NeoSSNet: Real-Time Neonatal Chest Sound Separation Using Deep Learning.

Goal: Auscultation for neonates is a simple and non-invasive method of diagnosing cardiovascular and respiratory disease. However, obtaining high-quality chest sounds containing only heart or lung sounds is non-trivial. Hence, this study introduces a new deep-learning model named NeoSSNet and evaluates its performance in neonatal chest sound separation with previous methods. Methods: We propose a masked-based architecture similar to Conv-TasNet. The encoder and decoder consist of 1D convolution and 1D transposed convolution, while the mask generator consists of a convolution and transformer architecture. The input chest sounds were first encoded as a sequence of tokens using 1D convolution. The tokens were then passed to the mask generator to generate two masks, one for heart sounds and one for lung sounds. Each mask is then applied to the input token sequence. Lastly, the tokens are converted back to waveforms using 1D transposed convolution. Results: Our proposed model showed superior results compared to the previous methods based on objective distortion measures, ranging from a 2.01 dB improvement to a 5.06 dB improvement. The proposed model is also significantly faster than the previous methods, with at least a 17-time improvement. Conclusions: The proposed model could be a suitable preprocessing step for any health monitoring system where only the heart sound or lung sound is desired.

Umbilical cord blood-derived therapy for preterm lung injury: a systematic review and meta-analysis.

INTRODUCTION: Lung injuries, such as bronchopulmonary dysplasia (BPD), remain a major complication of preterm birth, with limited therapeutic options. One potential emerging therapy is umbilical cord blood (UCB)-derived therapy. OBJECTIVES: To systematically assess the safety and efficacy of UCB-derived therapy for preterm lung injury in preclinical and clinical studies. METHODS: A systematic search of MEDLINE, Embase, CENTRAL, ClinicalTrials.gov, and WHO International Trials Registry Platform was performed. A meta-analysis was conducted with Review Manager (5.4.1) using a random effects model. Data was expressed as standardized mean difference (SMD) for preclinical data and pooled relative risk (RR) for clinical data, with 95% confidence intervals (CI). Potential effect modifiers were investigated via subgroup analysis. Certainty of evidence was assessed using the GRADE system. RESULTS: Twenty-three preclinical studies and six clinical studies met eligibility criteria. Statistically significant improvements were seen across several preclinical outcomes, including alveolarization (SMD, 1.32, 95%CI [0.99, 1.65]), angiogenesis (SMD, 1.53, 95%CI [0.87, 2.18]), and anti-inflammatory cytokines (SMD, 1.68, 95%CI [1.03, 2.34]). In clinical studies, 103 preterm infants have received UCB-derived therapy for preterm lung injury and no significant difference was observed in the development of BPD (RR, 0.93, 95%CI [0.73, 1.18]). Across both preclinical and clinical studies, administration of UCB-derived therapy appeared safe. Certainty of evidence was assessed as "low." CONCLUSIONS: Administration of UCB-derived therapy was associated with statistically significant improvements across several lung injury markers in preclinical studies. Early clinical studies demonstrated the administration of UCB-derived therapy as safe and feasible but lacked data regarding efficacy.

Early Neurodevelopmental Assessments for Predicting Long-Term Outcomes in Infants at High Risk of Cerebral Palsy.

Importance: Studies suggest that early neurodevelopmental assessments are beneficial for identifying cerebral palsy, yet their effectiveness in practical scenarios and their ability to detect cognitive impairment are limited. Objective: To assess the effectiveness of early neurodevelopmental assessments in identifying cerebral palsy and cognitive and other neurodevelopmental impairments, including their severity, within a multidisciplinary clinic. Design, Setting, and Participants: This diagnostic study was conducted at Monash Children's Hospital, Melbourne, Australia. Participants were extremely preterm infants born at less than 28 weeks' gestation or extremely low birth weight infants less than 1000 g and term encephalopathic infants who received therapeutic hypothermia, attending the early neurodevelopmental clinic between January 2019 and July 2021. Data were analyzed from December 2023 to January 2024. Exposures: Early cerebral palsy or high risk of cerebral palsy, the absence of fidgety movements, and Hammersmith Infant Neurological Examination (HINE) scores at corrected age (CA) 3 to 4 months. Early cerebral palsy or high risk of cerebral palsy diagnosis was based on absent fidgety movements, a low HINE score (<57), and medical neurological examination. Main Outcome and Measures: The outcomes of interest were cerebral palsy, cognitive and neurodevelopmental impairments and their severity, diagnosed at 24 to 36 months' CA. Results: A total of 116 infants (median [IQR] gestational age, 27 [25-29] weeks; 65 [56%] male) were included. Diagnosis of early cerebral palsy or high risk of cerebral palsy demonstrated a sensitivity of 92% (95% CI, 63%-99%) and specificity of 84% (95% CI, 76%-90%) for predicting cerebral palsy and 100% (95% CI, 59%-100%) sensitivity and 80% (95% CI, 72%-87%) specificity for predicting moderate to severe cerebral palsy. Additionally, the accuracy of diagnosis of early cerebral palsy or high risk of cerebral palsy was 85% (95% CI, 77%-91%) for predicting cerebral palsy and 81% (95% CI, 73%-88%) for predicting moderate to severe cerebral palsy. Similarly, the absence of fidgety movements had an 81% (95% CI, 73%-88%) accuracy in predicting cerebral palsy, and HINE scores exhibited good discriminatory power with an area under the curve of 0.88 (95% CI, 0.79-0.97) for cerebral palsy prediction. However, for cognitive impairment, the predictive accuracy was 44% (95% CI, 35%-54%) for an early cerebral palsy or high risk of cerebral palsy diagnosis and 45% (95% CI, 36%-55%) for the absence of fidgety movements. Similarly, HINE scores showed poor discriminatory power for predicting cognitive impairment, with an area under the curve of 0.62 (95% CI, 0.51-0.73). Conclusions and Relevance: In this diagnostic study of infants at high risk for cerebral palsy or other cognitive or neurodevelopmental impairment, early neurodevelopmental assessments at 3 to 4 months' CA reliably predicted cerebral palsy and its severity at 24 to 36 months' CA, signifying its crucial role in facilitating early intervention. However, for cognitive impairment, longer-term assessments are necessary for accurate identification.

Combining activity and grimace scores reflects perinatal stability in infants <32 weeks gestational age.

BACKGROUND: Over 95% of infants less than 32 weeks gestational age-very preterm infants (VPTI)-require cardiorespiratory support at birth. Clinical condition at birth is assessed by the Apgar score, but the precision and accuracy of activity and grimace has not been evaluated. We hypothesised activity and grimace could predict the level of cardiorespiratory support required for stabilisation. METHODS: Two hundred twenty-nine videos of VPTI resuscitations at Monash Children's Hospital and The Royal Women's Hospital, Melbourne were evaluated, with 78 videos eligible for assessment. Activity and grimace were scored (0, 1, or 2) by seven consultant neonatologists, with inter-rater reliability assessed. Activity and grimace were correlated with the maximum level of cardiorespiratory support required for stabilisation. RESULTS: Kendall's Coefficient of Concordance (W) showed strong interobserver agreement for activity (W = 0.644, p < 0.001) and grimace (W = 0.722, p < 0.001). Neither activity nor grimace independently predicted the level of cardiorespiratory support required. Combining activity and grimace showed non-vigorous infants (combined score <2) received more cardiorespiratory support than vigorous (combined score ≥ 2). CONCLUSION: Scoring of activity and grimace was consistent between clinicians. Independently, activity and grimace did not correlate with perinatal stabilisation. Combined scoring showed non-vigorous infants had greater resuscitation requirements. IMPACT: Our study evaluates the precision and accuracy of activity and grimace to predict perinatal stability, which has not been validated in infants <32 weeks gestational age. We found strong score agreement between assessors, indicating video review is a practical and precise method for grading of activity and grimace. Combined scoring to allow a dichotomous evaluation of infants as non-vigorous or vigorous showed the former group required greater cardiorespiratory support at birth.

Advances in neonatal cell therapies: Proceedings of the First Neonatal Cell Therapies Symposium (2022).

Despite considerable advances, there is a need to improve the outcomes of newborn infants, especially related to prematurity, encephalopathy and other conditions. In principle, cell therapies have the potential to protect, repair, or sometimes regenerate vital tissues; and improve or sustain organ function. In this review, we present highlights from the First Neonatal Cell Therapies Symposium (2022). Cells tested in preclinical and clinical studies include mesenchymal stromal cells from various sources, umbilical cord blood and cord tissue derived cells, and placental tissue and membrane derived cells. Overall, most preclinical studies suggest potential for benefit, but many of the cells tested were not adequately defined, and the optimal cell type, timing, frequency, cell dose or the most effective protocols for the targeted conditions is not known. There is as yet no clinical evidence for benefit, but several early phase clinical trials are now assessing safety in newborn babies. We discuss parental perspectives on their involvement in these trials, and lessons learnt from previous translational work of promising neonatal therapies. Finally, we make a call to the many research groups around the world working in this exciting yet complex field, to work together to make substantial and timely progress to address the knowledge gaps and move the field forward. IMPACT: Survival of preterm and sick newborn infants is improving, but they continue to be at high risk of many systemic and organ-specific complications. Cell therapies show promising results in preclinical models of various neonatal conditions and early phase clinical trials have been completed or underway. Progress on the potential utility of cell therapies for neonatal conditions, parental perspectives and translational aspects are discussed in this paper.

Early neurodevelopmental outcomes of extreme preterm infants exposed to paracetamol: a retrospective cohort study.

BACKGROUND: Paracetamol is commonly used for analgesia and patent ductus arteriosus (PDA) treatment in preterm infants. We aimed to evaluate early neurodevelopmental outcomes of extreme preterm infants exposed to paracetamol during their neonatal admission. METHODS: This retrospective cohort study included surviving infants born at <29 weeks gestation, or with a birth weight of <1000 grams. Neurodevelopmental outcomes studied were early cerebral palsy (CP) or high risk of CP diagnosis, Hammersmith Infant Neurological Examination (HINE) score and Prechtl General Movement Assessment (GMA) at 3-4 months corrected age. RESULTS: Two hundred and forty-two infants were included, of which 123 were exposed to paracetamol. After adjusting for birth weight, sex and chronic lung disease, there were no significant associations between paracetamol exposure and early CP or high risk of CP diagnosis (aOR 1.46, 95% CI 0.61, 3.5), abnormal or absent GMA (aOR 0.82, 95% CI 0.37, 1.79) or HINE score (adjusted ß -0.19, 95% CI -2.39, 2.01). Subgroup analysis stratifying paracetamol exposure into <180 mg/kg or ≥180 mg/kg cumulative dose found that neither had significant effects on outcomes. CONCLUSIONS: In this cohort of extreme preterm infants, no significant association was found between exposure to paracetamol during the neonatal admission and adverse early neurodevelopment. IMPACT: Paracetamol is commonly used in the neonatal period for analgesia and patent ductus arteriosus treatment in preterm infants, although prenatal paracetamol use has been associated with adverse neurodevelopmental outcomes. Exposure to paracetamol during the neonatal admission was not associated with adverse early neurodevelopment at 3-4 months corrected age in this cohort of extreme preterm infants. The findings from this observational study is consistent with the small body of literature supporting the lack of association between neonatal paracetamol exposure and adverse neurodevelopmental outcomes in preterm infants.

Umbilical Cord Blood-Derived Cell Therapy for Perinatal Brain Injury: A Systematic Review & Meta-Analysis of Preclinical Studies.

Perinatal brain injury is a major contributor to long-term adverse neurodevelopment. There is mounting preclinical evidence for use of umbilical cord blood (UCB)-derived cell therapy as potential treatment. To systematically review and analyse effects of UCB-derived cell therapy on brain outcomes in preclinical models of perinatal brain injury. MEDLINE and Embase databases were searched for relevant studies. Brain injury outcomes were extracted for meta-analysis to calculate standard mean difference (SMD) with 95% confidence interval (CI), using an inverse variance, random effects model. Outcomes were separated based on grey matter (GM) and white matter (WM) regions where applicable. Risk of bias was assessed using SYRCLE, and GRADE was used to summarise certainty of evidence. Fifty-five eligible studies were included (7 large, 48 small animal models). UCB-derived cell therapy significantly improved outcomes across multiple domains, including decreased infarct size (SMD 0.53; 95% CI (0.32, 0.74), p < 0.00001), apoptosis (WM, SMD 1.59; 95%CI (0.86, 2.32), p < 0.0001), astrogliosis (GM, SMD 0.56; 95% CI (0.12, 1.01), p = 0.01), microglial activation (WM, SMD 1.03; 95% CI (0.40, 1.66), p = 0.001), neuroinflammation (TNF-α, SMD 0.84; 95%CI (0.44, 1.25), p < 0.0001); as well as improved neuron number (SMD 0.86; 95% CI (0.39, 1.33), p = 0.0003), oligodendrocyte number (GM, SMD 3.35; 95 %CI (1.00, 5.69), p = 0.005) and motor function (cylinder test, SMD 0.49; 95 %CI (0.23, 0.76), p = 0.0003). Risk of bias was determined as serious, and overall certainty of evidence was low. UCB-derived cell therapy is an efficacious treatment in pre-clinical models of perinatal brain injury, however findings are limited by low certainty of evidence.

Feasibility of cord blood collection for autologous cell therapy applications in extremely preterm infants.

BACKGROUND AIMS: Umbilical cord blood (UCB)-derived cells show strong promise as a treatment for neonatal brain injury in pre-clinical models and early-phase clinical trials. Feasibility of UCB collection and autologous administration is reported for term infants, but data are limited for preterm infants. Here the authors assessed the feasibility of UCB-derived cell collection for autologous use in extremely preterm infants born at less than 28 weeks, a population with a high incidence of brain injury and subsequent neurodisability. METHODS: In a prospective study at a tertiary hospital in Melbourne, Australia, UCB was collected from infants born at less than 28 weeks and processed to obtain total nucleated cells (TNCs), CD34+ cells, mononuclear cells and cell viability via fluorescence-activated cell sorting prior to cryopreservation. Feasibility was pre-defined as volume adequate for cryopreservation (>9 mL UCB collected) and >25 × 106 TNCs/kg retrieved. RESULTS: Thirty-eight infants (21 male, 17 female) were included in the study. Twenty-four (63.1%) were delivered via cesarean section, 30 (78.9%) received delayed cord clamping before collection and 11 (28.9%) were a multiple birth. Median (interquartile range [IQR]) gestational age was 26.0 weeks (24.5-27.5) and mean (standard deviation) birth weight was 761.5 g (221.5). Median (IQR) UCB volume collected was 19.1 mL/kg (10.5-23.5), median (IQR) TNC count was 105.2 × 106/kg (57.4-174.4), median (IQR) CD34+ cell count was 1.5 × 106/kg (0.6-2.1) and median (IQR) cell viability pre-cryopreservation was 95% (92.1-96.0). Feasibility of collection volume and cell count suitable for cell cryopreservation was achieved in 27 (71%) and 28 (73.6%) infants, respectively. CONCLUSIONS: UCB-derived cell collection adequate for cryopreservation and subsequent autologous reinfusion was achieved in 70% of extremely preterm infants. Extremely preterm UCB demonstrated a higher CD34+:TNC ratio compared with published full-term values. Recruitment to demonstrate safety of UCB cell administration in extremely premature infants is ongoing in the CORD-SAFE study (trial registration no. ACTRN12619001637134).

Factors Influencing the Efficacy of Umbilical Cord Blood-Derived Cell Therapy for Perinatal Brain Injury.

INTRODUCTION: We have previously described preclinical literature which supports umbilical cord blood-derived cell (UCBC) therapy as an efficacious treatment for perinatal brain injury. However, efficacy of UCBCs may be influenced by different patient population and intervention characteristics. OBJECTIVES: To systematically review the effects of UCBCs on brain outcomes in animal models of perinatal brain injury across subgroups to better understand the contribution of model type (preterm versus term), brain injury type, UCB cell type, route of administration, timing of intervention, cell dosage, and number of doses. METHODS: A systematic search of MEDLINE and Embase databases was performed to identify studies using UCBC therapy in animal models of perinatal brain injury. Subgroup differences were measured by chi2 test where possible. RESULTS: Differential benefits of UCBCs were seen across a number of subgroup analyses including intraventricular hemorrhage (IVH) vs. hypoxia ischemia (HI) model (apoptosis white matter (WM): chi2 = 4.07; P = .04, neuroinflammation-TNF-α: chi2 = 5.99; P = .01), UCB-derived mesenchymal stromal cells (MSCs) vs. UCB-derived mononuclear cells (MNCs) (oligodendrocyte WM: chi2 = 5.01; P = .03, neuroinflammation-TNF-α: chi2 = 3.93; P = .05, apoptosis grey matter (GM), astrogliosis WM), and intraventricular/intrathecal vs. systemic routes of administration (microglial activation GM: chi2 = 7.51; P = .02, astrogliosis WM: chi2 = 12.44; P = .002). We identified a serious risk of bias and overall low certainty of evidence. CONCLUSIONS: Preclinical evidence suggests UCBCs to show greater efficacy in the injury model of IVH compared to HI, the use of UCB-MSCs compared to UCB-MNCs and the use of local administrative routes compared to systemic routes in animal models of perinatal brain injury. Further research is needed to improve certainty of evidence and address knowledge gaps.

Noisy Neonatal Chest Sound Separation for High-Quality Heart and Lung Sounds.

Stethoscope-recorded chest sounds provide the opportunity for remote cardio-respiratory health monitoring of neonates. However, reliable monitoring requires high-quality heart and lung sounds. This paper presents novel artificial intelligence-based Non-negative Matrix Factorisation (NMF) and Non-negative Matrix Co-Factorisation (NMCF) methods for neonatal chest sound separation. To assess these methods and compare them with existing single-channel separation methods, an artificial mixture dataset was generated comprising heart, lung, and noise sounds. Signal-to-noise ratios were then calculated for these artificial mixtures. These methods were also tested on real-world noisy neonatal chest sounds and assessed based on vital sign estimation error, and a signal quality score of 1-5, developed in our previous works. Overall, both the proposed NMF and NMCF methods outperform the next best existing method by 2.7 dB to 11.6 dB for the artificial dataset, and 0.40 to 1.12 signal quality improvement for the real-world dataset. The median processing time for the sound separation of a 10 s recording was found to be 28.3 s for NMCF and 342 ms for NMF. With the stable and robust performance of our proposed methods, we believe these methods are useful to denoise neonatal heart and lung sounds in the real-world environment.

Prediction of Neonatal Respiratory Distress in Term Babies at Birth from Digital Stethoscope Recorded Chest Sounds.

Neonatal respiratory distress is a common condition that if left untreated, can lead to short- and long-term complications. This paper investigates the usage of digital stethoscope recorded chest sounds taken within 1 min post-delivery, to enable early detection and prediction of neonatal respiratory distress. Fifty-one term newborns were included in this study, 9 of whom developed respiratory distress. For each newborn, 1 min anterior and posterior recordings were taken. These recordings were pre-processed to remove noisy segments and obtain high-quality heart and lung sounds. The random undersampling boosting (RUSBoost) classifier was then trained on a variety of features, such as power and vital sign features extracted from the heart and lung sounds. The RUSBoost algorithm produced specificity, sensitivity, and accuracy results of 85.0%, 66.7% and 81.8%, respectively. Clinical relevance--- This paper investigates the feasibility of digital stethoscope recorded chest sounds for early detection of respiratory distress in term newborn babies, to enable timely treatment and management.

Assessing the Utility of Neonatal Screening Assessments in Early Diagnosis of Cerebral Palsy in Preterm Infants.

Background: Early diagnosis of cerebral palsy (CP) in high-risk infants is possible at 3−4 months' corrected age (CA) using standardised assessments. Aim: To assess the utility of neonatal screening assessments­writhing general movements (GMs) and the Hammersmith Neonatal Neurological Examination (HNNE)­to predict CP/high-risk status at 3−4 months' CA in extremely preterm infants. Methods: Retrospective cohort study of high-risk preterm infants (born < 29 weeks' gestation and/or birth weight < 1000 g) attending an Early Neurodevelopment Clinic. Data from neonatal assessments were compared with CP/high-risk diagnosis at 3−4 months' CA, fidgety GMs, and Hammersmith Infant Neurological Examinations (HINE) using logistic regression, linear regression, and Spearman rank correlation. Results: Two hundred and two preterm infants (median gestation age at birth 27.3 (IQR 25.4−28.3) weeks, mean birth weight 870.3 (SD 248.4) grams) were included. A total of 26 (12.8%) infants received early CP/high-risk diagnoses at 3−4 months' CA. A lower gestational age (GA) (OR = 0.78; p = 0.029, 95% CI [0.26, 0.97]) and abnormal writhing GMs (OR 1.56; p = 0.019, 95% CI [1.07, 2.27]) were predictive of CP/high-risk diagnosis. Although after adjustment for sex, GA, birth weight, and growth restriction, GA (aOR = 0.67; p = 0.068, 95% CI [0.44, 1.03]) and writhing GMs (aOR = 1.44; p = 0.087, 95% CI [0.95, 2.20]) were not significant, a strong trend still persisted. The HNNE scores significantly correlated with both the HINE evaluation (rs = 0.43, p < 0.001, 95% CI [0.31, 0.56]) and fidgety GMs (rs = −0.10, p = 0.012, 95% CI [−0.32, −0.04]). Linear regression confirmed the HNNE was highly predictive of the HINE (correlation coefficient 0.82; p < 0.001, 95% CI [0.48, 1.15]). Writhing GMs did not significantly correlate with either fidgety GMs (p = 0.723, 95% CI [−0.12, 0.17]) or the HINE (p = 0.173, 95% CI [−0.24, 0.04]). Conclusions: Abnormal writhing GMs in the neonatal period were non-significantly associated with early CP/high-risk diagnoses in extremely preterm infants in a multivariate analysis. Additionally, the HNNE significantly correlated with both fidgety GMs and the HINE.

Umbilical Cord Blood and Cord Tissue-Derived Cell Therapies for Neonatal Morbidities: Current Status and Future Challenges.

Cell therapies are an emerging focus for neonatal research, with benefits documented for neonatal respiratory, neurological, and cardiac conditions in pre-clinical studies. Umbilical cord blood (UCB) and umbilical cord (UC) tissue-derived cell therapy is particularly appealing for preventative or regenerative treatment of neonatal morbidities; they are a resource that can be collected at birth and used as an autologous or allogeneic therapy. Moreover, UCB contains a diverse mix of stem and progenitor cells that demonstrate paracrine actions to mitigate damaging inflammatory, immune, oxidative stress, and cell death pathways in several organ systems. In the past decade, published results from early-phase clinical studies have explored the use of these cells as a therapeutic intervention in neonates. We present a systematic review of published and registered clinical trials of UCB and cord tissue-derived cell therapies for neonatal morbidities. This search yielded 12 completed clinical studies: 7 were open-label phase I and II safety and feasibility trials, 3 were open-label dose-escalation trials, 1 was a open-label placebo-controlled trial, and 1 was a phase II randomized controlled trial. Participants totaled 206 infants worldwide; 123 (60%) were full-term infants and 83 (40%) were preterm. A majority (64.5%) received cells via an intravenous route; however, 54 (26.2%) received cells via intratracheal administration, 10 (4.8%) intraoperative cardiac injection, and 9 (4.3%) by direct intraventricular (brain) injection. Assessment of efficacy to date is limited given completed studies have principally been phase I and II safety studies. A further 24 trials investigating UCB and UC-derived cell therapies in neonates are currently registered.

A New Non-Negative Matrix Co-Factorisation Approach for Noisy Neonatal Chest Sound Separation.

Obtaining high quality heart and lung sounds enables clinicians to accurately assess a newborns cardio-respiratory health and provide timely care. However, noisy chest sound recordings are common, hindering timely and accurate assessment. A new Non-negative Matrix Co-Factorisation based approach is proposed to separate noisy chest sound recordings into heart, lung and noise components to address this problem. This method is achieved through training with 20 high quality heart and lung sounds, in parallel with separating the sounds of the noisy recording. The method was tested on 68 10-second noisy recordings containing both heart and lung sounds and compared to the current state of the art Non-negative Matrix Factorisation methods. Results show significant improvements in heart and lung sound quality scores respectively, and improved accuracy of 3.6bpm and 1.2bpm in heart and breathing rate estimation respectively, when compared to existing methods.

Staff awareness and bundling reduce skin breaks and blood tests in neonatal intensive care.

AIM: Skin breaks (SBs) for procedures and blood sampling are common in neonatal intensive care units (NICU), contributing to pain, infection risk and anaemia. We aimed to document their prevalence, identify areas for improvement and, through staff awareness, reduce their frequency. METHODS: Quality improvement project via prospective audit at a tertiary-level NICU in Australia was conducted. All infants admitted to the NICU for >24 h during two audit periods were included in the study. A specifically designed bedside audit tool was used to prospectively document all SB and blood tests performed on infants during a 4-week audit period (audit 1). Results were reviewed to identify areas for improvement, and disseminated to staff at unit meetings, shift handover and email. Following education and awareness, the audit was repeated (audit 2), and data were compared. Frequency of SB and blood tests performed was measured. Data were tested for normality and analysed using parametric or non-parametric tests where appropriate. RESULTS: There were 52 NICU admissions during each audit period (104 total), with 34 (65%) and 31 (60%) having audit sheets completed, respectively. Median (interquartile range) gestational age and mean (standard deviation) birthweight were 29 (26.3-35) weeks and 1836 (1185) g for audit 1, 30 (28.5-31.5) weeks and 1523 (913) g for audit 2. The reduction in total blood tests (mean) was 36.3%, skin breaks per admitted baby day reduced by 60% and total blood volume sampled (mean) by 37.7%. CONCLUSIONS: A quality improvement project by prospective audit and staff education was associated with reductions in frequency of skin breaks and blood tests in the NICU.

Elective replacement of peripheral intravenous cannulas in neonates.

BACKGROUND: Newborns admitted to neonatal units often require vascular access. Peripheral intravenous cannulas allow essential medication, fluids, and/or parenteral nutrition to be delivered. Peripheral intravenous cannulas are often associated with complications, such as extravasation, infiltration, phlebitis, leakage, spontaneous dislodgement, and catheter-associated blood stream infection. METHODS: A secondary analysis of a randomized controlled trial evaluating standard replacement versus elective replacement (72-96 h) of peripheral intravenous cannula was conducted in a tertiary-level neonatal unit in Melbourne, Australia. The main outcome of this analysis was to assess the risk of combined adverse events associated with elective replacement of peripheral intravenous cannula. A cost analysis of the intervention was also conducted. RESULTS: Combined adverse outcomes noted per infant were 48 (87.27%) in the standard replacement group versus 44 (75.86%) in the elective replacement group (RR 0.87; 95% CI 0.71-1.04, p = 0.15). In terms of combined adverse outcome per 1000 intravenous hours, there was a significant risk ratio of 0.81 in the elective group compared with the standard group (95% CI 0.65-0.98, p = 0.04). Gestation (adjusted odds ratio (AOR) 0.58; 95% CI 0.35-0.96, p = 0.03), male gender (AOR 4.65; 95% CI 1.07-20.28, p = 0.04), elective replacement (AOR 0.12; 95% CI 0.03-0.68, p = 0.01), and the total number of re-sites (AOR 27.84; 95% CI 4.61-168.18, p < 0.001) were significant risk factors associated with adverse events. There were also significantly higher costs involved with elective replacement. CONCLUSION: Elective replacement of peripheral intravenous cannulas was not shown to reduce the risk of combined adverse events. Elective peripheral intravenous cannula replacement also incurred a higher cost.

Neonatal Heart and Lung Sound Quality Assessment for Robust Heart and Breathing Rate Estimation for Telehealth Applications.

With advances in digital stethoscopes, internet of things, signal processing and machine learning, chest sounds can be easily collected and transmitted to the cloud for remote monitoring and diagnosis. However, low quality of recordings complicates remote monitoring and diagnosis, particularly for neonatal care. This paper proposes a new method to objectively and automatically assess the signal quality to improve the accuracy and reliability of heart rate (HR) and breathing rate (BR) estimation from noisy neonatal chest sounds. A total of 88 10-second long chest sounds were taken from 76 preterm and full-term babies. Six annotators independently assessed the signal quality, number of detectable beats, and breathing periods from these recordings. For quality classification, 187 and 182 features were extracted from heart and lung sounds, respectively. After feature selection, class balancing, and hyperparameter optimization, a dynamic binary classification model was trained. Then HR and BR were automatically estimated from the chest sound and several approaches were compared.The results of subject-wise leave-one-out cross-validation, showed that the model distinguished high and low quality recordings in the test set with 96% specificity, 81% sensitivity and 93% accuracy for heart sounds, and 86% specificity, 69% sensitivity and 82% accuracy for lung sounds. The HR and BR estimated from high quality sounds resulted in significantly less median absolute error (4 bpm and 12 bpm difference, respectively) compared to those from low quality sounds. The methods presented in this work, facilitates automated neonatal chest sound auscultation for future telehealth applications.

Acoustic analysis of neonatal breath sounds using digital stethoscope technology.

BACKGROUND: There is no published literature regarding the use of the digital stethoscope (DS) and computerized breath sound analysis in neonates, despite neonates experiencing a high burden of respiratory disease. We aimed to determine if the DS could be used to study breath sounds of term and preterm neonates without respiratory disease, and detect a difference in acoustic characteristics between them. METHODS: A commercially available DS was used to record breath sounds of term and preterm neonates not receiving respiratory support between 24 and 48 hours after birth. Recordings were extracted, filtered, and computer analysis performed to obtain power spectra and mel frequency cepstral coefficient (MFCC) profiles. RESULTS: Recordings from 26 term and 26 preterm infants were obtained. The preterm cohort had an average gestational age (median and interquartile range) of 32 (31-33) weeks and term 39 (38-39) weeks. Birth weight (mean and SD) was 1767 (411) g for the preterm and 3456 (442) g for the term cohort. Power spectra demonstrated the greatest power in the low-frequency range of 100 to 250 Hz for both groups. There were significant differences (P < .05) in the average power at low (100-250 Hz), medium (250-500 Hz), high (500-1000 Hz), and very high (1000-2000 Hz) frequency bands. MFCC profiles also demonstrated significant differences between groups (P < .05). CONCLUSION: It is feasible to use DS technology to analyze breath sounds in neonates. DS was able to determine significant differences between the acoustic characteristics of term and preterm infants breathing in room air. Further investigation of DS technology for neonatal breath sounds is warranted.

Digital stethoscopes in paediatric medicine.

AIM: To explore, synthesise and discuss currently available digital stethoscopes (DS) and the evidence for their use in paediatric medicine. METHODS: Systematic review and narrative synthesis of digital stethoscope use in paediatrics following searches of OVID Medline, Embase, Scopus, PubMed and Google Scholar databases. RESULTS: Six digital stethoscope makes were identified to have been used in paediatric focused studies so far. A total of 25 studies of DS use in paediatrics were included. We discuss the use of digital stethoscope technology in current paediatric medicine, comment on the technical properties of the available devices, the effectiveness and limitations of this technology, and potential uses in the fields of paediatrics and neonatology, from telemedicine to computer-aided diagnostics. CONCLUSION: Further validation and testing of available DS devices is required. Comparison studies between different types of DS would be useful in identifying strengths and flaws of each DS as well as identifying clinical situations for which each may be most appropriately suited.