Breathing: does regular mean normal?

Biosignal-Based Digital Biomarkers for Prediction of Ventilator Weaning Success

We evaluated new features from biosignals comprising diverse physiological response information to predict the outcome of weaning from mechanical ventilation (MV). We enrolled 89 patients who were candidates for weaning from MV in the intensive care unit and collected continuous biosignal data: electrocardiogram (ECG), respiratory impedance, photoplethysmogram (PPG), arterial blood pressure, and ventilator parameters during a spontaneous breathing trial (SBT). We compared the collected biosignal data's variability between patients who successfully discontinued MV (n = 67) and patients who did not (n = 22). To evaluate the usefulness of the identified factors for predicting weaning success, we developed a machine learning model and evaluated its performance by bootstrapping. The following markers were different between the weaning success and failure groups: the ratio of standard deviations between the short-term and long-term heart rate variability in a Poincaré plot, sample entropy of ECG and PPG, α values of ECG, and respiratory impedance in the detrended fluctuation analysis. The area under the receiver operating characteristic curve of the model was 0.81 (95% confidence interval: 0.70-0.92). This combination of the biosignal data-based markers obtained during SBTs provides a promising tool to assist clinicians in determining the optimal extubation time.

Breathing variability-implications for anaesthesiology and intensive care

The respiratory system reacts instantaneously to intrinsic and extrinsic inputs. This adaptability results in significant fluctuations in breathing parameters, such as respiratory rate, tidal volume, and inspiratory flow profiles. Breathing variability is influenced by several conditions, including sleep, various pulmonary diseases, hypoxia, and anxiety disorders. Recent studies have suggested that weaning failure during mechanical ventilation may be predicted by low respiratory variability. This review describes methods for quantifying breathing variability, summarises the conditions and comorbidities that affect breathing variability, and discusses the potential implications of breathing variability for anaesthesia and intensive care.

Development and validation of a sample entropy-based method to identify complex patient-ventilator interactions during mechanical ventilation

Patient-ventilator asynchronies can be detected by close monitoring of ventilator screens by clinicians or through automated algorithms. However, detecting complex patient-ventilator interactions (CP-VI), consisting of changes in the respiratory rate and/or clusters of asynchronies, is a challenge. Sample Entropy (SE) of airway flow (SE-Flow) and airway pressure (SE-Paw) waveforms obtained from 27 critically ill patients was used to develop and validate an automated algorithm for detecting CP-VI. The algorithm's performance was compared versus the gold standard (the ventilator's waveform recordings for CP-VI were scored visually by three experts; Fleiss' kappa = 0.90 (0.87-0.93)). A repeated holdout cross-validation procedure using the Matthews correlation coefficient (MCC) as a measure of effectiveness was used for optimization of different combinations of SE settings (embedding dimension, m, and tolerance value, r), derived SE features (mean and maximum values), and the thresholds of change (Th) from patient's own baseline SE value. The most accurate results were obtained using the maximum values of SE-Flow (m = 2, r = 0.2, Th = 25%) and SE-Paw (m = 4, r = 0.2, Th = 30%) which report MCCs of 0.85 (0.78-0.86) and 0.78 (0.78-0.85), and accuracies of 0.93 (0.89-0.93) and 0.89 (0.89-0.93), respectively. This approach promises an improvement in the accurate detection of CP-VI, and future study of their clinical implications.

Lower interbreath interval complexity is associated with extubation failure in mechanically ventilated patients during spontaneous breathing trials

OBJECTIVE

To determine whether lower complexity of interbreath interval as measured with nonlinear analysis techniques will identify patients who fail to separate from mechanical ventilation after 30-minute spontaneous breathing trials (SBTs).

METHODS

Respiratory waveforms from SBT of patients in surgical or burn intensive care units were recorded for later analysis. The decision to extubate was made by attending physician. Extubated patients were observed for 48 hours; during this time, reintubation or noninvasive positive pressure ventilation was considered as a failure. Analysis of waveform data by software was performed post hoc. Sample entropy (SampEn) and other nonlinear measures were 48 hours of extubation.

RESULTS

Thirty-two patients (24 burn, 8 trauma/surgical admissions; mean age, 40.2 +/- 16.9 years; 26 men and 6 women) who were intubated >24 hours were extubated after SBT. Twenty-four patients were successfully separated from mechanical ventilation and eight failed. Age, gender, and mechanism of injury did not influence outcome. SampEn calculated for the two groups presented in this study was different with the cohort that failed extubation having a lower mean value (1.35 +/- 0.39 vs. 1.87 +/- 0.27; p < 0.001). Other nonlinear metrics were moved in concert with SampEn. The stationarity in the respiratory signal was not different between groups.

CONCLUSION

In intubated patients, the interbreath interval in those who were successfully separated from mechanical ventilation was more irregular than those who failed, as measured by nonlinear techniques. When available at bedside, these metrics may be useful markers of pulmonary health and assist in clinical decision making.

Biosignal analysis techniques for weaning outcome assessment

Discontinuation of mechanical ventilation in critically ill patients is a challenging task and involves a careful weighting of the benefits of early extubation and the risks of premature spontaneous breathing trial. Recently, apart from studying different physiological variables by means of descriptive statistical tests, breathing pattern variability analysis has been performed for the assessment of weaning readiness. A limited number of clinical studies implementing different weaning protocols in heterogeneous groups of patients and using a variable set of signal processing techniques have appeared in the critical care literature, with varying results. The purpose of this review article is 3-fold: (1) to describe the different signal processing techniques being implemented for the assessment of weaning readiness, (2) to provide insight into the pathophysiological mechanisms that may govern breath-to-breath variability/complexity in health and disease, and (3) to present results from the critical care literature derived from the application of biosignal analysis tools for the identification of possible weaning indices.

Online monitoring of pulse pressure variation to guide fluid therapy after cardiac surgery

BACKGROUND

The arterial pulse pressure variation induced by mechanical ventilation (deltaPP) has been shown to be a predictor of fluid responsiveness. Until now, deltaPP has had to be calculated offline (from a computer recording or a paper printing of the arterial pressure curve), or to be derived from specific cardiac output monitors, limiting the widespread use of this parameter. Recently, a method has been developed for the automatic calculation and real-time monitoring of deltaPP using standard bedside monitors. Whether this method is to predict reliable predictor of fluid responsiveness remains to be determined.

METHODS

We conducted a prospective clinical study in 59 mechanically ventilated patients in the postoperative period of cardiac surgery. Patients studied were considered at low risk for complications related to fluid administration (pulmonary artery occlusion pressure < 20 mm Hg, left ventricular ejection fraction > or = 40%). All patients were instrumented with an arterial line and a pulmonary artery catheter. Cardiac filling pressures and cardiac output were measured before and after intravascular fluid administration (20 mL/kg of lactated Ringer's solution over 20 min), whereas deltaPP was automatically calculated and continuously monitored.

RESULTS

Fluid administration increased cardiac output by at least 15% in 39 patients (66% = responders). Before fluid administration, responders and nonresponders were comparable with regard to right atrial and pulmonary artery occlusion pressures. In contrast, deltaPP was significantly greater in responders than in nonresponders (17% +/- 3% vs 9% +/- 2%, P < 0.001). The deltaPP cut-off value of 12% allowed identification of responders with a sensitivity of 97% and a specificity of 95%.

CONCLUSION

Automatic real-time monitoring of deltaPP is possible using a standard bedside monitor and was found to be a reliable method to predict fluid responsiveness after cardiac surgery. Additional studies are needed to determine if this technique can be used to avoid the complications of fluid administration in high-risk patients.

Breathing pattern variability: a weaning predictor in postoperative patients recovering from systemic inflammatory response syndrome

OBJECTIVE

To investigate whether breathing pattern variability can serve as a potential weaning predictor for postoperative patients recovering from systemic inflammatory response syndrome (SIRS).

DESIGN AND SETTING

A prospective measurement of retrospectively analyzed breathing pattern variability in a surgical intensive care unit.

PATIENTS

Seventy-eight mechanically ventilated SIRS patients who had undergone abdominal surgery were included when they were ready for weaning. They were divided into success (n=57) and failure (n=21) groups based upon their weaning outcome.

MEASUREMENTS AND RESULTS

Before weaning, tidal volume, total breath duration, inspiratory time, expiratory time, and peak inspiratory flow were continuously monitored for 30 min, while patients received 5 cmH2O pressure support weaning trial. After the patients successfully completed the trial, they were extubated. Successful weaning was defined as patients free from the ventilator for over 48 h, whereas a weaning failure was considered as reinstitution of mechanical ventilation within 48 h of extubation. The coefficient of variation and two values of standard deviation (SD1 and SD2; indicators of the dispersion of data points in the plot) obtained from the Poincaré plot of five respiratory parameters in the failure group were significantly lower than those in the success group. The area under the receiver operating characteristic curve of these variability indices was within the range of 0.73-0.80, indicating the accuracy of prediction.

CONCLUSIONS

Small breathing pattern variability is associated with a high incidence of weaning failure in postoperative patients recovering from SIRS, and this variability may potentially serve as a weaning predictor.