Targeting Arterial Oxygen Saturation by Closed-Loop Control of Inspired Oxygen in Preterm Infants

Oxygenation Fluctuations Associated with Severe Retinopathy of Prematurity: Insights from a Multimodal Deep Learning Approach

Purpose

Retinopathy of prematurity (ROP) is one of the leading causes of blindness in children. Although the role of oxygen in the pathophysiology of ROP is well established, a precise understanding of the dynamic relationship between oxygen exposure ROP incidence and severity is lacking. The purpose of this study was to evaluate the correlation between time-dependent oxygen variables and the onset of ROP.

Design

Retrospective cohort study.

Participants

Two hundred thirty infants who were born at a single academic center and met the inclusion criteria were included. Infants are mainly born between January 2011 and October 2022.

Methods

Patient data were extracted from electronic health records (EHRs), with sufficient time-dependent oxygen data. Clinical outcomes for ROP were recorded as none/mild or moderate/severe (defined as type II or worse). Mixed-effects linear models were used to compare the 2 groups in terms of dynamic oxygen variables, such as daily average and the coefficient of variation (COV) fraction of inspired oxygen (FiO2). Support vector machine (SVM) and long-short-term memory (LSTM)-based multimodal models were trained with fivefold cross-validation to predict which infants would develop moderate/severe ROP. Gestational age (GA), birth weight, and time-dependent oxygen variables were used to develop predictive models.

Main Outcome Measures

Model cross-validation performance was evaluated by computing the mean area under the receiver operating characteristic (AUROC) curve, precision, recall, and F1 score.

Results

We found that both daily average and COV of FiO2 were associated with more severe ROP (adjusted P < 0.001). With fivefold cross-validation, the multimodal LSTM models had higher performance than the best static models (SVM using GA and 3 average FiO2 features) and SVM models trained on GA alone (mean AUROC = 0.89 ± 0.04 vs. 0.86 ± 0.05 vs. 0.83 ± 0.04).

Conclusions

The development of severe ROP might not only be influenced by oxygen exposure but also by its fluctuation, which provides direction for future study of pathophysiological factors associated with severe ROP development. Additionally, we demonstrated that multimodal neural networks can be a method to extract useful information from time-series data, which may be a valuable methodology for the investigation of other diseases using EHR data.

Financial Disclosures

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Care Bundle to Improve Oxygen Maintenance and Events

Prolonged periods spent outside the target range of oxygen saturation (SpO₂) in preterm infants, along with frequent desaturation events, predispose them to retinopathy of prematurity (ROP) and long-term neurodevelopmental impairment. The primary aim of this study was to increase the mean time spent within the target SpO₂ range (WTR) by 10% and to reduce the frequency of desaturation events by 5 events per patient day, respectively, within 18 months of implementing a care bundle.

Methods

This study was completed in a 46-bed neonatal intensive care unit (NICU), involving 246 staff members and led by a quality improvement team. The change interventions included implementing new practice guidelines, reviewing daily summaries of SpO₂ maintenance, daily infant wellness assessment, standardizing workflow, and responding to SpO₂ alarms. In addition, we collected staff satisfaction and compliance with change interventions, resource use, and morbidity and mortality data at discharge.

Results

The mean time spent WTR increased from 65.3% to 75.3%, and the frequency of desaturation events decreased from 25.1 to 16.5 events per patient day, respectively, with a higher magnitude of benefit in infants on days with supplemental oxygen. Postimplementation, the duration of high-frequency ventilation and supplemental oxygen were lower, but morbidity and mortality rates were similar. Staff satisfaction with training workshops, coaching, use of the infant wellness assessment tool, and SpO₂ alarm management algorithms were 74%, 82%, 80%, and 74%, respectively.

Conclusion

Implementing a care bundle to improve oxygen maintenance and reduce desaturation events increased the time spent WTR and reduced the frequency of desaturation events.

Closed-loop ventilation

PURPOSE OF REVIEW

The last 25 years have seen considerable development in modes of closed-loop ventilation and there are now several of them commercially available. They not only offer potential benefits for the individual patient, but may also improve the organization within the intensive care unit (ICU). Clinicians are showing both greater interest and willingness to address the issues of a caregiver shortage and overload of bedside work in the ICU. This article reviews the clinical benefits of using closed-loop ventilation modes, with a focus on control of oxygenation, lung protection, and weaning.

RECENT FINDINGS

Closed-loop ventilation modes are able to maintain important physiological variables, such as oxygen saturation measured by pulse oximetry, tidal volume (VT), driving pressure (ΔP), and mechanical power (MP), within target ranges aimed at ensuring continuous lung protection. In addition, these modes adapt the ventilator support to the patient's needs, promoting diaphragm activity and preventing over-assistance. Some studies have shown the potential of these modes to reduce the duration of both weaning and mechanical ventilation.

SUMMARY

Recent studies have primarily demonstrated the safety, efficacy, and feasibility of using closed-loop ventilation modes in the ICU and postsurgery patients. Large, multicenter randomized controlled trials are needed to assess their impact on important short- and long-term clinical outcomes, the organization of the ICU, and cost-effectiveness.

Clinical Evaluation of an Automatic Oxygen Control System for Premature Infants Receiving High-Flow Nasal Cannula for Respiratory Support: A Pilot Study

A pilot clinical study was conducted that compared the peripheral oxygen saturation (SpO2) targeting performance of an automatic oxygen control system with manual oxygen control, which is the standard of care for preterm and low birth weight infants on high-flow nasal cannula (HFNC). The new oxygen control device studied was used to automatically adjust the fraction of inspired oxygen (FiO2) according to a desired SpO2 target setpoint and measured feedback signals including the SpO2 and other signals. A crossover study was designed with several endpoints including the comparison of the percentage of time that the SpO2 was within the target range with the automatic oxygen control device versus manual oxygen control. Other metrics were also compared to assess the performance of the system including the number of bradycardia events. The pilot study included six patients that fit the inclusion criteria. The results showed that there were improvements in all of the measured outcomes considered including statistically significant improvements in the number of bradycardia events during the period when the automatic oxygen control device was used.

Automation of oxygen titration in preterm infants: Current evidence and future challenges

For the preterm infant with respiratory insufficiency requiring supplemental oxygen, tight control of oxygen saturation (SpO₂) is advocated, but difficult to achieve in practice. Automated control of oxygen delivery has emerged as a potential solution, with six control algorithms currently embedded in commercially-available respiratory support devices. To date, most clinical evaluations of these algorithms have been short-lived crossover studies, in which a benefit of automated over manual control of oxygen titration has been uniformly noted, along with a reduction in severe SpO₂ deviations and need for manual FiO₂ adjustments. A single non-randomised study has examined the effect of implementation of automated oxygen control with the CLiO₂ algorithm as standard care for preterm infants; no clear benefits in relation to clinical outcomes were noted, although duration of mechanical ventilation was lessened. The results of randomised controlled trials are awaited. Beyond the gathering of evidence regarding a treatment effect, we contend that there is a need for a better understanding of the function of contemporary control algorithms under a range of clinical conditions, further exploration of techniques of adaptation to individualise algorithm performance, and a concerted effort to apply this technology in low resource settings in which the majority of preterm infants receive care. Attainment of these goals will be paramount in optimisation of oxygen therapy for preterm infants globally.

The relationship between intermittent hypoxemia events and neural outcomes in neonates

This brief review examines 1) patterns of intermittent hypoxemia in extremely preterm infants during early postnatal life, 2) the relationship between neonatal intermittent hypoxemia exposure and outcomes in both human and animal models, 3) potential mechanistic pathways, and 4) future alterations in clinical care that may reduce morbidity. Intermittent hypoxemia events are pervasive in extremely preterm infants (<28 weeks gestation at birth) during early postnatal life. An increased frequency of intermittent hypoxemia events has been associated with a range of poor neural outcomes including language and cognitive delays, motor impairment, retinopathy of prematurity, impaired control of breathing, and intraventricular hemorrhage. Neonatal rodent models have shown that exposure to short repetitive cycles of hypoxia induce a pathophysiological cascade. However, not all patterns of intermittent hypoxia are deleterious and some may even improve neurodevelopmental outcomes. Therapeutic interventions include supplemental oxygen, pressure support and pharmacologic drugs but prolonged hyperoxia and pressure exposure have been associated with cardiopulmonary morbidity. Therefore, it becomes imperative to distinguish high risk from neutral and/or even beneficial patterns of intermittent hypoxemia during early postnatal life. Identification of such patterns could improve clinical care with targeted interventions for high-risk patterns and minimal or no exposure to treatment modalities for low-risk patterns.