selection criterion was used to develop a positive linear logic model predicting the expert panel's categorizations of the need for corrective intervention. The model was incorporated into a software tool for clinical implementation. The tool was implemented prospectively on 68 NIV patients simultaneous to a bedside practitioner scoring the need for corrective intervention due to the perceived severity of patient-ventilator asynchrony. The categories from the tool and the practitioner were compared with the rate of agreement, sensitivity, specificity, and receiver operator characteristic analyses. The rate of agreement in categorizing the suggested need for clinical intervention due to the perceived presence of patient-ventilator asynchrony between the tool and experienced bedside practitioners was 95% with a Kappa score of 0.85 (p < 0.001). Further analysis found a specificity of 84% and sensitivity of 99%. The tool appears to accurately match the suggested need for corrective intervention by a bedside practitioner. Application of the tool allows for continuous, real time, and non-invasive monitoring of patients receiving NIV, and may enable early corrective interventions to ameliorate potential patient-ventilator asynchrony.

Patient-ventilator asynchronies during mechanical ventilation: current knowledge and research priorities

BACKGROUND

Mechanical ventilation is common in critically ill patients. This life-saving treatment can cause complications and is also associated with long-term sequelae. Patient-ventilator asynchronies are frequent but underdiagnosed, and they have been associated with worse outcomes.

MAIN BODY

Asynchronies occur when ventilator assistance does not match the patient's demand. Ventilatory overassistance or underassistance translates to different types of asynchronies with different effects on patients. Underassistance can result in an excessive load on respiratory muscles, air hunger, or lung injury due to excessive tidal volumes. Overassistance can result in lower patient inspiratory drive and can lead to reverse triggering, which can also worsen lung injury. Identifying the type of asynchrony and its causes is crucial for effective treatment. Mechanical ventilation and asynchronies can affect hemodynamics. An increase in intrathoracic pressure during ventilation modifies ventricular preload and afterload of ventricles, thereby affecting cardiac output and hemodynamic status. Ineffective efforts can decrease intrathoracic pressure, but double cycling can increase it. Thus, asynchronies can lower the predictive accuracy of some hemodynamic parameters of fluid responsiveness. New research is also exploring the psychological effects of asynchronies. Anxiety and depression are common in survivors of critical illness long after discharge. Patients on mechanical ventilation feel anxiety, fear, agony, and insecurity, which can worsen in the presence of asynchronies. Asynchronies have been associated with worse overall prognosis, but the direct causal relation between poor patient-ventilator interaction and worse outcomes has yet to be clearly demonstrated. Critical care patients generate huge volumes of data that are vastly underexploited. New monitoring systems can analyze waveforms together with other inputs, helping us to detect, analyze, and even predict asynchronies. Big data approaches promise to help us understand asynchronies better and improve their diagnosis and management.

CONCLUSIONS

Although our understanding of asynchronies has increased in recent years, many questions remain to be answered. Evolving concepts in asynchronies, lung crosstalk with other organs, and the difficulties of data management make more efforts necessary in this field.

Patient-ventilator asynchrony in adult critically ill patients

INTRODUCTION

Patient-ventilator asynchrony is considered a major clinical problem for mechanically ventilated patients. It occurs during partial ventilatory support, when the respiratory muscles and the ventilator interact to contribute generating the volume output. In this review article, we consider all studies published on patient-ventilator asynchrony in the last 25 years.

EVIDENCE ACQUISITION

We selected 62 studies. The different forms of asynchrony are first defined and classified. We also describe the methods used for detecting and quantifying asynchronies. We then outline the outcome variables considered for evaluating the clinical consequences of asynchronies. The methodology for detection and quantification of patient-ventilator asynchrony are quite heterogeneous. In particular, the Asynchrony Index is calculated differently among studies.

EVIDENCE SYNTHESIS

Sixteen studies established some relationship between asynchronies and one or more clinical outcomes, such as duration of mechanical ventilation (seven studies), mortality (five studies), length of intensive care and hospital stay (four studies), patient comfort (four studies), quality of sleep (three studies), and rate of tracheotomy (three studies). In patients with severe patient-ventilator asynchrony, four of seven studies (57%) report prolonged duration of mechanical ventilation, one of five (20%) increased mortality, one of four (25%) longer intensive care and hospital lengths of stay, four of four (100%) worsened comfort, three of four (75%) deteriorated quality of sleep, and one of three (33%) increased rate of tracheotomy.

CONCLUSIONS

Given the varying outcomes considered and the erratic results, it remains unclear whether asynchronies really affects patient outcome, and the relationship between asynchronies and outcome is causative or associative.

Predicting Patient-ventilator Asynchronies with Hidden Markov Models

In mechanical ventilation, it is paramount to ensure the patient's ventilatory demand is met while minimizing asynchronies. We aimed to develop a model to predict the likelihood of asynchronies occurring. We analyzed 10,409,357 breaths from 51 critically ill patients who underwent mechanical ventilation >24 h. Patients were continuously monitored and common asynchronies were identified and regularly indexed. Based on discrete time-series data representing the total count of asynchronies, we defined four states or levels of risk of asynchronies, z1 (very-low-risk) - z4 (very-high-risk). A Poisson hidden Markov model was used to predict the probability of each level of risk occurring in the next period. Long periods with very few asynchronous events, and consequently very-low-risk, were more likely than periods with many events (state z4). States were persistent; large shifts of states were uncommon and most switches were to neighbouring states. Thus, patients entering states with a high number of asynchronies were very likely to continue in that state, which may have serious implications. This novel approach to dealing with patient-ventilator asynchrony is a first step in developing smart alarms to alert professionals to patients entering high-risk states so they can consider actions to improve patient-ventilator interaction.

Patient-ventilator asynchrony

Patient-v entilator asynchrony (PVA) is a mismatch between the patient, regarding time, flow, volume, or pressure demands of the patient respiratory system, and the ventilator, which supplies such demands, during mechanical ventilation (MV). It is a common phenomenon, with incidence rates ranging from 10% to 85%. PVA might be due to factors related to the patient, to the ventilator, or both. The most common PVA types are those related to triggering, such as ineffective effort, auto-triggering, and double triggering; those related to premature or delayed cycling; and those related to insufficient or excessive flow. Each of these types can be detected by visual inspection of volume, flow, and pressure waveforms on the mechanical ventilator display. Specific ventilatory strategies can be used in combination with clinical management, such as controlling patient pain, anxiety, fever, etc. Deep sedation should be avoided whenever possible. PVA has been associated with unwanted outcomes, such as discomfort, dyspnea, worsening of pulmonary gas exchange, increased work of breathing, diaphragmatic injury, sleep impairment, and increased use of sedation or neuromuscular blockade, as well as increases in the duration of MV, weaning time, and mortality. Proportional assist ventilation and neurally adjusted ventilatory assist are modalities of partial ventilatory support that reduce PVA and have shown promise. This article reviews the literature on the types and causes of PVA, as well as the methods used in its evaluation, its potential implications in the recovery process of critically ill patients, and strategies for its resolution.

Patient-ventilator asynchrony

Patient-v entilator asynchrony (PVA) is a mismatch between the patient, regarding time, flow, volume, or pressure demands of the patient respiratory system, and the ventilator, which supplies such demands, during mechanical ventilation (MV). It is a common phenomenon, with incidence rates ranging from 10% to 85%. PVA might be due to factors related to the patient, to the ventilator, or both. The most common PVA types are those related to triggering, such as ineffective effort, auto-triggering, and double triggering; those related to premature or delayed cycling; and those related to insufficient or excessive flow. Each of these types can be detected by visual inspection of volume, flow, and pressure waveforms on the mechanical ventilator display. Specific ventilatory strategies can be used in combination with clinical management, such as controlling patient pain, anxiety, fever, etc. Deep sedation should be avoided whenever possible. PVA has been associated with unwanted outcomes, such as discomfort, dyspnea, worsening of pulmonary gas exchange, increased work of breathing, diaphragmatic injury, sleep impairment, and increased use of sedation or neuromuscular blockade, as well as increases in the duration of MV, weaning time, and mortality. Proportional assist ventilation and neurally adjusted ventilatory assist are modalities of partial ventilatory support that reduce PVA and have shown promise. This article reviews the literature on the types and causes of PVA, as well as the methods used in its evaluation, its potential implications in the recovery process of critically ill patients, and strategies for its resolution.

Prevalence and Prognosis Impact of Patient-Ventilator Asynchrony in Early Phase of Weaning according to Two Detection Methods

BACKGROUND

Patient-ventilator asynchrony is associated with a poorer outcome. The prevalence and severity of asynchrony during the early phase of weaning has never been specifically described. The authors' first aim was to evaluate the prognosis impact and the factors associated with asynchrony. Their second aim was to compare the prevalence of asynchrony according to two methods of detection: a visual inspection of signals and a computerized method integrating electromyographic activity of the diaphragm.

METHODS

This was an ancillary study of a multicenter, randomized controlled trial comparing neurally adjusted ventilatory assist to pressure support ventilation. Asynchrony was quantified at 12, 24, 36, and 48 h after switching from controlled ventilation to a partial mode of ventilatory assistance according to the two methods. An asynchrony index greater than or equal to 10% defined severe asynchrony.

RESULTS

A total of 103 patients ventilated for a median duration of 5 days (interquartile range, 3 to 9 days) were included. Whatever the method used for quantification, severe patient-ventilator asynchrony was not associated with an alteration of the outcome. No factor was associated with severe asynchrony. The prevalence of asynchrony was significantly lower when the quantification was based on flow and pressure than when it was based on the electromyographic activity of the diaphragm at 0.3 min (interquartile range, 0.2 to 0.8 min) and 4.7 min (interquartile range, 3.2 to 7.7 min; P < 0.0001), respectively.

CONCLUSIONS

During the early phase of weaning in patients receiving a partial ventilatory mode, severe patient-ventilator asynchrony was not associated with adverse clinical outcome, although the prevalence of patient-ventilator asynchrony varies according to the definitions and methods used for detection.

Development and Validation of a Multi-Algorithm Analytic Platform to Detect Off-Target Mechanical Ventilation

Healthcare-specific analytic software is needed to process the large volumes of streaming physiologic waveform data increasingly available from life support devices such as mechanical ventilators. Detection of clinically relevant events from these data streams will advance understanding of critical illness, enable real-time clinical decision support, and improve both clinical outcomes and patient experience. We used mechanical ventilation waveform data (VWD) as a use case to address broader issues of data access and analysis including discrimination between true events and waveform artifacts. We developed an open source data acquisition platform to acquire VWD, and a modular, multi-algorithm analytic platform (ventMAP) to enable automated detection of off-target ventilation (OTV) delivery in critically-ill patients. We tested the hypothesis that use of artifact correction logic would improve the specificity of clinical event detection without compromising sensitivity. We showed that ventMAP could accurately detect harmful forms of OTV including excessive tidal volumes and common forms of patient-ventilator asynchrony, and that artifact correction significantly improved the specificity of event detection without decreasing sensitivity. Our multi-disciplinary approach has enabled automated analysis of high-volume streaming patient waveform data for clinical and translational research, and will advance the study and management of critically ill patients requiring mechanical ventilation.

Respiratory rate variability in sleeping adults without obstructive sleep apnea

Characterizing respiratory rate variability (RRV) in humans during sleep is challenging, since it requires the analysis of respiratory signals over a period of several hours. These signals are easily distorted by movement and volitional inputs. We applied the method of spectral analysis to the nasal pressure transducer signal in 38 adults with no obstructive sleep apnea, defined by an apnea‐hypopnea index <5, who underwent all‐night polysomnography (PSG). Our aim was to detect and quantitate RRV during the various sleep stages, including wakefulness. The nasal pressure transducer signal was acquired at 100 Hz and consecutive frequency spectra were generated for the length of the PSG with the Fast Fourier Transform. For each spectrum, we computed the amplitude ratio of the first harmonic peak to the zero frequency peak (H₁/DC), and defined as RRV as (100 − H₁/DC) %. RRV was greater during wakefulness compared to any sleep stage, including rapid‐eye‐movement. Furthermore, RRV correlated with the depth of sleep, being lowest during N3. Patients spent most their sleep time supine, but we found no correlation between RRV and body position. There was a correlation between respiratory rate and sleep stage, being greater in wakefulness than in any sleep stage. We conclude that RRV varies according to sleep stage. Moreover, spectral analysis of nasal pressure signal appears to provide a valid measure of RRV during sleep. It remains to be seen if the method can differentiate normal from pathological sleep patterns.

Efficacy of ventilator waveform observation for detection of patient-ventilator asynchrony during NIV: a multicentre study

The objective of this study was to assess ability to identify asynchronies during noninvasive ventilation (NIV) through ventilator waveforms according to experience and interface, and to ascertain the influence of breathing pattern and respiratory drive on sensitivity and prevalence of asynchronies.

35 expert and 35 nonexpert physicians evaluated 40 5-min NIV reports displaying flow–time and airway pressure–time tracings; identified asynchronies were compared with those ascertained by three examiners who evaluated the same reports displaying, additionally, tracings of diaphragm electrical activity. We determined: 1) sensitivity, specificity, and positive and negative predictive values; 2) the correlation between the double true index (DTI) of each report (i.e., the ratio between the sum of true positives and true negatives, and the overall breath count) and the corresponding asynchrony index (AI); and 3) the influence of breathing pattern and respiratory drive on both AI and sensitivity.

Sensitivities to detect asynchronies were low either according to experience (0.20 (95% CI 0.14–0.29) for expert versus 0.21 (95% CI 0.12–0.30) for nonexpert, p=0.837) or interface (0.28 (95% CI 0.17–0.37) for mask versus 0.10 (95% CI 0.05–0.16) for helmet, p<0.0001). DTI inversely correlated with the AI (r²=0.67, p<0.0001). Breathing pattern and respiratory drive did not affect prevalence of asynchronies and sensitivity.

Patient–ventilator asynchrony during NIV is difficult to recognise solely by visual inspection of ventilator waveforms.

Detection of patient–ventilator asynchrony during NIV by visual inspection of ventilator waveforms is difficulthttp://ow.ly/3ce930eGdn6

Automated logging of inspiratory and expiratory non-synchronized breathing (ALIEN) for mechanical ventilation

Asynchronous Events (AEs) during mechanical ventilation (MV) result in increased work of breathing and potential poor patient outcomes. Thus, it is important to automate AE detection. In this study, an AE detection method, Automated Logging of Inspiratory and Expiratory Non-synchronized breathing (ALIEN) was developed and compared between standard manual detection in 11 MV patients. A total of 5701 breaths were analyzed (median [IQR]: 500 [469-573] per patient). The Asynchrony Index (AI) was 51% [28-78]%. The AE detection yielded sensitivity of 90.3% and specificity of 88.3%. Automated AE detection methods can potentially provide clinicians with real-time information on patient-ventilator interaction.

Monitoring respiration: what the clinician needs to know

A recent large prospective cohort study showed an unexpectedly high in-hospital mortality after major non-cardiac surgery in Europe, as well as a high incidence of postoperative pulmonary complications. The direct effect of postoperative respiratory complications on mortality is still under investigation, for intensive care unit (ICU) and in the perioperative period. Although respiratory monitoring has not been actually proven to affect in-hospital mortality, it plays an important role in patient care, leading to appropriate setting of ventilatory support as well as risk stratification. The aim of this article is to provide an overview of various respiratory monitoring techniques including the role of conventional and most recent methods in the perioperative period and in critically ill patients. The most recent techniques proposed for bedside respiratory monitoring, including lung imaging, are presented and discussed, comparing them to those actually considered as gold standards.

Decreased respiratory rate variability during mechanical ventilation is associated with increased mortality

OBJECTIVE

Patients on ventilatory support often experience significant changes in respiratory rate. Our aim was to determine the possible association between respiratory rate variability (RRV) and outcomes in these patients.

DESIGN

A longitudinal, prospective, observational study of patients mechanically ventilated for at least 12 h performed in a medical-surgical intensive care unit. Patients were enrolled within 24 h of the initiation of ventilatory support. We measured airway signals continuously for the duration of ventilatory support and calculated expiratory flow frequency spectra at 2.5-min intervals. We assessed RRV using the amplitude ratio of the flow spectrum's first harmonic to the zero frequency component. Measures of the amplitude ratio were averaged over the total monitored time. Patients with time-averaged amplitude ratios <40 % were classified as high RRV and those ≥40 % as low RRV. All-cause mortality rates were assessed at 28 and 180 days from enrollment with a Cox proportional hazards model adjusted for disease acuity by the simplified acute physiology score II.

RESULTS

We enrolled 178 patients, of whom 47 had high RRV and 131 low RRV. Both groups had similar disease acuity upon enrollment. The 28- and 180-day mortality rates were greater for low RRV patients with hazard ratios of 4.81 (95 % CI 1.85-12.65, p = 0.001) and 2.26 (95 % CI 1.21-4.20, p = 0.01), respectively. Independent predictors of 28-day mortality were low RRV, i.v. vasopressin, and SAPS II.

CONCLUSIONS

Decreased RRV during ventilatory support is associated with increased mortality. The mechanisms responsible for this finding remain to be determined.

Year in review 2011: Critical Care - respirology

Management of acute respiratory failure is an important component of intensive care. In this review, we analyze 21 original research articles published last year in Critical Care in the field of respiratory and critical care medicine. The articles are summarized according to the following topic categories: acute respiratory distress syndrome, mechanical ventilation, adjunctive therapies, and pneumonia.

On the imperfect synchrony between patient and ventilator

Because patient-ventilator asynchrony (PVA) is recognized as a major clinical problem for patients undergoing ventilatory assistance, automatic methods of PVA detection have been proposed in recent years. A novel approach is airflow spectral analysis, which, when related to visual inspection of airway pressure and flow waveforms, has been shown to reach a sensitivity and specificity of greater than 80% in detecting an asynchrony index of greater than 10%. The availability of automatic non-invasive methods of PVA detection at the bedside would likely be of benefit in intensive care unit practice, but they may be limited by shortcomings, so clear proof of their effectiveness is needed.