Vital signs as physiomarkers of neonatal sepsis

Continuous prediction and clinical alarm management of late-onset sepsis in preterm infants using vital signs from a patient monitor

BACKGROUND AND OBJECTIVE

Continuous prediction of late-onset sepsis (LOS) could be helpful for improving clinical outcomes in neonatal intensive care units (NICU). This study aimed to develop an artificial intelligence (AI) model for assisting the bedside clinicians in successfully identifying infants at risk for LOS using non-invasive vital signs monitoring.

METHODS

In a retrospective study from the NICU of the Máxima Medical Center in Veldhoven, the Netherlands, a total of 492 preterm infants less than 32 weeks gestation were included between July 2016 and December 2018. Data on heart rate (HR), respiratory rate (RR), and oxygen saturation (SpO2) at 1 Hz were extracted from the patient monitor. We developed multiple AI models using 102 extracted features or raw time series to provide hourly LOS risk prediction. Shapley values were used to explain the model. For the best performing model, the effect of different vital signs and also the input type of signals on model performance was tested. To further assess the performance of applying the best performing model in a real-world clinical setting, we performed a simulation using four different alarm policies on continuous real-time predictions starting from three days after birth.

RESULTS

A total of 51 LOS patients and 68 controls were finally included according to the patient inclusion and exclusion criteria. When tested by seven-fold cross-validations, the mean (standard deviation) area under the receiver operating characteristic curve (AUC) six hours before CRASH was 0.875 (0.072) for the best performing model, compared to the other six models with AUC ranging from 0.782 (0.089) to 0.846 (0.083). The best performing model performed only slightly worse than the model learning from raw physiological waveforms (0.886 [0.068]), successfully detecting 96.1 % of LOS patients before CRASH. When setting the expected alarm window to 24 h and using a multi-threshold alarm policy, the sensitivity metric was 71.6 %, while the positive predictive value was 9.9 %, resulting in an average of 1.15 alarms per day per patient.

CONCLUSIONS

The proposed AI model, which learns from routinely collected vital signs, has the potential to assist clinicians in the early detection of LOS. Combined with interpretability and clinical alarm management, this model could be better translated into medical practice for future clinical implementation.

Metabolic trade-offs in Neonatal sepsis triggered by TLR4 and TLR1/2 ligands result in unique dysfunctions in neural breathing circuits

Neonatal sepsis remains one of the leading causes of mortality in newborns. Several brainstem-regulated physiological processes undergo disruption during neonatal sepsis. Mechanistic knowledge gaps exist at the interplay between metabolism and immune activation to brainstem neural circuits and pertinent physiological functions in neonates. To delineate this association, we induced systemic inflammation either by TLR4 (LPS) or TLR1/2 (PAM3CSK4) ligand administration in postnatal day 5 mice (PD5). Our findings show that LPS and PAM3CSK4 evoke substantial changes in respiration and metabolism. Physiological trade-offs led to hypometabolic-hypothermic responses due to LPS, but not PAM3CSK4, whereas to both TLR ligands blunted respiratory chemoreflexes. Neuroinflammatory pathways modulation in brainstem showed more robust effects in LPS than PAM3CSK4. Brainstem neurons, microglia, and astrocyte gene expression analyses showed unique responses to TLR ligands. PAM3CSK4 did not significantly modulate gene expression changes in GLAST-1 positive brainstem astrocytes. PD5 pups receiving PAM3CSK4 failed to maintain a prolonged metabolic state repression, which correlated to enhanced gasping latency and impaired autoresuscitation during anoxic chemoreflex challenges. In contrast, LPS administered pups showed no significant changes in anoxic chemoreflex. Electrophysiological studies from brainstem slices prepared from pups exposed to either TLR4 or PAM3CSK4 showed compromised transmission between preBötzinger complex and Hypoglossal as an exclusive response to the TLR1/2 ligand. Spatial gene expression analysis demonstrated a region-specific modulation of PAM3CSK4 within the raphe nucleus relative to other anatomical sites evaluated. Our findings suggest that metabolic changes due to inflammation might be a crucial tolerance mechanism for neonatal sepsis preserving neural control of breathing.

Antibiotic Stewardship in the Neonatal Intensive Care Unit

Antibiotic stewardship is a multidisciplinary, evidence-based approach to optimize antibiotic use and mitigate development of antibiotic resistance. Neonates have high rates of antibiotic exposure, particularly those born preterm and admitted to the NICU, and mounting evidence describes the adverse consequences of such exposures in the absence of infection. Here, we review the general principles of antibiotic stewardship and how they can be applied in NICUs. The unique characteristics of NICUs and patients cared for in this setting, which warrant unique implementation strategies and special considerations are discussed. We summarize current antibiotic use metrics for assessment of responses to stewardship interventions and changes over time, and review evidence-based infection prevention practices in the NICU. Current recommendations for empiric antibiotic use in the NICU and the utility of infection biomarkers are summarized. Lastly, given the growing global threat of increasing antibiotic resistance, specific threats in the NICU are highlighted.

Sepsis Huddles in the Neonatal Intensive Care Unit: A Retrospective Cohort Study of Late-onset Infection Recognition and Severity Assessment

OBJECTIVE

To analyze relationships between provider-documented signs prompting sepsis evaluations, assessments of illness severity, and late-onset infection (LOI).

STUDY DESIGN

Retrospective cohort study of all infants receiving a sepsis huddle in conjunction with a LOI evaluation. Participants were ≥3 days old and admitted to a level IV neonatal intensive care unit (NICU) from September 2018 through May 2021. Data were extracted from standardized sepsis huddle notes in the electronic health record, including clinical signs prompting LOI evaluations, illness severity assessments (from least to most severe: green, yellow, and red), and management plans. To analyze relationships of sepsis huddle characteristics with the detection of culture-confirmed LOI (bacteremia, urinary tract infection, or meningitis), we utilized diagnostic test statistics, area under the receiver-operator characteristic analyses, and multivariable logistic regression.

RESULTS

We identified 1209 eligible sepsis huddles among 604 infants. There were 111 culture-confirmed LOI episodes (9% of all huddles). Twelve clinical signs of infection poorly distinguished infants with and without LOI, with sensitivity for each ranging from 2% to 36% and area under the receiver-operator characteristic ranging 0.49-0.53. Multivariable logistic regression identified increasing odds of infection with higher perceived illness severity at the time of sepsis huddle, adjusted for gestational age and receipt of intensive care supports.

CONCLUSIONS

Clinical signs prompting sepsis huddles were nonspecific and not predictive of concurrent LOI. Higher perceived illness severity was associated with presence of infection, despite some misclassification based on objective criteria. In level IV NICUs, antimicrobial stewardship through development of criteria for antibiotic noninitiation may be challenging, as presenting signs of LOI are similar among infants with and without confirmed infection.

Urinary tract infections in very premature neonates: the definition dilemma

BACKGROUND AND OBJECTIVES

Data on urinary tract infections (UTIs) in very preterm neonates (VPTNs) are scarce. We aimed to (i) describe the characteristics of UTIs in VPTNs and (ii) compare the diagnostic practices of neonatal clinicians to established pediatric guidelines.

METHODS

All VPTNs (<29 weeks GA) with a suspected UTI at the CHU Sainte-Justine neonatal intensive care unit from January 1, 2014, and December 31, 2019, were included and divided into two definition categories: Possible UTI, and Definite UTI.

RESULTS

Most episodes were Possible UTI (87%). Symptoms of UTIs and pathogens varied based on the definition category. A positive urinalysis was obtained in 25%. Possible UTI episodes grew 2 organisms in 62% of cases and <50,000 CFU/mL in 62% of cases.

CONCLUSION

Characteristics of UTIs in VPTNs vary based on the definition category and case definitions used by clinicians differ from that of established pediatric guidelines.

Heart rate and oxygen saturation patterns in very low birth weight infants with early onset sepsis and histologic chorioamnionitis

BACKGROUND

Chorioamnionitis and early onset sepsis (EOS) in very low birth weight (VLBW,< 1500 g) infants may cause a systemic inflammatory response reflected in patterns of heart rate (HR) and oxygenation measured by pulse oximetry (SpO2). Identification of these patterns might inform decisions about duration of antibiotic therapy after birth.

OBJECTIVE

Compare early HR and SpO2 patterns in VLBW infants with or without early onset sepsis (EOS) or histologic chorioamnionitis (HC).

STUDY DESIGN

Retrospective study of placental pathology and HR and SpO2 in the first 72 h from birth in relation to EOS status for inborn VLBW NICU patients 2012-2019.

RESULT

Among 362 VLBW infants with HR and SpO2 data available, clinical, or culture-positive EOS occurred in 91/362 (25%) and HC in 81/355 (22%). In univariate analysis, EOS was associated with higher mean HR, lower mean SpO2, and less negative skewness of HR in the first 3 days after birth. HC was associated with higher standard deviation and skewness of HR but no difference in SpO2. In multivariable modeling, significant risk factors for EOS were mean HR, gestational age, HC, mean SpO2, and skewness of SpO2.

CONCLUSION

HR and SpO2 patterns differ shortly after birth in VLBW infants exposed to HC or with EOS, likely reflecting a systemic inflammatory response.

Impact of race on heart rate characteristics monitoring in very low birth weight infants

BACKGROUND

A multicenter RCT showed that displaying a heart rate characteristics index (HRCi) predicting late-onset sepsis reduced mortality for VLBW infants. We aimed to assess whether HRCi display had a differential impact for Black versus White infants.

METHODS

We performed secondary data analysis of Black and White infants enrolled in the HeRO RCT. We evaluated the predictive performance of the HRCi for infants with Black or White maternal race. Using models adjusted for birth weight, we assessed outcomes and interventions for a race × randomization interaction.

RESULTS

Among 2607 infants, Black infants had lower birth weight, gestational age, length of stay, and ventilator days, while sepsis and mortality were similar. The HRCi performed equally for sepsis prediction in Black and White infants. We found no differential effect of randomization by race on sepsis, mortality, antibiotic days, length of stay, or ventilator days. However, there was a differential randomization effect by race for blood cultures per patient: White RR 1.11 (95% CrI 1.04-1.18), Black RR 1.00 (0.93-1.07).

CONCLUSIONS

The HRCi performed similarly for sepsis prediction in Black and White infants. Randomization to HRCi display increased blood cultures in White but not in Black infants, while the impact on other outcomes or interventions was similar.

IMPACT

Predictive analytics, such as heart rate characteristics (HRC) monitoring for late-onset neonatal sepsis, should have equal impact among patients of different race. Infants with Black or White maternal race randomized to HRC display had similar outcomes, but randomization to the study arm increased a related clinical intervention, blood cultures, in White but not in Black infants. This study provides evidence of a differential effect of predictive models on clinical care by race. The work will promote consideration and analysis of equity in the implementation of predictive analytics.

Ventilatory and Orthostatic Challenges Reveal Biomarkers for Neurocognition in Children and Young Adults With Congenital Central Hypoventilation Syndrome

BACKGROUND

Children and young adults with congenital central hypoventilation syndrome (CCHS) are at risk of cognitive deficits. They experience autonomic dysfunction and chemoreceptor insensitivity measured during ventilatory and orthostatic challenges, but relationships between these features are undefined.

RESEARCH QUESTION

Can a biomarker be identified from physiologic responses to ventilatory and orthostatic challenges that is related to neurocognitive outcomes in CCHS?

STUDY DESIGN AND METHODS

This retrospective study included 25 children and young adults with CCHS tested over an inpatient stay. Relationships between physiologic measurements during hypercarbic and hypoxic ventilatory challenges, hypoxic ventilatory challenges, and orthostatic challenges and neurocognitive outcomes (by Wechsler intelligence indexes) were examined. Independent variable inclusion was determined by significant associations in Pearson's analyses. Multivariate linear regressions were used to assess relationships between measured physiologic responses to challenges and neurocognitive scores.

RESULTS

Significant relationships were identified between areas of fluid intelligence and measures of oxygen saturation (SpO2) and heart rate (HR) during challenges. Specifically, perceptual reasoning was related to HR (adjusted regression [β] coefficient, -0.68; 95% CI, 1.24 to -0.12; P = .02) during orthostasis. Working memory was related to change in HR (β, -1.33; 95% CI, -2.61 to -0.05; P = .042) during the hypoxic ventilatory challenge. Processing speed was related to HR (β, -1.19; 95% CI, -1.93 to -0.46; P = .003) during orthostasis, to baseline SpO2 (hypercarbic and hypoxic β, 8.57 [95% CI, 1.63-15.51]; hypoxic β, 8.37 [95% CI, 3.65-13.11]; P = .002 for both) during the ventilatory challenges, and to intrachallenge SpO2 (β, 5.89; 95% CI, 0.71-11.07; P = .028) during the hypoxic ventilatory challenge.

INTERPRETATION

In children and young adults with CCHS, SpO2 and HR-or change in HR-at rest and as a response to hypoxia and orthostasis are related to cognitive outcomes in domains of known risk, particularly fluid reasoning. These findings can guide additional research on the usefulness of these as biomarkers in understanding the impact of daily physical stressors on neurodevelopment in this high-risk group.

Respiratory Rate Extraction from Neonatal Near-Infrared Spectroscopy Signals

Background: Near-infrared spectroscopy (NIRS) relative concentration signals contain 'noise' from physiological processes such as respiration and heart rate. Simultaneous assessment of NIRS and respiratory rate (RR) using a single sensor would facilitate a perfectly time-synced assessment of (cerebral) physiology. Our aim was to extract respiratory rate from cerebral NIRS intensity signals in neonates admitted to a neonatal intensive care unit (NICU). Methods: A novel algorithm, NRR (NIRS RR), is developed for extracting RR from NIRS signals recorded from critically ill neonates. In total, 19 measurements were recorded from ten neonates admitted to the NICU with a gestational age and birth weight of 38 ± 5 weeks and 3092 ± 990 g, respectively. We synchronously recorded NIRS and reference RR signals sampled at 100 Hz and 0.5 Hz, respectively. The performance of the NRR algorithm is assessed in terms of the agreement and linear correlation between the reference and extracted RRs, and it is compared statistically with that of two existing methods. Results: The NRR algorithm showed a mean error of 1.1 breaths per minute (BPM), a root mean square error of 3.8 BPM, and Bland-Altman limits of agreement of 6.7 BPM averaged over all measurements. In addition, a linear correlation of 84.5% (p < 0.01) was achieved between the reference and extracted RRs. The statistical analyses confirmed the significant (p < 0.05) outperformance of the NRR algorithm with respect to the existing methods. Conclusions: We showed the possibility of extracting RR from neonatal NIRS in an intensive care environment, which showed high correspondence with the reference RR recorded. Adding the NRR algorithm to a NIRS system provides the opportunity to record synchronously different physiological sources of information about cerebral perfusion and respiration by a single monitoring system. This allows for a concurrent integrated analysis of the impact of breathing (including apnea) on cerebral hemodynamics.

Global, regional, and national burden of neonatal sepsis and other neonatal infections, 1990-2019: findings from the Global Burden of Disease Study 2019

To provide an overview of the global, regional, and national incidence and mortality of neonatal sepsis and other neonatal infections (NS) and their change trends from 1990 to 2019, based on the data from the 2019 Global Burden of Disease study. This was a retrospective demographic analysis based on aggregated data. Annual incident cases, deaths, age-standardized incidence rate (ASIR), age-standardized mortality rate (ASMR) and their percentage changes of NS during 1990-2019 were collected from the 2019 Global Burden of Disease study. Globally, the incident cases of NS increased by 12.79% (from 5.59 million in 1990 to 6.31 million in 2019), and the deaths decreased by 12.93% (from 0.26 million in 1990 to 0.23 million in 2019). In the globe, the ASIR of NS per 100,000 population increased by 14.35% (from 85.21 in 1990 to 97.43 in 2019), and the ASMR decreased by 11.91% (from 3.97 in 1990 to 3.5 in 2019).

CONCLUSION

Increasing trends in incidence and decreasing trends in mortality of NS were observed worldwide from 1990 to 2019. More robust epidemiological research and effective health strategies are urgently needed to reduce the disease burden of neonatal sepsis worldwide.

WHAT IS KNOWN

• Neonatal sepsis has significant impacts on neonatal health, but estimates on the global burden and trends of neonatal sepsis are scarce and existing findings vary considerably.

WHAT IS NEW

• Globally, there were 6.31 million incident cases of neonatal sepsis and 0.23 million deaths due to neonatal sepsis. • Increasing trends in incidence and decreasing trends in mortality of neonatal sepsis were observed worldwide from 1990 to 2019, with the highest absolute burden in sub-Saharan Africa and Asia.

Cardiorespiratory signature of neonatal sepsis: development and validation of prediction models in 3 NICUs

BACKGROUND

Heart rate characteristics aid early detection of late-onset sepsis (LOS), but respiratory data contain additional signatures of illness due to infection. Predictive models using cardiorespiratory data may improve early sepsis detection. We hypothesized that heart rate (HR) and oxygenation (SpO₂) data contain signatures that improve sepsis risk prediction over HR or demographics alone.

METHODS

We analyzed cardiorespiratory data from very low birth weight (VLBW, <1500 g) infants admitted to three NICUs. We developed and externally validated four machine learning models to predict LOS using features calculated every 10 m: mean, standard deviation, skewness, kurtosis of HR and SpO₂, and cross-correlation. We compared feature importance, discrimination, calibration, and dynamic prediction across models and cohorts. We built models of demographics and HR or SpO₂ features alone for comparison with HR-SpO₂ models.

RESULTS

Performance, feature importance, and calibration were similar among modeling methods. All models had favorable external validation performance. The HR-SpO₂ model performed better than models using either HR or SpO₂ alone. Demographics improved the discrimination of all physiologic data models but dampened dynamic performance.

CONCLUSIONS

Cardiorespiratory signatures detect LOS in VLBW infants at 3 NICUs. Demographics risk-stratify, but predictive modeling with both HR and SpO₂ features provides the best dynamic risk prediction.

IMPACT

Heart rate characteristics aid early detection of late-onset sepsis, but respiratory data contain signatures of illness due to infection. Predictive models using both heart rate and respiratory data may improve early sepsis detection. A cardiorespiratory early warning score, analyzing heart rate from electrocardiogram or pulse oximetry with SpO₂, predicts late-onset sepsis within 24 h across multiple NICUs and detects sepsis better than heart rate characteristics or demographics alone. Demographics risk-stratify, but predictive modeling with both HR and SpO₂ features provides the best dynamic risk prediction. The results increase understanding of physiologic signatures of neonatal sepsis.

Artificial and human intelligence for early identification of neonatal sepsis

Artificial intelligence may have a role in the early detection of sepsis in neonates. Machine learning can identify patterns that predict high or increasing risk for clinical deterioration from a sepsis-like illness. In developing this potential addition to NICU care, careful consideration should be given to the data and methods used to develop, validate, and evaluate prediction models. When an AI system alerts clinicians to a change in a patient's condition that warrants a bedside evaluation, human intelligence and experience come into play to determine an appropriate course of action: evaluate and treat or wait and watch closely. With intelligently developed, validated, and implemented AI sepsis systems, both clinicians and patients stand to benefit. IMPACT: This narrative review highlights the application of AI in neonatal sepsis prediction. It describes issues in clinical prediction model development specific to this population. This article reviews the methods, considerations, and literature on neonatal sepsis model development and validation. Challenges of AI technology and potential barriers to using sepsis AI systems in the NICU are discussed.

Neuromonitoring in neonatal critical care part II: extremely premature infants and critically ill neonates

Neonatal intensive care has expanded from cardiorespiratory care to a holistic approach emphasizing brain health. To best understand and monitor brain function and physiology in the neonatal intensive care unit (NICU), the most commonly used tools are amplitude-integrated EEG, full multichannel continuous EEG, and near-infrared spectroscopy. Each of these modalities has unique characteristics and functions. While some of these tools have been the subject of expert consensus statements or guidelines, there is no overarching agreement on the optimal approach to neuromonitoring in the NICU. This work reviews current evidence to assist decision making for the best utilization of these neuromonitoring tools to promote neuroprotective care in extremely premature infants and in critically ill neonates. Neuromonitoring approaches in neonatal encephalopathy and neonates with possible seizures are discussed separately in the companion paper. IMPACT: For extremely premature infants, NIRS monitoring has a potential role in individualized brain-oriented care, and selective use of aEEG and cEEG can assist in seizure detection and prognostication. For critically ill neonates, NIRS can monitor cerebral perfusion, oxygen delivery, and extraction associated with disease processes as well as respiratory and hypodynamic management. Selective use of aEEG and cEEG is important in those with a high risk of seizures and brain injury. Continuous multimodal monitoring as well as monitoring of sleep, sleep-wake cycling, and autonomic nervous system have a promising role in neonatal neurocritical care.

Central apnea detection in premature infants using machine learning

BACKGROUND AND OBJECTIVE

Apnea of prematurity is one of the most common diagnosis in neonatal intensive care units. Apneas can be classified as central, obstructive or mixed. According to the current international standards, minimal fluctuations or absence of fluctuations in the chest impedance (CI) suggest a central apnea (CA). However, automatic detection of reduced CI fluctuations leads to a high number of central apnea-suspected events (CASEs), the majority being false alarms. We aim to improve automatic detection of CAs by using machine learning to optimize detection of CAs among CASEs.

METHODS

Using an optimized algorithm for automated detection, all CASEs were detected in a population of 10 premature infants developing late-onset sepsis and 10 age-matched control patients. CASEs were inspected by two clinical experts and annotated as CAs or rejections in two rounds of annotations. A total of 47 features were extracted from the ECG, CI and oxygen saturation signals considering four 30 s-long moving windows, from 30 s before to 15 s after the onset of each CASE, using a moving step size of 5 s. Consecutively, new CA detection models were developed based on logistic regression with elastic net penalty, random forest and support vector machines. Performance was evaluated using both leave-one-patient-out and 10-fold cross-validation considering the mean area under the receiver-operating-characteristic curve (AUROC).

RESULTS

The CA detection model based on logistic regression with elastic net penalty returned the highest mean AUROC when features extracted from all four time windows were included, both using leave-one-patient-out and 10-fold cross-validation (mean AUROC of 0.88 and 0.90, respectively). Feature relevance was found to be the highest for features derived from the CI. A threshold for the false positive rate in the mean receiver-operating-characteristic curve equal to 0.3 led to a high percentage of correct detections for all CAs (78.2%) and even higher for CAs followed by a bradycardia (93.4%) and CAs followed by both a bradycardia and a desaturation (95.2%), which are more critical for the well-being of premature infants.

CONCLUSIONS

Models based on machine learning can lead to improved CA detection with fewer false alarms.

Updates in Late-Onset Sepsis: Risk Assessment, Therapy, and Outcomes

Neonatal late-onset sepsis (LOS) continues to threaten morbidity and mortality in the NICU and poses ongoing diagnostic and therapeutic challenges. Early recognition of clinical signs, rapid evaluation, and prompt initiation of treatment are critical to prevent life-threatening deterioration. Preterm infants-born at ever-decreasing gestational ages-are at particularly high risk for life-long morbidities and death. This changing NICU population necessitates continual reassessments of diagnostic and preventive measures and evidence-based treatment for LOS. The clinical presentation of LOS is varied and nonspecific. Despite ongoing research, reliable, specific laboratory biomarkers facilitating early diagnosis are lacking. These limitations drive an ongoing practice of liberal initiation of empiric antibiotics among infants with suspected LOS. Subsequent promotion of multidrug-resistant microorganisms threatens the future of antimicrobial therapy and puts preterm and chronically ill infants at even higher risk of nosocomial infection. Efforts to identify adjunctive therapies counteracting sepsis-driven hyperinflammation and sepsis-related functional immunosuppression are ongoing. However, most approaches have either failed to improve LOS prognosis or are not yet ready for clinical application. This article provides an overview of the epidemiology, risk factors, diagnostic tools, and treatment options of LOS in the context of increasing numbers of extremely preterm infants. It addresses the question of whether LOS could be identified earlier and more precisely to allow for earlier and more targeted therapy and discusses rational approaches to antibiotic therapy to avoid overuse. Finally, this review elucidates the necessity of long-term follow-up of infants with a history of LOS.

Paediatric and neonatal sepsis and inflammation

Sepsis has a huge impact on global mortality and has been declared as a priority by the World Health organisation the WHO.¹ Children have a high incidence of sepsis especially in the neonatal with an estimated 3 million babies affected worldwide and mortality ranges from 11 to 19%.² In addition, long-term neurodevelopmental outcomes are affected but this is largely unquantified. However, challenges remain in the early recognition, diagnosis and standardised management of sepsis. This series on Sepsis and inflammation in children reviews the conundrums of diagnostic criteria, biomarkers, management and future strategies to improve outcomes.