Predicting Apnoeic Events in Preterm Infants

Detecting central apneas using multichannel signals in premature infants

Objective. Monitoring of apnea of prematurity, performed in neonatal intensive care units by detecting central apneas (CAs) in the respiratory traces, is characterized by a high number of false alarms. A two-step approach consisting of a threshold-based apneic event detection algorithm followed by a machine learning model was recently presented in literature aiming to improve CA detection. However, since this is characterized by high complexity and low precision, we developed a new direct approach that only consists of a detection model based on machine learning directly working with multichannel signals.Approach. The dataset used in this study consisted of 48 h of ECG, chest impedance and peripheral oxygen saturation extracted from 10 premature infants. CAs were labeled by two clinical experts. 47 features were extracted from time series using 30 s moving windows with an overlap of 5 s and evaluated in sets of 4 consecutive moving windows, in a similar way to what was indicated for the two-step approach. An undersampling method was used to reduce imbalance in the training set while aiming at increasing precision. A detection model using logistic regression with elastic net penalty and leave-one-patient-out cross-validation was then tested on the full dataset.Main results. This detection model returned a mean area under the receiver operating characteristic curve value equal to 0.86 and, after the selection of a FPR equal to 0.1 and the use of smoothing, an increased precision (0.50 versus 0.42) at the expense of a decrease in recall (0.70 versus 0.78) compared to the two-step approach around suspected apneic events.Significance. The new direct approach guaranteed correct detections for more than 81% of CAs with lengthL≥ 20 s, which are considered among the most threatening apneic events for premature infants. These results require additional verifications using more extensive datasets but could lead to promising applications in clinical practice.

The effect of vibrotactile stimulation on hypoxia-induced irregular breathing and apnea in preterm rabbits

BACKGROUND

Manual tactile stimulation is used to counteract apnea in preterm infants, but it is unknown when this intervention should be applied. We compared an anticipatory to a reactive approach using vibrotactile stimulation to prevent hypoxia induced apneas.

METHODS

Preterm rabbit kittens were prematurely delivered and randomized to either group. All kittens breathed spontaneously with a positive airway pressure of 8 cmH2O while they were imaged using phase contrast X-ray. Irregular breathing (IB) was induced using gradual hypoxia. The anticipatory group received stimulation at the onset of IB and the reactive group if IB transitioned into apnea. Breathing rate (BR), heart rate (HR) and functional residual capacity (FRC) were compared.

RESULTS

Anticipatory stimulation significantly reduced apnea incidence and maximum inter-breath intervals and increased BR following IB, compared to reactive stimulation. Recovery in BR but not HR was more likely with anticipatory stimulation, although both BR and HR were significantly higher at 120 s after stimulation onset. FRC values and variability were not different.

CONCLUSIONS

Anticipated vibrotactile stimulation is more effective in preventing apnea and enhancing breathing when compared to reactive stimulation in preterm rabbits. Stimulation timing is likely to be a key factor in reducing the incidence and duration of apnea.

IMPACT

Anticipated vibrotactile stimulation can prevent apnea and stimulate breathing effort in preterm rabbits. Anticipated vibrotactile stimulation increases the likelihood of breathing rate recovery following hypoxia induced irregular breathing, when compared to reactive stimulation. Automated stimulation in combination with predictive algorithms may improve the treatment of apnea in preterm infants.

Bradycardia May Decrease Cardiorespiratory Coupling in Preterm Infants

Bradycardia, frequently observed in preterm infants, presents significant risks due to the immaturity of their autonomic nervous system (ANS) and respiratory systems. These infants may face cardiorespiratory events, leading to severe complications like hypoxemia and neurodevelopmental disorders. Although neonatal care has advanced, the influence of bradycardia on cardiorespiratory coupling (CRC) remains elusive. This exploratory study delves into CRC in preterm infants, emphasizing disparities between events with and without bradycardia. Using the Preterm Infant Cardio-Respiratory Signals (PICS) database, we analyzed interbeat (R-R) and inter-breath intervals (IBI) from 10 preterm infants. The time series were segmented into bradycardic (B) and non-bradycardic (NB) segments. Employing information theory measures, we quantified the irregularity of cardiac and respiratory time series. Notably, B segments had significantly lower entropy values for R-R and IBI than NB segments, while mutual information was higher in NB segments. This could imply a reduction in the complexity of respiratory and cardiac dynamics during bradycardic events, potentially indicating weaker CRC. Building on these insights, this research highlights the distinctive physiological characteristics of preterm infants and underscores the potential of emerging non-invasive diagnostic tools.

Prevalence and Impact of Feeding-Related Events on Hospital Stay in Preterm and Term Newborns

BACKGROUND

Nursing assessment of milk flow regulation and associated apnea, bradycardia, and desaturation (ABD events) contribute to considerations for the discharge of newborns from the acute care setting. Research regarding infant feeding-related (FR) events (sucking and swallowing difficulties) and ABD events in moderate to late-preterm and full-term infants is lacking.

PURPOSE

This study observes the impact of FR and ABD events during feeding on hospital length of stay (LOS) and healthcare utilization (cost) in moderate-to-late preterm newborns, as well as full-term infants.

METHODS

In a retrospective study, bottle-fed infants admitted to the level II specialty care nursery of an academic community hospital in Southern California were observed for FR and ABD events. Statistical analyses were used to determine the impact of FR events on adjusted LOS, to evaluate the interaction between FR event status and adjusted LOS on total hospital charges, and to assess the statistical independence between FR events and diagnostic-related group severity.

RESULTS

The full sample of patient records included 308 infants born between 32- and 44-week gestational age between April 1, 2018, and October 31, 2022. LOS was twice as long in infants who had FR events. Total median charges were higher in the group with FR events at $160,165 versus $64,380 with non-FR events.

IMPLICATIONS FOR PRACTICE AND RESEARCH

Increased knowledge in the epidemiology and nursing care of infants experiencing milk flow regulation and associated ABD events is critical for informing practices and guidelines related to the prevention of related morbidities.

Comparison of oxygen supplementation in very preterm infants: Variations of oxygen saturation features and their application to hypoxemic episode based risk stratification

Background

Oxygen supplementation is commonly used to maintain oxygen saturation (SpO₂) levels in preterm infants within target ranges to reduce intermittent hypoxemic (IH) events, which are associated with short- and long-term morbidities. There is not much information available about differences in oxygenation patterns in infants undergoing such supplementations nor their relation to observed IH events. This study aimed to describe oxygenation characteristics during two types of supplementation by studying SpO₂ signal features and assess their performance in hypoxemia risk screening during NICU monitoring.

Subjects and methods

SpO₂ data from 25 infants with gestational age <32 weeks and birthweight <2,000 g who underwent a cross over trial of low-flow nasal cannula (NC) and digitally-set servo-controlled oxygen environment (OE) supplementations was considered in this secondary analysis. Features pertaining to signal distribution, variability and complexity were estimated and analyzed for differences between the supplementations. Univariate and regularized multivariate logistic regression was applied to identify relevant features and develop screening models for infants likely to experience a critically high number of IH per day of observation. Their performance was assessed using area under receiver operating curves (AUROC), accuracy, sensitivity, specificity and F1 scores.

Results

While most SpO₂ measures remained comparable during both supplementations, signal irregularity and complexity were elevated while on OE, pointing to more volatility in oxygen saturation during this supplementation mode. In addition, SpO₂ variability measures exhibited early prognostic value in discriminating infants at higher risk of critically many IH events. Poincare plot variability at lag 1 had AUROC of 0.82, 0.86, 0.89 compared to 0.63, 0.75, 0.81 for the IH number, a clinical parameter at observation times of 30 min, 1 and 2 h, respectively. Multivariate models with two features exhibited validation AUROC > 0.80, F1 score > 0.60 and specificity >0.85 at observation times ≥ 1 h. Finally, we proposed a framework for risk stratification of infants using a cumulative risk score for continuous monitoring.

Conclusion

Analysis of oxygen saturation signal routinely collected in the NICU, may have extensive applications in inferring subtle changes to cardiorespiratory dynamics under various conditions as well as in informing clinical decisions about infant care.

Sensory stimulation for apnoea mitigation in preterm infants

Apnoea, a pause in respiration, is ubiquitous in preterm infants and are often associated with physiological instability, which may lead to longer-term adverse neurodevelopmental consequences. Despite current therapies aimed at reducing the apnoea burden, preterm infants continue to exhibit apnoeic events throughout their hospital admission. Bedside staff are frequently required to manually intervene with different forms of stimuli, with the aim of re-establishing respiratory cadence and minimizing the physiological impact of each apnoeic event. Such a reactive approach makes apnoea and its associated adverse consequences inevitable and places a heavy reliance on human intervention. Different approaches to improving apnoea management in preterm infants have been investigated, including the use of various sensory stimuli. Despite studies reporting sensory stimuli of various forms to have potential in reducing apnoea frequency, non-invasive intermittent positive pressure ventilation is the only automated stimulus currently used in the clinical setting for infants with persistent apnoeic events. We find that the development of automated closed-looped sensory stimulation systems for apnoea mitigation in preterm infants receiving non-invasive respiratory support is warranted, including the possibility of stimulation being applied preventatively, and in a multi-modal form. IMPACT: This review examines the effects of various forms of sensory stimulation on apnoea mitigation in preterm infants, namely localized tactile, generalized kinesthetic, airway pressure, auditory, and olfactory stimulations. Amongst the 31 studies reviewed, each form of sensory stimulation showed some positive effects, although the findings were not definitive and comparative studies were lacking. We find that the development of automated closed-loop sensory stimulation systems for apnoea mitigation is warranted, including the possibility of stimulation being applied preventatively, and in a multi-modal form.

New method to measure interbreath intervals in infants for the assessment of apnoea and respiration

Background

Respiratory disorders, including apnoea, are common in preterm infants due to their immature respiratory control compared with term-born infants. However, our inability to accurately measure respiratory rate in hospitalised infants results in unreported episodes of apnoea and an incomplete picture of respiratory activity.

Methods

We develop, validate and use a novel algorithm to identify interbreath intervals (IBIs) and apnoeas in preterm infants. In 42 preterm infants (1600 hours of recordings), we assess IBIs from the chest electrical impedance pneumograph using an adaptive amplitude threshold for the detection of breaths. The algorithm is refined by comparing its accuracy with clinically observed breaths and pauses in breathing. We develop an automated classifier to differentiate periods of true apnoea from artefactually low amplitude signal. We assess the performance of this algorithm in the detection of morphine-induced respiratory depression. Finally, we use the algorithm to investigate whether retinopathy of prematurity (ROP) screening alters the IBI distribution.

Results

Individual breaths were detected with a false-positive rate of 13% and a false-negative rate of 12%. The classifier identified true apnoeas with an accuracy of 93%. As expected, morphine caused a significant shift in the IBI distribution towards longer IBIs. Following ROP screening, there was a significant increase in pauses in breathing that lasted more than 10 s (t-statistic=1.82, p=0.023). This was not reflected by changes in the monitor-derived respiratory rate and no episodes of apnoea were recorded in the medical records.

Conclusions

We show that our algorithm offers an improved method for the identification of IBIs and apnoeas in preterm infants. Following ROP screening, increased respiratory instability can occur even in the absence of clinically significant apnoeas. Accurate assessment of infant respiratory activity is essential to inform clinical practice.

Apnoea of Prematurity and Neurodevelopmental Outcomes: Current Understanding and Future Prospects for Research

Infants who are born prematurely are at significant risk of apnoea. In addition to the short-term consequences such as hypoxia, apnoea of prematurity has been associated with long-term morbidity, including poor neurodevelopmental outcomes. Clinical trials have illustrated the importance of methylxanthine drugs, in particular caffeine, in reducing the risk of long term adverse neurodevelopmental outcomes. However, the extent to which apnoea is causative of this secondary neurodevelopmental delay or is just associated in a background of other sequelae of prematurity remains unclear. In this review, we first discuss the pathophysiology of apnoea of prematurity, previous studies investigating the relationship between apnoea and neurodevelopmental delay, and treatment of apnoea with caffeine therapy. We propose a need for better methods of measuring apnoea, along with improved understanding of the neonatal brain's response to consequent hypoxia. Only then can we start to disentangle the effects of apnoea on neurodevelopment in preterm infants. Moreover, by better identifying those infants who are at risk of apnoea, and neurodevelopmental delay, we can work toward a risk stratification system for these infants that is clinically actionable, for example, with doses of caffeine tailored to the individual. Optimising treatment of apnoea for individual infants will improve neonatal care and long-term outcomes for this population.

Towards Continuous Camera-Based Respiration Monitoring in Infants

Aiming at continuous unobtrusive respiration monitoring, motion robustness is paramount. However, some types of motion can completely hide the respiration information and the detection of these events is required to avoid incorrect rate estimations. Therefore, this work proposes a motion detector optimized to specifically detect severe motion of infants combined with a respiration rate detection strategy based on automatic pixels selection, which proved to be robust to motion of the infants involving head and limbs. A dataset including both thermal and RGB (Red Green Blue) videos was used amounting to a total of 43 h acquired on 17 infants. The method was successfully applied to both RGB and thermal videos and compared to the chest impedance signal. The Mean Absolute Error (MAE) in segments where some motion is present was 1.16 and 1.97 breaths/min higher than the MAE in the ideal moments where the infants were still for testing and validation set, respectively. Overall, the average MAE on the testing and validation set are 3.31 breaths/min and 5.36 breaths/min, using 64.00% and 69.65% of the included video segments (segments containing events such as interventions were excluded based on a manual annotation), respectively. Moreover, we highlight challenges that need to be overcome for continuous camera-based respiration monitoring. The method can be applied to different camera modalities, does not require skin visibility, and is robust to some motion of the infants.