Laerdal (Norway)

ABSTRACT Background Most births worldwide (>80%) occur in health care facilities, yet 2.3 million newborns die annually. If the know – do gap between evidence and implementation was closed, an estimated 752,000 newborn deaths could be prevented per year. To bridge this gap, we describe the co-design of the Implementation Toolkit for Small and Sick Newborn Care (Newborn Toolkit), a web platform and linked community of global implementers, facilitated by NEST360 and UNICEF. The Newborn Toolkit enables access to practical, curated resources, including tools for peer learning and adaptation to country contexts. Methods A systematic three step process was followed. Step 1) Structure: We used an organising framework of WHO and UNICEF ten core components for health systems strengthening. We then reviewed relevant knowledge management platforms to identify elements facilitating user engagement. Step 2) Content: >300 implementers collated publications and tools for ten core components. Step 3) Refining and building community: User data analytics and surveys plus direct feedback from the global communities of practice provided data to improve website and webinar content. Results Step 1) Structure: In 2020, the Newborn Toolkit website structure was co-designed based on the ten core components. Step 2) Content: Working groups, organised by core components, collated over 1,100 resources in 15 languages. Step 3) Refining and building community: Cross-country learning was facilitated through 45 webinars with multi-disciplinary speakers from all continents including caregivers, clinicians, non-governmental organisation representatives, engineers, and data scientists. French language translation and engagement was added between 2023-2025. Unique user counts increased with 28,146 in 2023 to 62,561 in 2025 from 198 countries and territories. The most viewed content includes WHO guidelines, neonatal floor plans, the ABC device costing tool, and data tools. Conclusions Given the urgency for accelerated progress for newborn survival by 2030, rapid implementation of proven solutions is needed. It is crucial that implementers can access evidence and tools to adapt for their specific context, rather than “reinventing the wheel”. Systems change is complex, requiring novel approaches to make it doable, such as standard, simplified action pathways available on the Newborn Toolkit. Gaps to address include evidence availability in multiple languages. KEY FINDINGS WHAT WAS KNOWN? 2.3 million neonatal deaths are estimated annually and 65 countries are at-risk of missing Sustainable Development Goal 3.2 of reducing the number of neonatal deaths to less than 12 per 1,000 live births by 2030 There exists a know–do gap in global newborn health referring to the inability to translate evidence, what is known to work, into practice to improve health outcomes for WHO-UNICEF level-2 Small and Sick Newborn Care Frameworks based on country experiences have been created to guide health systems strengthening such as the WHO/UNICEF core components; however, operationalisation is needed Evidence, guidelines, and resources for Small and Sick Newborn Care were available; however, there existed a gap in knowledge management platforms dedicated to enabling evidence-based implementation of health systems strengthening interventions in low-resource settings WHAT WAS DONE THAT IS NEW? We co-designed a knowledge management platform for resources including tools, readings, and case studies to bridge the know–do gap for Small and Sick Newborn Care in low-resource settings Content and resources on the site were organised according to the ten WHO/UNICEF core components for health systems strengthening plus infection prevention and control This platform was operationalised and scaled by linking to, and engaging with, a global community of practice We applied a continuous learning and feedback integration approach to develop and refine content, enable accessibility including by language, and tailor engagement initiatives to implementer needs informed by website user and webinar data analytics WHAT WAS FOUND? The platform hosts over 1,100 tools and readings with resources available in 15 languages Between 2021–2025, this platform had 157,452 unique users, from 198 countries and territories 45 webinars were hosted between 2022–2025 showcasing implementation case studies and facilitating cross-country learning Knowledge management and targeted engagement can enable uptake of information by organising content in practical, digestible, and feasible formats WHAT NEXT? The know–do gap in Small and Sick Newborn Care needs to be closed. Providing up-to-date, relevant evidence that adapts to emerging knowledge and local learning, alongside leadership and financial inputs, could facilitate quality care delivery through data-driven decision making Bridging language barriers, through content translation, is a priority and crucial to enable wider access to up-to-date evidence

Basic resuscitation practices, particularly bag-mask ventilation, reduce newborn deaths from respiratory depression. There is strong scientific premise for improving bag-mask ventilation with feedback strategies, but there are significant barriers to bedside feedback in low-resource settings. To address these barriers, we developed LIVEBORN, a mobile health application to support feedback for newborn resuscitations. LIVEBORN uses data on provider actions and the newborn's condition entered in real-time by an observer to provide real-time guidance during resuscitation and support debriefing after resuscitation. In a pilot study, we designed and then evaluated strategies to incorporate LIVEBORN Feedback into clinical practice at two health facilities in the Democratic Republic of the Congo, with one facility allocated to real-time guidance and one to debriefing. Providers at each facility used a participatory research methodology called Trials of Improved Practices to design and refine their strategy prior to pilot testing. The primary outcome of the pilot study was the feasibility of observing resuscitation care with LIVEBORN, defined as the percentage of births observed using LIVEBORN with a threshold of at least 50% of births observed to achieve feasibility. We also evaluated usability with the System Usability Scale and explored midwives' perceptions of LIVEBORN Feedback in focus group discussions. During the pilot test, we found both strategies to be feasible with 74% of births observed with LIVEBORN at the real-time guidance facility and 67% at the debriefing facility. The strategy was also sufficiently usable with a System Usability Scale median score of 68 (Q1 65, Q3 78). Midwives perceived LIVEBORN Feedback to be helpful and believed it could save lives, but sometimes disagreed with LIVEBORN Feedback's guidance to ventilate. In conclusion, we identified context-specific, feasible strategies for incorporating LIVEBORN Feedback into clinical care. We are now evaluating the effectiveness of LIVEBORN Feedback in a randomized control trial.

Detta kapitel ger en omfattande översikt av de viktigaste datadrivna metoderna för kvalitetsbedömning av givardata som kan vara ett stöd för drift och processoptimering. Begreppet datadrivna metoder används här som ett samlingsnamn för de beräkningsmetoder och algoritmer (maskininlärning, mekanistiska modeller etc.) som på olika sätt kan användas för att tolka data. Kapitlet introducerar begreppet redundanta mätningar som ligger till grund för själva kvalitetsbedömningen i de flesta metoderna. Kapitlet går också igenom det typiska dataflödet som består av en inledande analys, förbehandling av data och metodspecifika beräkningssteg. Vart och ett av dessa tre delsteg beskrivs i tre separata avsnitt. Utöver detta så ges även riktlinjer för att välja den lämpligaste metoden och de viktigaste prestandamåtten som används för att utvärdera dem samt en förklaring av hur man samlar in metadata utifrån datadrivna valideringsmetoder.

IntroductionRoad traffic injuries (RTIs) are the leading cause of mortality among children and adolescents. This study aimed to compare clinical characteristics and identify factors associated with severe RTIs based on types of road users among children and adolescents with RTIs.MethodsA retrospective multicentre observational study was conducted using the Emergency Department-based Injury In-depth Surveillance registry in South Korea. A total of 78 021 participants younger than 19 years who presented with RTIs to the participating emergency departments from 2011 to 2021 were classified into four groups: passengers, pedestrians, motorcyclists and bicyclists. Demographic and injury-related factors were analysed using a multivariate logistic regression model to determine associations with severe RTIs, as indicated by the Excess Mortality Ratio-based Injury Severity Score of ≥16. The prevalence of traumatic brain injury (TBI), hospitalisations, intensive care unit (ICU) admissions and severe RTIs among road users was compared.ResultsHead injuries were most prevalent in passengers (55.3%), motorcyclists (46.7%) and bicyclists (50.1%). Motorcyclists exhibited the highest proportion of TBI (8.3%), total admissions (28.8%), ICU admissions (8.2%), severe RTIs (41.0%) and mortality (2.0%). Safety devices significantly reduced severe RTIs in passengers and motorcyclists (adjusted OR (95% CI) 0.77 (0.70 to 0.85) and 0.69 (0.62 to 0.76), respectively.ConclusionThe distinct clinical characteristics and factors associated with severe RTIs among different road user types in children and adolescents highlight the need for targeted interventions. Tailoring strategies to the specific requirements of each group is essential for effectively mitigating the occurrence of severe RTIs in this vulnerable demographic.

Deprivation of oxygen in an infant during and after birth leads to birth asphyxia, which is considered one of the leading causes of death in the neonatal period. Adequate resuscitation activities are performed immediately after birth to save the majority of newborns. The primary resuscitation activities include ventilation, stimulation, drying, suction, and chest compression. While resuscitation guidelines exist, little research has been conducted on measured resuscitation episodes. Objective data collected for measuring and registration of the executed resuscitation activities can be used to generate temporal timelines. This paper is primarily aimed to introduce methods for analyzing newborn resuscitation activity timelines, through visualization, aggregation, redundancy and dimensionality reduction. We are using two datasets: 1) from Stavanger University Hospital with 108 resuscitation episodes, and 2) from Haydom Lutheran Hospital with 76 episodes. The resuscitation activity timelines were manually annotated, but in future work we will use the proposed method on automatically generated timelines from video and sensor data. We propose an encoding generator with unique codes for combination of activities. A visualization of aggregated episodes is proposed using sparse nearest neighbor graph, shown to be useful to compare datasets and give insights. Finally, we propose a method consisting of an autoencoder trained for reducing redundancy in encoded resuscitation timeline descriptions, followed by a neighborhood component analysis for dimensionality reduction. Visualization of the resulting features shows very good class separability and potential for clustering the resuscitation files according to the outcome of the newborns as dead, admitted to NICU or normal. This shows great potential for extracting important resuscitation patterns when tested on larger datasets.

Newborn mortality is a global challenge with around 2.4 million neonatal deaths in 2019. One third of these occur within the first-and-only day of life with labour complications and birth asphyxia being the primary causes. Existing guidelines for newborn resuscitation are based on limited scientific evidence, and evidens based research is sought for. To increase our knowledge on resuscitation of newborns, it is crucial to first quantify what is currently being done in terms of therapeutic activities, such as ventilation and stimulation, and how they affect resuscitation outcomes. In the current study, the therapeutic activities during newborn resuscitation are quantified by estimating a timeline describing the start and stop of activities. The proposed approach is combining methods using both video and time series data recorded during resuscitation, where the predictions are based on the available sources. From video the activity recognition is done by a 3D CNN method. For the signal data feature extraction is performed on ECG and accelerometer signals and thereafter machine learning is done to perform stimulation detection. We show that best results are achieved with all signals and video available, for the activity “stimulation” we get an AUC of 0.86, sensitivity of 82.32%, specificity of 82.23%, and precision of 57.59%. If only signals or video is available we still get good results with AUC at 0.80, and 0.84 respectively.

Newborn resuscitation guidelines recommend positive pressure ventilation (PPV) for newborns who do not establish effective spontaneous breathing after birth. T-piece resuscitator systems are commonly used in high-resource settings and can additionally provide positive end-expiratory pressure (PEEP). Short expiratory time, high resistance, rapid dynamic changes in lung compliance and large tidal volumes increase the possibility of incomplete exhalation. Previous publications indicate that this may occur during newborn resuscitation. Our aim was to study examples of incomplete exhalations in term newborn resuscitation and discuss these against the theoretical background. Examples of flow and pressure data from respiratory function monitors (RFM) were selected from 129 term newborns who received PPV using a T-piece resuscitator. RFM data were not presented to the user during resuscitation. Examples of incomplete exhalation with higher-than-set PEEP-levels were present in the recordings with visual correlation to factors affecting time needed to complete exhalation. Incomplete exhalation and the relationship to expiratory time constants have been well described theoretically. We documented examples of incomplete exhalations with increased PEEP-levels during resuscitation of term newborns. We conclude that RFM data from resuscitations can be reviewed for this purpose and that incomplete exhalations should be further explored, as the clinical benefit or risk of harm are not known.

European guidelines recommend the use of pulse oximetry (PO) during newborn resuscitation, especially when there is a need for positive pressure ventilation or supplemental oxygen. The objective was to evaluate (i) to what extent PO was used, (ii) the time and resources spent on the application of PO, and (iii) the proportion of time with a useful PO signal during newborn resuscitation. A prospective observational study was conducted at Stavanger University Hospital, Norway, between 6 June 2019 and 16 November 2021. Newborn resuscitations were video recorded, and the use of PO during the first ten minutes of resuscitation was recorded and analysed. Of 7466 enrolled newborns, 289 (3.9%) received ventilation at birth. The resuscitation was captured on video in 230 cases, and these newborns were included in the analysis. PO was applied in 222 of 230 (97%) newborns, median (quartiles) 60 (24, 58) seconds after placement on the resuscitation table. The proportion of time used on application and adjustments of PO during ongoing ventilation and during the first ten minutes on the resuscitation table was 30% and 17%, respectively. Median two healthcare providers were involved in the PO application. Video of the PO monitor signal was available in 118 (53%) of the 222 newborns. The proportion of time with a useful PO signal during ventilation and during the first ten minutes on the resuscitation table was 5% and 35%, respectively. In total, 97% of resuscitated newborns had PO applied, in line with resuscitation guidelines. However, the application of PO was time-consuming, and a PO signal was only obtained 5% of the time during positive pressure ventilation.

BackgroundStimulating infants to elicit a cry at birth is common but could result in unnecessary handling. We evaluated heart rate in infants who were crying versus non-crying but breathing immediately after birth.MethodsThis was single-centre observational study of singleton, vaginally born infants at ≥33 weeks of gestation. Infants who were crying or non-crying but breathing within 30 s after birth were included. Background demographic data and delivery room events were recorded using tablet-based applications and synchronised with continuous heart rate data recorded by a dry-electrode electrocardiographic monitor. Heart rate centile curves for the first 3 min of life were generated with piecewise regression analysis. Odds of bradycardia and tachycardia were compared using multiple logistic regression.Results1155 crying and 54 non-crying but breathing neonates were included in the final analyses. There were no significant differences in the demographic and obstetric factors between the cohorts. Non-crying but breathing infants had higher rates of early cord clamping <60 s after birth (75.9% vs 46.5%) and admission to the neonatal intensive care unit (13.0% vs 4.3%). There were no significant differences in median heart rates between the cohorts. Non-crying but breathing infants had higher odds of bradycardia (heart rate <100 beats/min, adjusted OR 2.64, 95% CI 1.34 to 5.17) and tachycardia (heart rate ≥200 beats/min, adjusted OR 2.86, 95% CI 1.50 to 5.47).ConclusionInfants who are quietly breathing but do not cry after birth have an increased risk of both bradycardia and tachycardia, and admission to the neonatal intensive care unit.Trial registration numberISRCTN18148368.

Abstract Background: Approximately 3-8\% of all newborns do not breathe spontaneously at birth, and require time critical resuscitation. Resuscitation guidelines are mostly based on best practice, and more research on newborn resucitation is highly sought for. Methods: The NewbornTime project will develop artificial intelligence (AI) based solutions for activity recognition during newborn resuscitations based on both visible light spectrum videos and infrared spectrum (thermal) videos. In addition, time-of-birth detection will be developed using thermal videos from the delivery rooms. Deep Neural Network models will be developed, focusing on methods for limited supervision and solutions adapting to on-site environments. A timeline description of the video analysis output enables objective analysis of resuscitation events. The project further aims to use machine learning to find patterns in large amount of such timeline data to better understand how newborn resuscitation treatment is given and how it can be improved. The automatic video analysis and timeline generation will be developed for on-site usage, allowing for data-driven simulation and clinical debrief for health-care providers, and paving the way for automated real-time feedback. This brings added value to the medical staff, mothers and newborns, and society at large. Discussion: The project is a interdisciplinary collaboration, combining AI, image processing, blockchain and cloud technology, with medical expertise, which will lead to increased competences and capacities in these various fields.