Mothers' acceptability of using novel technology with video and audio recording during newborn resuscitation: A cross-sectional survey.

OBJECTIVE: This study aims to assess the acceptability of a novel technology, MAchine Learning Application (MALA), among the mothers of newborns who required resuscitation. SETTING: This study took place at Bharatpur Hospital, which is the second-largest public referral hospital with 13 000 deliveries per year in Nepal. DESIGN: This is a cross-sectional survey. DATA COLLECTION AND ANALYSIS: Data collection took place from January 21 to February 13, 2022. Self-administered questionnaires on acceptability (ranged 1-5 scale) were collected from participating mothers. The acceptability of the MALA system, which included video and audio recordings of the newborn resuscitation, was examined among mothers according to their age, parity, education level and technology use status using a stratified analysis. RESULTS: The median age of 21 mothers who completed the survey was 25 years (range 18-37). Among them, 11 mothers (52.4%) completed their bachelor's or master's level of education, 13 (61.9%) delivered first child, 14 (66.7%) owned a computer and 16 (76.2%) carried a smartphone. Overall acceptability was high that all participating mothers positively perceived the novel technology with video and audio recordings of the infant's care during resuscitation. There was no statistical difference in mothers' acceptability of MALA system, when stratified by mothers' age, parity, or technology usage (p>0.05). When the acceptability of the technology was stratified by mothers' education level (up to higher secondary level vs. bachelor's level or higher), mothers with Bachelor's degree or higher more strongly felt that they were comfortable with the infant's care being video recorded (p = 0.026) and someone using a tablet when observing the infant's care (p = 0.046). Compared with those without a computer (n = 7), mothers who had a computer at home (n = 14) more strongly agreed that they were comfortable with someone observing the resuscitation activity of their newborns (71.4% vs. 14.3%) (p = 0.024). CONCLUSION: The novel technology using video and audio recordings for newborn resuscitation was accepted by mothers in this study. Its application has the potential to improve resuscitation quality in low-and-middle income settings, given proper informed consent and data protection measures are in place.

"Needed but lacked": Exploring demand- and supply-side determinants of access to cardiopulmonary resuscitation training for the lay public in China.

Background: Despite years of public cardiopulmonary resuscitation (CPR) training efforts, the training rate and survival following out-of-hospital cardiac arrest (OHCA) have increased modestly in China. Access is imperative to increase the public CPR training rate, which is determined by both demand- (e.g., the lay public) and supply-side (e.g., CPR trainers) factors. We aimed to explore the demand and supply determinants of access to CPR training for the lay public in China. Methods: Qualitative semi-structured interviews were conducted with 77 laypeople (demand side) and eight key stakeholders from CPR training institutions (supply side) in Shanghai, China. The interview guide was informed by Levesque et al. healthcare access framework. Data were transcribed, quantified, described, and analyzed through thematic content analysis. Results: On the demand side, the laypeople's ability to perceive their need and willingness for CPR training was strong. However, they failed to access CPR training mainly due to the lack of information on where to get trained. Overestimation of skills, optimism bias, and misconceptions impeded laypeople from attending training. On the supply side, trainers were able to meet the needs of the trainees with existing resources, but they relied on participants who actively sought out and registered for training and lacked an understanding of the needs of the public for marketing and encouraging participation in the training. Conclusion: Insufficient information and lack of initiative on the demand side, lack of motivation, and understanding of public needs on the supply side all contributed to the persistently low CPR training rate in China. Suppliers should integrate resources, take the initiative to increase the CPR training rate, innovate training modes, expand correct publicity, and establish whole-process management of training programs.

Delayed and Interrupted Ventilation with Excess Suctioning after Helping Babies Breathe with Congolese Birth Attendants.

There is a substantial gap in our understanding of resuscitation practices following Helping Babies Breathe (HBB) training. We sought to address this gap through an analysis of observed resuscitations following HBB 2nd edition training in the Democratic Republic of the Congo. This is a secondary analysis of a clinical trial evaluating the effect of resuscitation training and electronic heart rate monitoring on stillbirths. We included in-born, liveborn neonates ≥28 weeks gestation whose resuscitation care was directly observed and documented. For the 2592 births observed, providers dried/stimulated before suctioning in 97% of cases and suctioned before ventilating in 100%. Only 19.7% of newborns not breathing well by 60 s (s) after birth ever received ventilation. Providers initiated ventilation at a median 347 s (>five minutes) after birth; no cases were initiated within the Golden Minute. During 81 resuscitations involving ventilation, stimulation and suction both delayed and interrupted ventilation with a median 132 s spent drying/stimulating and 98 s suctioning. This study demonstrates that HBB-trained providers followed the correct order of resuscitation steps. Providers frequently failed to initiate ventilation. When ventilation was initiated, it was delayed and interrupted by stimulation and suctioning. Innovative strategies targeting early and continuous ventilation are needed to maximize the impact of HBB.

Increased risk of bradycardia in vigorous infants receiving early as compared to delayed cord clamping at birth.

OBJECTIVE: To compare HR pattern of vigorous newborns during the first 180 s with early (≤60 s, ECC) or delayed (>60 s, DCC) cord clamping. STUDY DESIGN: Observational study including dry-electrode ECG monitoring of 610 vaginally-born singleton term and late-preterm (≥34 weeks) who were vigorous after birth. RESULTS: 198 received ECC while 412 received DCC with median cord clamping at 37 s and 94 s. Median HR remained stable from 30 to 180 s with DCC (172 and 170 bpm respectively) but increased with ECC (169 and 184 bpm). The proportion with bradycardia was higher among ECC than DCC at 30 s and fell faster in the DCC through 60 s. After adjusting for factors affecting timing of cord clamping, ECC had significant risk of bradycardia compared to DCC (aRR 1.51; 95% CI; 1.01-2.26). CONCLUSION: Early heart instability and higher risk of bradycardia with ECC as compared to DCC supports the recommended clinical practice of DCC.

Usability, acceptability and feasibility of a novel technology with visual guidance with video and audio recording during newborn resuscitation: a pilot study.

OBJECTIVE: Inadequate adherence to resuscitation for non-crying infants will have poor outcome and thus rationalise a need for real-time guidance and quality improvement technology. This study assessed the usability, feasibility and acceptability of a novel technology of real-time visual guidance, with sound and video recording during resuscitation. SETTING: A public hospital in Nepal. DESIGN: A cross-sectional design. INTERVENTION: The technology has an infant warmer with light, equipped with a tablet monitor, NeoBeat and upright bag and mask. The tablet records resuscitation activities, ventilation sound, heart rate and display time since birth. Healthcare providers (HCPs) were trained on the technology before piloting. DATA COLLECTION AND ANALYSIS: HCPs who had at least 8 weeks of experience using the technology completed a questionnaire on usability, feasibility and acceptability (ranged 1-5 scale). Overall usability score was calculated (ranged 1-100 scale). RESULTS: Among the 30 HCPs, 25 consented to the study. The usability score was good with the mean score (SD) of 68.4% (10.4). In terms of feasibility, the participants perceived that they did not receive adequate support from the hospital administration for use of the technology, mean score (SD) of 2.44 (1.56). In terms of acceptability, the information provided in the monitor, that is, time elapsed from birth was easy to understand with mean score (SD) of 4.60 (0.76). CONCLUSION: The study demonstrates reasonable usability, feasibility and acceptability of a technological solution that records audio visual events during resuscitation and provides visual guidance to improve care.

Perceptions and experiences of Congolese midwives implementing a low-cost battery-operated heart rate meter during newborn resuscitation.

Background: 900,000 newborns die from respiratory depression each year; nearly all of these deaths occur in low- and middle-income countries. Deaths from respiratory depression are reduced by evidence-based resuscitation. Electronic heart rate monitoring provides a sensitive indicator of the neonate's status to inform resuscitation care, but is infrequently used in low-resource settings. In a recent trial in the Democratic Republic of the Congo, midwives used a low-cost, battery-operated heart rate meter (NeoBeat) to continuously monitor heart rate during resuscitations. We explored midwives' perceptions of NeoBeat including its utility and barriers and facilitators to use. Methods: After a 20-month intervention in which midwives from three facilities used NeoBeat during resuscitations, we surveyed midwives and conducted focus group discussions (FGDs) regarding the incorporation of NeoBeat into clinical care. FGDs were conducted in Lingala, the native language, then transcribed and translated from Lingala to French to English. We analyzed data by: (1) coding of transcripts using Nvivo, (2) comparison of codes to identify patterns in the data, and (3) grouping of codes into categories by two independent reviewers, with final categories determined by consensus. Results: Each midwife from Facility A used NeoBeat on an estimated 373 newborns, while each midwife at facilities B and C used NeoBeat an average 24 and 47 times, respectively. From FGDs with 30 midwives, we identified five main categories of perceptions and experiences regarding the use of NeoBeat: (1) Providers' initial skepticism evolved into pride and a belief that NeoBeat was essential to resuscitation care, (2) Providers viewed NeoBeat as enabling their resuscitation and increasing their capacity, (3) NeoBeat helped providers identify flaccid newborns as liveborn, leading to hope and the perception of saving of lives, (4) Challenges of use of NeoBeat included cleaning, charging, and insufficient quantity of devices, and (5) Providers desired to continue using the device and to expand its use beyond resuscitation and their own facilities. Conclusion: Midwives perceived that NeoBeat enabled their resuscitation practices, including assisting them in identifying non-breathing newborns as liveborn. Increasing the quantity of devices per facility and developing systems to facilitate cleaning and charging may be critical for scale-up.

Can high school students teach their peers high quality cardiopulmonary resuscitation (CPR)?

Background: If adolescents can teach each other cardiopulmonary resuscitation (CPR) during school hours, this may be a cost-effective approach to CPR training. The aim of this study was to evaluate CPR quality among students trained by student instructors in CPR. Material and methods: Three high schools participated. Recruited student instructors (SIs) were given a two-day course by professional instructors. Theoretic knowledge was acquired through an e-learning program. The SIs then trained fellow students in a 90-minute practical CPR session during physical education classes. All participants performed a 4-minutes test of CPR performance. Data was collected using Little Anne QCPR manikins with QCPR classroom software (Laerdal Medical Inc, Norway). Statistical equivalence in CPR performance was assessed applying the two one-sided tests (TOST)-procedure. Results: Eight professional instructors trained 76 SIs who trained approximately 2650 students in CPR. The number of available tests for analysis of student performance was 982. The compression rates were within guideline recommendations for SIs (mean 110.6, SD 5.4) and students (mean 118.6, SD 8.6). The corresponding numbers for mean compression depth were 7.2 cm (SD 0.7) and 7 cm (SD 1.0). Students demonstrated greater variation in mouth-to-mouth (MTM) skills, with only 41% performing at least 15 successful ventilations during the test. Except for the total number of MTM ventilations (mean difference -5.6), CPR performance was deemed statistically equivalent between professional instructors, SIs and students. Conclusions: High school students can be trained as CPR instructors and teach fellow students CPR with good quality, with some variation in MTM-ventilation skills.

Effect of resuscitation training and implementation of continuous electronic heart rate monitoring on identification of stillbirth.

AIM: To evaluate the effect of resuscitation training and continuous electronic heart rate (HR) monitoring of non-breathing newborns on identification of stillbirth. METHODS: We conducted a pre-post interventional trial in three health facilities in the Democratic Republic of the Congo. We collected data on a retrospective control group of newborns that reflected usual resuscitation practice (Epoch 1). In the prospective, interventional group, skilled birth attendants received resuscitation training in Helping Babies Breathe and implemented continuous electronic HR monitoring of non-breathing newborns (Epoch 2). Our primary outcome was the incidence of stillbirth with secondary outcomes of fresh or macerated stillbirth, neonatal death before discharge and perinatal death. Among a subset, we conducted expert review of electronic HR data to estimate misclassification of stillbirth in Epoch 2. We used a generalized estimating equation, adjusted for variation within-facility, to compare risks between EPOCHs. RESULTS: There was no change in total stillbirths following resuscitation training and continuous electronic HR monitoring of non-breathing newborns (aRR 1.15 [0.95, 1.39]). We observed an increased rate of macerated stillbirth (aRR 1.58 [1.24, 2.02]), death before discharge (aRR 3.31 [2.41, 4.54]), and perinatal death (aRR 1.61 [1.38, 1.89]) during the intervention period. In expert review, 20% of newborns with electronic HR data that were classified by SBAs as stillborn were liveborn. CONCLUSION: Resuscitation training and use of continuous electronic HR monitoring did not reduce stillbirths nor eliminate misclassification.

Improving Newborn Resuscitation by Making Every Birth a Learning Event.

One third of all neonatal deaths are caused by intrapartum-related events, resulting in neonatal respiratory depression (i.e., failure to breathe at birth). Evidence-based resuscitation with stimulation, airway clearance, and positive pressure ventilation reduces mortality from respiratory depression. Improving adherence to evidence-based resuscitation is vital to preventing neonatal deaths caused by respiratory depression. Standard resuscitation training programs, combined with frequent simulation practice, have not reached their life-saving potential due to ongoing gaps in bedside performance. Complex neonatal resuscitations, such as those involving positive pressure ventilation, are relatively uncommon for any given resuscitation provider, making consistent clinical practice an unrealistic solution for improving performance. This review discusses strategies to allow every birth to act as a learning event within the context of both high- and low-resource settings. We review strategies that involve clinical-decision support during newborn resuscitation, including the visual display of a resuscitation algorithm, peer-to-peer support, expert coaching, and automated guidance. We also review strategies that involve post-event reflection after newborn resuscitation, including delivery room checklists, audits, and debriefing. Strategies that make every birth a learning event have the potential to close performance gaps in newborn resuscitation that remain after training and frequent simulation practice, and they should be prioritized for further development and evaluation.

Assessment of breathing in cardiac arrest: a randomised controlled trial of three teaching methods among laypersons.

BACKGROUND: The aim of this trial was to compare a video- and a simulation-based teaching method to the conventional lecture-based method, hypothesizing that the video- and simulation-based teaching methods would lead to improved recognition of breathing patterns during cardiac arrest. METHODS: In this Danish, investigator-initiated, stratified, randomised controlled trial, adult laypersons (university students, military conscripts and elderly retirees) participating in European Resuscitation Council Basic Life Support courses were randomised to receive teaching on how to recognise breathing patterns using a lecture- (usual practice), a video-, or a simulation-based teaching method. The primary outcome was recognition of breathing patterns in nine videos of actors simulating normal breathing, no breathing, and agonal breathing (three of each). We analysed outcomes using logistic regression models and present results as odds ratios (ORs) with 95% confidence intervals (CIs) and P-values from likelihood ratio tests. RESULTS: One hundred fifty-three participants were included in the analyses from February 2, 2018 through May 21, 2019 and recognition of breathing patterns was statistically significantly different between the teaching methods (P = 0.013). Compared to lecture-based teaching (83% correct answers), both video- (90% correct answers; OR 1.77, 95% CI: 1.19-2.64) and simulation-based teaching (88% correct answers; OR 1.48; 95% CI: 1.01-2.17) led to significantly more correct answers. Video-based teaching was not statistically significantly different compared to simulation-based teaching (OR 1.20; 95% CI: 0.78-1.83). CONCLUSION: Video- and simulation-based teaching methods led to improved recognition of breathing patterns among laypersons participating in adult Basic Life Support courses compared to the conventional lecture-based teaching method.

When dispatcher assistance is not saving lives: assessment of process compliance, barriers and outcomes in out-of-hospital cardiac arrest in a metropolitan city in China.

BACKGROUND: Several Chinese cities have implemented dispatcher-assisted cardiopulmonary resuscitation (DA-CPR), although out-of-hospital cardiac arrest (OHCA) survival rates remain low. We aimed to assess the process compliance, barriers and outcomes of OHCA in one of the earliest implemented (DA-CPR) programmes in China. METHODS: We retrospectively reviewed OHCA emergency dispatch records of Suzhou emergency medical service from 2014 to 2015 and included adult OHCA victims (>18 years) with a bystander-witnessed atraumatic OHCA that was subsequently confirmed by on-site emergency physician. The circumstances and DA-CPR process related to the OHCA event were analysed. Dispatch audio records were reviewed to identify potential barriers to implementation during the DA-CPR process. RESULTS: Of the 151 OHCA victims, none survived. The median time from patient collapse to call for emergency services and that from call to provision of cardiopulmonary resuscitation instructions was 30 (IQR 20-60) min and 115 (IQR 90-153) s, respectively. Only 110 (80.3%) bystanders/rescuers followed the dispatcher instructions; of these, 51 (46.3%) undertook persistent chest compressions. Major barriers to following the DA-CPR instructions were present in 104 (68.9%) cases, including caller disconnection of the call, distraught mood or refusal to carry out either compressions or ventilations. CONCLUSIONS: The OHCA survival rate and the DA-CPR process were far from optimal. The zero survival rate is disproportionally low compared with survival statistics in high-income countries. The prolonged delay in calling the emergency services negated and rendered futile any DA-CPR efforts. Thus, efforts targeted at developing public awareness of OHCA, calling for help and competency in DA-CPR should be increased.

REFINE (Rapid Feedback for quality Improvement in Neonatal rEsuscitation): an observational study of neonatal resuscitation training and practice in a tertiary hospital in Nepal.

BACKGROUND: Simulation-based training in neonatal resuscitation is more effective when reinforced by both practice and continuous improvement processes. We aim to evaluate the effectiveness of a quality improvement program combined with an innovative provider feedback device on neonatal resuscitation practice and outcomes in a public referral hospital of Nepal. METHODS: A pre- and post-intervention study will be implemented in Pokhara Academy of Health Sciences, a hospital with 8610 deliveries per year. The intervention package will include simulation-based training (Helping Babies Breathe) enhanced with a real-time feedback system (the NeoBeat newborn heart rate meter with the NeoNatalie Live manikin and upright newborn bag-mask with PEEP) accompanied by a quality improvement process. An independent research team will collect perinatal data and conduct stakeholder interviews. DISCUSSION: This study will provide further information on the efficiency of neonatal resuscitation training and implementation in the context of new technologies and quality improvement processes. TRIAL REGISTRATION: https://doi.org/10.1186/ISRCTN18148368 , date of registration-31 July 2018.

Effect of a real-time feedback smartphone application (TCPRLink) on the quality of telephone-assisted CPR performed by trained laypeople in China: a manikin-based randomised controlled study.

OBJECTIVES: To determine the effect of a free smartphone application (TCPRLink) that provides real-time monitoring and audiovisual feedback on chest compressions (CC) on trained layperson telephone-assisted cardiopulmonary resuscitation (T-CPR) performance. DESIGN: A manikin-based randomised controlled study. SETTING: This study was conducted at a multidisciplinary university and a community centre in China. PARTICIPANTS: One hundred and eighty-six adult participants (age 18-65 years) with T-CPR training experience were randomly assigned to the TCPRLink (n=94) and T-CPR (n=92) groups with age stratification. INTERVENTIONS: We compared the participants' performance for 6 min of CC in a simulated T-CPR scenario both at the baseline and after 3 months. PRIMARY AND SECONDARY OUTCOME MEASURES: The primary outcomes were the CC rate and proportion of adequate CC rate (100-120 min-1). The secondary outcomes included the proportion of participants counting the CC rhythm, time to first CC, CC depth, hands-off time and CC full-release ratio. RESULTS: Participants in the TCPRLink feedback group more consistently performed CC with higher rate, both initially and 3 months later (median 111 (IQR 109-113) vs 108 (103-112) min-1, p=0.002 and 111 (109-113) vs 108 (105-112) min-1, p<0.001, respectively), with less need to count the rhythm (21.3% vs 41.3%, p=0.003% and 7% vs 22.6%, p=0.004, respectively) compared with the T-CPR group. There were no significant differences in time to the first CC, hands-off time or CC full-release ratio. Among 55-65 year group, the CC depth was deeper in the TCPRLink group than in the TCPR group (47.1±9.6 vs 38.5±8.7 mm, p=0.001 and 44.7±10.1 vs 39.3±10.8 mm, p=0.07, respectively). CONCLUSIONS: The TCPRLink application improved T-CPR quality in trained laypersons to provide more effective CCs and lighten the load of counting out the CC with the dispatcher in a simulated T-CPR scenario. Further investigations are required to confirm this effectiveness in real-life resuscitation attempts.

The general public's ability to operate automated external defibrillator: A controlled simulation study.

BACKGROUND: Automated external defibrillators (AEDs) enable laypeople to provide early defibrillations to patients undergoing cardiac arrest, but scant information is available on the general public's ability to use AEDs. This study assessed the ability of laypeople to operate AEDs, the effect of a 15-minute training, and whether skills differed by age. METHODS: From May 1 to December 31, 2018, a prospective simulation study was conducted with 94 laypeople aged 18-65 years (32 aged 18-24 years, 34 aged 25-54 years, and 28 aged 55-65 years) with no prior AED training. The participants' AED skills were assessed individually pre-training, post-training, and at a three-month follow-up using a simulated cardiac arrest scenario. The critical actions and time intervals were evaluated during the AED operating process. RESULTS: Only 14 (14.9%) participants (eight aged 18-24 years, four aged 25-54 years, and two aged 55-65 years) successfully delivered defibrillations before training. AED operation errors were more likely to occur among the participants aged 55-65 years than among other age groups. After training, the proportion of successful defibrillations increased significantly (18-24 years old: 25.0% vs. 71.9%, P<0.01; 25-54 years old: 11.8% vs. 70.6%, P<0.01; 55-65 years old: 7.1% vs. 67.9%, P<0.01). After three months, 26.1% of the participants aged 55-65 years successfully delivered defibrillations, which was significantly lower than that of participants aged 18-24 years (54.8%) and 25-54 years (64.3%) (P=0.02). There were no differences in time measures among three age groups in each test. CONCLUSIONS: The majority of untrained laypeople cannot effectively operate AEDs. More frequent training and refresher courses are crucial to improve AED skills.

Importance of "Telephone Cardiopulmonary Resuscitation" in out-of-Hospital Cardiac Arrest in India.

BACKGROUND: Out-of-hospital cardiac arrest (OHCA) is a major cause of mortality in developing countries such as India. Most cardiac arrests happen outside the hospital and are associated with poor survival rates due to delay in recognition and in performing early cardiopulmonary resuscitation (CPR). Community CPR training and telephone CPR (T-CPR) in the dispatch centers have been shown to increase bystander CPR rates and survival. OBJECTIVES: The aim of this study is to identify the significance of T-CPR in OHCA and to discuss its implementation in the health system to improve OHCA outcomes in India. MATERIALS AND METHODS: A descriptive research study methodology was adopted following a literature search. RESULTS: The search criterion "Cardiovascular diseases" resulted in 162, "Out-side hospital cardiac arrest" in 50; For a comprehensive overview, these publications were evaluated looking for data on T-CPR incidence, criteria for detecting OHCA by emergency medical dispatchers, sensitivity and specificity, and BCPR. CONCLUSION: This current research stresses the scale and seriousness of the implementation of T-CPR in OHCA in India.

The Effectiveness of a New Dispatcher-Assisted Basic Life Support Training Program on Quality in Cardiopulmonary Resuscitation Performance During Training and Willingness to Perform Bystander Cardiopulmonary Resuscitation: A Cluster Randomized Controlled Study.

INTRODUCTION: A new dispatcher-assisted basic life support training program, called "Home Education and Resuscitation Outcome Study (HEROS)" was developed with a goal to provide high-quality dispatcher-assisted cardiopulmonary resuscitation (CPR) training, with a focus on untrained home bystanders. This study aimed to determine whether the HEROS program is associated with improved quality in CPR performance during training and willingness to provide bystander CPR compared with other basic life support programs without dispatcher-assisted CPR (non-HEROS). METHODS: This clustered randomized trial was conducted in 3 district health centers in Seoul. Intervention group was trained with the HEROS program and control group was trained with non-HEROS program. The primary outcome was overall CPR quality, measured as total CPR score. Secondary outcomes were other CPR quality parameters including average compression depth and rate, percentages of adequate depth, and acceptable release. Tertiary outcomes were posttraining survey results. Difference in difference analysis was performed to analyze the outcomes. RESULTS: Among total 1929 trainees, 907 (47.0%) were trained with HEROS program. Compared with the non-HEROS group, the HEROS group showed higher-quality CPR performances and better maintenance of their CPR quality throughout the course (total scores of 84% vs. 80% for first session and 72% vs. 67% for last session; difference in difference of 12.2 vs. 13.2). Other individual CPR parameters also showed significantly higher quality in the HEROS group. The posttraining survey showed that both groups were highly willing to perform bystander CPR (91.4% in the HEROS vs. 92.3% in the non-HEROS) with only 3.4% of respondents in the HEROS group were not willing to volunteer compared with 6.2% in the non-HEROS group (P < 0.01). CONCLUSIONS: The HEROS training program helped trainees perform high-quality CPR throughout the course and enhanced their willingness to provide bystander CPR.

Activity Recognition From Newborn Resuscitation Videos.

OBJECTIVE: Birth asphyxia is one of the leading causes of neonatal deaths. A key for survival is performing immediate and continuous quality newborn resuscitation. A dataset of recorded signals during newborn resuscitation, including videos, has been collected in Haydom, Tanzania, and the aim is to analyze the treatment and its effect on the newborn outcome. An important step is to generate timelines of relevant resuscitation activities, including ventilation, stimulation, suction, etc., during the resuscitation episodes. METHODS: We propose a two-step deep neural network system, ORAA-net, utilizing low-quality video recordings of resuscitation episodes to do activity recognition during newborn resuscitation. The first step is to detect and track relevant objects using Convolutional Neural Networks (CNN) and post-processing, and the second step is to analyze the proposed activity regions from step 1 to do activity recognition using 3D CNNs. RESULTS: The system recognized the activities newborn uncovered, stimulation, ventilation and suction with a mean precision of 77.67%, a mean recall of 77,64%, and a mean accuracy of 92.40%. Moreover, the accuracy of the estimated number of Health Care Providers (HCPs) present during the resuscitation episodes was 68.32%. CONCLUSION: The results indicate that the proposed CNN-based two-step ORAA-net could be used for object detection and activity recognition in noisy low-quality newborn resuscitation videos. SIGNIFICANCE: A thorough analysis of the effect the different resuscitation activities have on the newborn outcome could potentially allow us to optimize treatment guidelines, training, debriefing, and local quality improvement in newborn resuscitation.

A pilot study of Practice While Watch based 50 min school quality cardiopulmonary resuscitation classroom training: a cluster randomized control trial.

AIM: Cardiopulmonary resuscitation (CPR) training in schools can increase the rate of bystander CPR. We assessed whether a "Quality CPR (QCPR) Classroom" can support CPR performance by students trained by a teacher who is not a CPR instructor. METHODS: A cluster randomized trial was undertaken to assess the effectiveness of a 50-min Practice While Watch CPR training program enhanced by QCPR Classroom, which used 42 manikins connected by Bluetooth to real-time feedback monitoring. Fifty-seven students were divided into Group 1, taught by a non-CPR-instructor, and Group 2, taught by a CPR instructor. Psychomotor and cognitive tests were administered before and after training. Primary outcomes were post-training compression depth and rate and percent of improvement in adequate depth, recoil, and overall score. The secondary outcome was risk improvement. RESULTS: Post-training, Group 1 achieved 62.1 ± 7.7 mm and 118.0 ± 3.6 compressions/min whereas Group 2 achieved 57.4 ± 9.8 mm and 119.8 ± 5.4 compressions/min. The overall score improvement in percentage points was 36.4 ± 25.9% and 27.0 ± 27.7%, respectively (P ≤ 0.001 for both). The adequate depth improvement in percentage points was 22.4 ± 35.4% and 32.5 ± 40.0%, respectively (P = 0.33). Teaching by a non-CPR instructor improved student cognitive knowledge. CONCLUSIONS: Using a QCPR Classroom to enhance CPR teaching by a non-CPR-instructor results in similar or better outcomes compared to using a CPR instructor. Use of a Practice While Watch QCPR Classroom will provide adequate quality in preparing students for CPR.

Object Detection During Newborn Resuscitation Activities.

OBJECTIVE: Birth asphyxia is a major newborn mortality problem in low-resource countries. International guideline provides treatment recommendations; however, the importance and effect of the different treatments are not fully explored. The available data are collected in Tanzania, during newborn resuscitation, for analysis of the resuscitation activities and the response of the newborn. An important step in the analysis is to create activity timelines of the episodes, where activities include ventilation, suction, stimulation, etc. Methods: The available recordings are noisy real-world videos with large variations. We propose a two-step process in order to detect activities possibly overlapping in time. The first step is to detect and track the relevant objects, such as bag-mask resuscitator, heart rate sensors, etc., and the second step is to use this information to recognize the resuscitation activities. The topic of this paper is the first step, and the object detection and tracking are based on convolutional neural networks followed by post processing. RESULTS: The performance of the object detection during activities were 96.97% (ventilations), 100% (attaching/removing heart rate sensor), and 75% (suction) on a test set of 20 videos. The system also estimate the number of health care providers present with a performance of 71.16%. CONCLUSION: The proposed object detection and tracking system provides promising results in noisy newborn resuscitation videos. SIGNIFICANCE: This is the first step in a thorough analysis of newborn resuscitation episodes, which could provide important insight about the importance and effect of different newborn resuscitation activities.

Effect of skill drills on neonatal ventilation performance in a simulated setting- observation study in Nepal.

AIM: Maintaining neonatal resuscitation skills among health workers in low resource settings will require continuous quality improvement efforts. We aimed to evaluate the effect of skill drills and feedback on neonatal resuscitation and the optimal number of skill drills required to maintain the ventilation skill in a simulated setting. METHODS: An observational study was conducted for a period of 3 months in a referral hospital of Nepal. Sixty nursing staffs were trained on Helping Babies Breathe (HBB) 2.0 and daily skill drills using a high-fidelity manikin. The high-fidelity manikin had different clinical case scenarios and provided feedback as "well done" or "improvement required" based on the ventilation performance. Adequate ventilation was defined as bag-and-mask ventilation at the rate of 40-60 breaths per minute. The effective ventilation was defined as adequate ventilation with a "well done" feedback. We assessed the correlation of number skill drills and clinical case scenario with adequate ventilation rate using pearson's correlation. We assessed the correlation of number of skill dills performed by each participant with effective ventilation using Mann Whitney test. RESULTS: Among the total of 60 nursing staffs, all of them were competent with an average score of 12.73 ± 1.09 out of 14 (p < 0.001) on bag-and-mask ventilation skill checklist. Among the trained staff, 47 staffs participated in daily skill drills who performed a total of 331 skill drills and 68.9% of the ventilations were done adequately. Among the 47 nursing staffs who performed the skill drills, 228 (68.9%) drills were conducted at a ventilation rate of 40-60 breathes per minute. There was no correlation of the adequate ventilation with skill drill category (p = 0.88) and the level of skill performed (p = 0.28). Out of 47 participants performing the skill drills, 74.5% of them had done effective ventilation with a mean average of 8 skill drills (SD ± 4.78) (p-value- 0.032). CONCLUSION: In a simulated setting, participants who had an average skill drill of 8 in 3 months had effective ventilation. We demonstrated optimal skill drill sessions for maintain the neonatal resuscitation competency. Further evaluation will be required to validate the findings in a scale up setting.