Pre-apneic capnography waveform abnormalities during procedural sedation and analgesia

Deep learning classification of capnography waveforms: secondary analysis of the PRODIGY study

Capnography monitors trigger high priority 'no breath' alarms when CO2 measurements do not exceed a given threshold over a specified time-period. False alarms occur when the underlying breathing pattern is stable, but the alarm is triggered when the CO2 value reduces even slightly below the threshold. True 'no breath' events can be falsely classified as breathing if waveform artifact causes an aberrant spike in CO2 values above the threshold. The aim of this study was to determine the accuracy of a deep learning approach to classifying segments of capnography waveforms as either 'breath' or 'no breath'. A post hoc secondary analysis of data from 9 North American sites included in the PRediction of Opioid-induced Respiratory Depression In Patients Monitored by capnoGraphY (PRODIGY) study was conducted. We used a convolutional neural network to classify 15 s capnography waveform segments drawn from a random sample of 400 participants. Loss was calculated over batches of 32 using the binary cross-entropy loss function with weights updated using the Adam optimizer. Internal-external validation was performed by iteratively fitting the model using data from all but one hospital and then assessing its performance in the remaining hospital. The labelled dataset consisted of 10,391 capnography waveform segments. The neural network's accuracy was 0.97, precision was 0.97 and recall was 0.96. Performance was consistent across hospitals in internal-external validation. The neural network could reduce false capnography alarms. Further research is needed to compare the frequency of alarms derived from the neural network with the standard approach.

Predicting Prolonged Apnea During Nurse-Administered Procedural Sedation: Machine Learning Study

BACKGROUND

Capnography is commonly used for nurse-administered procedural sedation. Distinguishing between capnography waveform abnormalities that signal the need for clinical intervention for an event and those that do not indicate the need for intervention is essential for the successful implementation of this technology into practice. It is possible that capnography alarm management may be improved by using machine learning to create a "smart alarm" that can alert clinicians to apneic events that are predicted to be prolonged.

OBJECTIVE

To determine the accuracy of machine learning models for predicting at the 15-second time point if apnea will be prolonged (ie, apnea that persists for >30 seconds).

METHODS

A secondary analysis of an observational study was conducted. We selected several candidate models to evaluate, including a random forest model, generalized linear model (logistic regression), least absolute shrinkage and selection operator regression, ridge regression, and the XGBoost model. Out-of-sample accuracy of the models was calculated using 10-fold cross-validation. The net benefit decision analytic measure was used to assist with deciding whether using the models in practice would lead to better outcomes on average than using the current default capnography alarm management strategies. The default strategies are the aggressive approach, in which an alarm is triggered after brief periods of apnea (typically 15 seconds) and the conservative approach, in which an alarm is triggered for only prolonged periods of apnea (typically >30 seconds).

RESULTS

A total of 384 apneic events longer than 15 seconds were observed in 61 of the 102 patients (59.8%) who participated in the observational study. Nearly half of the apneic events (180/384, 46.9%) were prolonged. The random forest model performed the best in terms of discrimination (area under the receiver operating characteristic curve 0.66) and calibration. The net benefit associated with the random forest model exceeded that associated with the aggressive strategy but was lower than that associated with the conservative strategy.

CONCLUSIONS

Decision curve analysis indicated that using a random forest model would lead to a better outcome for capnography alarm management than using an aggressive strategy in which alarms are triggered after 15 seconds of apnea. The model would not be superior to the conservative strategy in which alarms are only triggered after 30 seconds.

High flow nasal oxygen during procedural sedation for cardiac implantable electronic device procedures: A randomised controlled trial

BACKGROUND

High flow nasal oxygen may better support the vulnerable respiratory state of patients during procedural sedation.

OBJECTIVE

The objective of this study was to investigate the effects of high flow nasal oxygen in comparison to facemask oxygen on ventilation during cardiac implantable electronic device procedures performed with procedural sedation.

DESIGN

A randomised controlled trial.

SETTING

The study was conducted at one academic hospital in Canada.

PARTICIPANTS

Adults undergoing elective cardiac implantable electronic device procedures with sedation administered by an anaesthesia assistant, supervised by an anaesthesiologist from August 2019 to March 2020.

INTERVENTIONS

Participants were randomised 1 : 1 to facemask (≥ 8 l · min-1) or high flow nasal oxygen (50 l · min-1 and a 50 : 50 oxygen to air ratio).

MAIN OUTCOME MEASURES

The primary outcome was peak transcutaneous carbon dioxide. Outcomes were analysed using Bayesian statistics.

RESULTS

The 129 participants who were randomised and received sedation were included. The difference in peak transcutaneous carbon dioxide was 0.0 kPa (95% CI -0.17 to 0.18). Minor adverse sedation events were 6.4 times more likely to occur in the high flow nasal oxygen group. This estimate is imprecise (95% CI 1.34 to 42.99). The odds ratio for oxygen desaturation for the high flow nasal oxygen group compared with the facemask group was 1.2 (95% CI 0.37 to 3.75). The difference in satisfaction with sedation scores between groups was 0.0 (95% CI -0.33 to 0.23).

CONCLUSIONS

Ventilation, as measured by TcCO2, is highly unlikely to differ by a clinically important amount between high flow nasal oxygen at 50 l min-1 or facemask oxygen at 8 l min-1. Further research with a larger sample size would be required to determine the optimal oxygen:air ratio when using high flow nasal oxygen during cardiac implantable electronic device procedures performed with sedation.

TRIAL REGISTRATION NUMBER

NCT03858257.