Computer-vision based recognition of cervical spine stabilization during trauma resuscitation.

Objective:To develop and evaluate a computer vision model for automating the identification of trauma resuscitation phases and procedures during trauma video review (TVR).Background:TVR is a valuable tool for assessing trauma resuscitation quality and identifying improvement opportunities. However, its labor-intensive nature limits widespread adoption.Methods:Ninety-five de-identified trauma resuscitation videos from a Level I trauma center were analyzed. Thirty videos (32%) were manually annotated to define 4 trauma phases—pre-arrival, paramedic handover, acute resuscitation, and pre-departure—and procedures, including X-rays, ultrasound, and intravenous access. A multi-institutional research group guided the annotation framework development. Interrater reliability was assessed using temporal intersection over union (tIoU). Model performance metrics included frame-wise accuracy, edit score, F1 scores (tIoU thresholds: 0.1, 0.25, 0.5), average precision (AP), and average recall.Results:The cohort included 65 (68.4%) male patients, median [interquartile range (IQR)] age 31 (23–44.5) years, with 75 (78.9%) blunt injuries and a median (IQR) injury severity score of 22 (12–29). Annotators achieved a high interrater reliability [mean (standard deviation) tIoU: 0.89 (0.19)]. The model achieved a frame-wise accuracy of 98.3%, edit score of 92.1%, and F1 scores of 94.5%, 94.1%, and 86.3% at tIoU thresholds of 0.1, 0.25, and 0.5, respectively. Procedure detection AP exceeded 66% for X-rays and central line placements.Conclusions:Computer vision can effectively automate TVR, enabling accurate phase segmentation and procedure detection. This approach has the potential to streamline TVR, promote adoption, and improve trauma care quality.

Bakcground: Cardiac arrest in the pediatric emergency department (PED) is an uncommon event requiring rapid assembly of ad hoc multidisciplinary care teams. Effective cardiopulmonary resuscitation (CPR) is influenced by teamwork, leadership, and communication. A designated CPR coach has been shown to improve CPR performance in simulated resuscitations. Objective: To describe dynamic components of pediatric CPR using video review and compare these factors between events with and without a designated CPR coach. Methods: Prospective observational study in a tertiary PED with a resuscitation video review program. Events where a child received chest compressions under videorecorded conditions were included. A CPR coach was designated at the team leader’s discretion. Data on CPR performance was collected from video review. Chest compressions (CC) were defined in CC segments (the duration of CC given by a single provider before switching to a different providers). Pauses in CC were measured in seconds and tasks performed during pauses (e.g. pulse check, rhythm check) were recorded. Unadjusted univariate analysis between events with and without a CPR coach was performed by c2 analyses for dichotomous variables and nonparametric analysis for continuous variables. Results: 88 events were analyzed (OHCA n=74, IHCA n=14; ROSC 23/88 (26%); survival to admission 21/88 (24%)). The median duration of CPR was 18 minutes (IQR 12 – 27 minutes). Median CC segment duration was 71 sec (IQR 42 – 104 sec). 84% of segments were less than 2 minutes; 39% were less than 1 minute. A median of 12 pauses in chest compressions occurred per event (range 2-30). Median pause duration was 4 sec (IQR 3 – 9 sec); 18% of pauses exceeded 10 seconds. The coordination of compressor change, pulse check, and rhythm check were done in 182/934 (18%) of CC pauses. Median chest compression fraction across all events was 87% (IQR 76% – 93%). A CPR coach was designated in 24/88 (27%) events. On univariate analysis comparing events with and without a CPR coach, there were no significant differences in CCF, average CC segment duration, or number of pauses > 10 sec. Conclusions: Using video review, areas for improvement in team performance during pediatric CPR were identified. The presence of a designated CPR coach was not associated with significant differences in these parameters. Future studies should examine the impact of targeted CPR coach training on dynamic team function to improve CPR.

Video-assisted dispatcher support in cardiopulmonary resuscitation (VA-CPR) has shown beneficial effects on CPR quality. This study examines the influence of professional background on the ability to identify typical errors in CPR performance using video-based assessments. Within this simulation-based observational study, 61 participants (31 EMS personnel, 30 emergency physicians) evaluated nine video sequences showing simulated CPR or ventilation. Participants were grouped by profession, not randomly. The primary endpoint was the correct identification of expert-defined errors in the presented videos, analyzed in relation to professional background. Evaluation accuracy for CPR and ventilation videos was examined in relation to participant characteristics. Overall, n = 427 CPR videos were correctly classified in 73.3% of cases by EMS personnel and 75.7% by emergency physicians (β = 0.370, SE = 0.297, 95% CI: -0.21 to 0.95, p = 0.213). Ventilation scenarios (n = 122) were correctly classified in 93.5% (EMS) and 98.3%, (EP) (β = 4.50, SE = 6.73, 95% CI: -8.82 to 17.82, p = 0.505). The models assessing classification accuracy for CPR and ventilation did not reach statistical significance (pCPR=0.869 and pventilation=0.183), and none of the tested predictors were significantly associated with evaluation accuracy. No significant differences in evaluation accuracy for CPR and ventilation videos were observed between professional groups or across tested participant characteristics.

Abstract Introduction Utilization of trauma video review for quality and performance improvement initiatives has increased in recent years across numerous institutions. The value of video review for burn resuscitations remains unknown. The Joint Commission estimates over 80% of serious, preventable adverse medical events occur due to ineffective handoffs. We sought to study emergency medical service (EMS) handoff and measure initial resuscitation metrics using burn resuscitation video review (BVR). This initial review sought to determine the feasibility of using BVR to study the compliance of EMS providers and outside hospitals with Advanced Burn Life Support (ABLS) guidelines. Methods As part of an ongoing multi-center study of BVR at ABA verified burn centers, we reviewed 15 burn resuscitations from a single institution between May 2024 – August 2024. A team of five analysts reviewed the recorded resuscitations. EMS handoffs were evaluated in terms of content, interruptions, and overall efficacy to include the age, sex, weight, and past medical history of the patient, time of injury, possibility of inhalation injury, most recent vital signs, medical treatments prior to arrival, estimated total body surface area of the burn, hourly urine output, and hourly fluid titration. Data collection includes time to initiation of resuscitation and initial burn treatment. Results Video review of burn resuscitations and EMS handoff is feasible, and the audiovisual clarity is sufficient for data extraction. EMS handoff, measured from the time the EMS provider started speaking until report completion, including answered questions, had an average length of [0:01:28 minutes] with a range of [0:00:27 – 0:03:30 minutes]. Interruptions during handoff were seen in all encounters (15/15). Content of handoff varied with 100% including mechanism of injury, 60% including age, and 33.3% including time of injury. When looking at vital signs, most recent heart rate was communicated in 26% of handoffs and blood pressure in 40%, whereas temperature was not relayed in any case. Inconsistencies in initial burn resuscitations were also seen, with 46.6% of patients not receiving any intravenous fluids from EMS and 33.3% of receiving burn teams not specifying fluid resuscitation upon patient arrival. Conclusions Preliminary analysis of this ongoing project indicates BVR will allow for effective quality improvement efforts targeting EMS handoff and resuscitation by evaluating real-time adherence rates to current ABLS guidelines and the initial resuscitation of our burn patients. Applicability of Research to Practice BVR may identify key opportunities for improvement in EMS communication and ABLS guideline adherence. For the first time, we will be able to directly evaluate real-time practice rather than infer from documentation. Funding for the Study N/A

Neonatal resuscitation video review - has the time for wider adoption come?

Introduction: Fluid resuscitation includes a wide variety of products, usually classified as crystalloids or colloids. Although crystalloids and colloids are frequently used in fluid resuscitation, the ideal fluid for resuscitation remains controversial. In this study, we aimed to evaluate the reliability of the information given by physician channels and physicians about fluid resuscitation on YouTube. Methods: To identify appropriate videos, a standard YouTube search was performed on 01.09.2024 using the terms “fluid resuscitation”, “fluid resuscitation in trauma patient” and “fluid resuscitation in burn patient”. Multiple scoring systems were used to evaluate the videos, including DISCERN, a validated tool for analyzing the quality of health information in consumer-targeted videos, the Journal of the American Medical Association (JAMA) and the Global Quality Score (GQS). All statistical tests were performed using SPSS version 27 (IBM®, Chicago, USA). Mean±standard deviation was used for descriptive statistics and numerical data with normal distribution. Median (minimum-maximum) was used for abnormally distributed data. Nominal data were expressed as numbers and percentages. Results: After excluding 77 videos (32 videos were not in English, 31 videos were not physician-generated, 14 videos were longer than 1.5 hours), 73 videos were evaluated in our study. The mean values (mean±sd) of the GQS, 5-point modified DISCERN and JAMA scores of the videos were 3.55±1.06, 3.41±1.17 and 2.62±0.93, respectively. In the GQS grouping, 17.8% of the videos analyzed were of poor quality, 27.4% were of moderate quality and 54.7% were of high quality. Conclusions: Our study shows that physician-generated fluid resuscitation videos on YouTube are generally of acceptable quality. Future studies could obtain more comprehensive results by evaluating content in different languages.

ABSTRACTObjectiveTo evaluate the impact of a Cardiopulmonary Resuscitation Video Decision Aid (CPR‐VDA) on pet owners’ resuscitation preferences, decisional confidence, conflict, and knowledge of CPR.DesignProspective, interventional survey study with data collected from January to March 2024. Owners of pets presenting through the Emergency Department completed a preintervention questionnaire. They then viewed a 7‐min CPR‐VDA and completed a postintervention questionnaire. Changes between pre‐ and postintervention scores were analyzed using Wilcoxon signed rank tests.SettingPrivate referral hospitalSubjectsSeventy‐eight pet ownersInterventionsViewing of a CPR‐VDAMeasurements and Main ResultsThe preintervention questionnaire assessed pet owner demographics, resuscitation preferences, decisional confidence and conflict, and prior knowledge about CPR. The postintervention questionnaire reassessed resuscitation preferences, decisional confidence and conflict, and CPR knowledge, with additional questions evaluating owner’ perceptions of the CPR‐VDA. Preintervention, 56 of 78 (72%) participants expressed a preference for “resuscitation” of their pet, five of 78 (6%) opted for “do not attempt resuscitation,” and 17 of 78 (22%) were “not sure.” Most participants (56/78 [72%]) did not change their resuscitation preference following the intervention. Participants felt more confident in their decision after watching the CPR‐VDA (p < 0.001). There was no difference in how conflicted they felt making this decision (median score on a rating scale of 1–5 was 2.25 preintervention and 2.42 postintervention; p = 0.192). Their knowledge of CPR improved (median correct answers increasing from 5.5/9 to 9/9; p < 0.001). Most participants rated the video “good” or “excellent” (72/78 [92%]), found the video helpful (62/78 [79%]), and were likely to recommend it to other pet owners (72/78 [92%]).ConclusionsThe use of a CPR‐VDA improved pet owner knowledge of CPR and increased their confidence in decision making. The CPR‐VDA was well received by pet owners and may be a useful tool to facilitate discussions regarding this topic.

Neonatal resuscitation video review (NRVR) involves recording and reviewing resuscitations for education and quality assurance. Though NRVR has been shown to improve teamwork and skill retention, it is not widely used. We evaluated clinicians' experiences of NRVR to understand how NRVR impacts learning and can be improved. Neonatal Intensive Care Unit (NICU) clinicians with previous NRVR experience were recruited for individual semi-structured interviews. Using a social constructivist viewpoint, five researchers used thematic analysis to analyze participant responses. Twenty-two clinicians (11 nurses, 11 doctors) were interviewed. All participants expressed positive attitudes towards NRVR. Four themes were identified: (1) Learning from reality-exposure to real-life resuscitations was highly clinically relevant. (2) Immersive self-regulation-watching videos aided recall and reflection. (3) Complexities in learner psychological safety-all participants acknowledged viewing NRVR videos could be confronting. Some expressed fear of judgment from colleagues, though the educational benefit of NRVR superseded this. (4) Accessing and learning from diverse vantage points-NRVR promoted group discussion, which prompted participant learning from colleagues' viewpoints. Neonatal clinicians reported NRVR to be an effective and safe method for learning and refining skills required during neonatal resuscitation, such as situational awareness and communication. Neonatal resuscitation video review is not known to be widely used in neonatal resuscitation teaching, and published research in this area is limited. Our study examined clinician attitudes towards an established neonatal resuscitation video review program. We found strong support for teaching using neonatal resuscitation video review among neonatal doctors and nurses, with key benefits including increased situational awareness and increased clinical exposure to resuscitations, while maintaining psychological safety for participants. The results of this study add evidence to support the addition of video review to neonatal resuscitation training.

To assess the impact of NRP virtual simulations (eSim™), video or no refresher training, on simulation performance, six months after a provider course; and to evaluate eSim™ acceptability. In this multi-site randomized controlled trial, NRP providers from four U.S. institutions were randomized to receive refreshers every two months with NRP eSim™, NRP resuscitation video, or no refresher (control). Simulation performance was assessed immediately after an NRP course and six months later. 248 participants completed the baseline simulation and 148 completed the six-month follow-up simulation. The majority (71%) of subjects had a decline in resuscitation skills at 6 months. There were no differences in performance between the study groups, but participants who reported using either the video or eSim™ had less decline in performance at the 6-month follow-up (p < 0.05). NRP refreshers with either eSim™ or NRP video may mitigate the decline in resuscitation skills after training.

To determine the impact of structured debriefings (SD) with audio/video review of trauma patients' resuscitation events on trauma team (TT) technical and non-technical skills. Single-center prospective observational cohort study. The study included all emergency department patients aged 18years or older who received resuscitation from the TT. Virtual meeting was held with the TT using SD to review one trauma patient resuscitation video. Technical skills improvement was based on adherence to the ATLS protocol and non-technical skills based on T-NOTECHS scale. There was statistically significant improvement in adherence to the ATLS protocol: 73% [55-82%] vs 91% [82-100%] (p < 0.001); and improvement in T-NOTECHS scale: 12 [10-14] vs 16 [14-19] points (p < 0.001). In this study, we found that structured debriefings with review of patients' resuscitation video recordings can have a significant positive impact on trauma team performance in the emergency department in both technical and non-technical skills.

This article is available in open access under Creative Common Attribution-Non-Commercial-No Derivatives 4.0 International (CC BY-NC-ND 4.0) license, allowing to download articles and share them with others as long as they credit the authors and the publisher, but without permission to change them in any way or use them commercially.

61 Measuring the Emotional Impact of Educational Resuscitation Videos Using Artificial Intelligence (AI)

Abstract Background Many methods and tools have been suggested to enhance the efficiency of trauma team (TT) work. However, most of these methods necessitate costly simulators and mannequins, which demand significant financial and human resources. Objective Was to determine the impact of structured debriefings (SD) with audio/video review of trauma patients' resuscitation events on TT technical and non-technical skills. Methods Single center prospective observational cohort study. The study included all ED patients aged 18 years or older who received resuscitation from the trauma team (TT). Virtual meeting was held with the TT using SD to review one trauma patient resuscitation video. Technical skills improvement was based on adherence to the ATLS protocol and non-technical skills based on T-NOTECHS scale. Results There was statistically significant improvement in adherence to the ATLS protocol: 73% [55–82%] vs 91% [82–100%] (p &lt; 0.001); and improvement in T-NOTECHS scale: 12 [10–14] vs 16 [14–19] points (p &lt; 0.001). Conclusion In this study we found that structured debriefings with review of patients' resuscitation video recordings can have a significant positive impact on trauma team performance in the emergency department in both technical and non-technical skills.

Adolescents need to know the main action to be given to OHCA (out-of-hospital cardiac arrest) patients because people who were close to cardiac arrest patients have an essential role in performing the resuscitation. The rapid resuscitation in the first few minutes will increase the chance of survival by double to triple. Increasing the ability of nonexpert people to perform resuscitation can be performed by providing training using standardized American Heart Association resuscitation videos. The study aimed to determine the change in resuscitation attitudes among adolescents after receiving the training video. The quasi-experimental design was used within a pretest-posttest group. The population of this study was 160 adolescents, and 94 respondents were recruited using a purposive sampling technique according to the inclusion criteria for high school youth who had never received cardiopulmonary resuscitation (CPR) training inside or outside of school. The variables in this study were training videos and attitudes to the practice. Data were analyzed using the Wilcoxon test. The results showed the attitudinal variable (p=0.0000.05). Among 94 respondents whole had a positive attitude (100%) before and after receiving the CPR training video. The attitudes are increasing after the implementation of the CPR training video compared to before the intervention. Providing first aid training to help cardiac arrest patients using training videos to the adolescent by healthcare team needs to be increased.

The quality of neonatal resuscitation after delivery needs to be improved to reach the Sustainable Development Goals 3.2 (reducing neonatal deaths to <12/1,000 live newborns) by the year 2030. Studies have emphasized the importance of correctly performing the basic steps of resuscitation including stimulation, heart rate assessment, ventilation, and thermal control. Recordings with video cameras have previously been shown to be one way to identify performance practices during neonatal resuscitation. A description of a low-cost delivery room set up for video recording of neonatal resuscitation. The technical setup includes rechargeable high-definition cameras with two-way audio, NeoBeat heart rate monitors, and the NeoTapAS data collection tools for iPad with direct data export of data for statistical analysis. The setup was field tested at Mulago National Referral Hospital, Kampala, Uganda, and Phu San Hanoi Hospital, Hanoi, Vietnam. The setup provided highly detailed resuscitation video footage including data on procedures and team performance, heart rate monitoring, and clinical assessment of the neonate. The data were analyzed with the free-of-charge NeoTapAS for iPad, which allowed fast and accurate registration of all resuscitative events. All events were automatically registered and exported to R statistical software for further analysis. Video analysis of neonatal resuscitation is an emerging quality assurance tool with the potential to improve neonatal resuscitation outcomes. Our methodology and technical setup are well adapted for low- and lower-middle-income countries settings where improving neonatal resuscitation outcomes is crucial. This delivery room video recording setup also included two-way audio communication that potentially could be implemented in day-to-day practice or used with remote teleconsultants.

Objective Handoffs by emergency medical services (EMS) personnel suffer from poor structure, inattention, and interruptions. The relationship between the quality of EMS communication and the non-technical performance of trauma teams remains unknown. Methods We analyzed 3 months of trauma resuscitation videos (highest acuity activations or patients with an Injury Severity Score [ISS] of ≥15). Handoffs were scored using the mechanism-injury-signs-treatment (MIST) framework for completeness (0–20), efficiency (category jumps), interruptions, and timeliness. Trauma team non-technical performance was scored using the Trauma Non-Technical Skills (T-NOTECHS) scale (5–15). Results We analyzed 99 videos. Handoffs lasted a median of 62 seconds [IQR: 43–74], scored 11 [10–13] for completeness, and had 2 [1–3] interruptions. Most interruptions were verbal (85.2%) and caused by the trauma team (64.9%). Most handoffs (92%) were efficient with 2 or fewer jumps. Patient transfer during handoff occurred in 53.5% of the videos; EMS providers giving handoff helped transfer in 69.8% of the Primary surveys began during handoff in 42.4% of the videos. Resuscitation teams who scored in the top-quartile on the T-NOTECHS (>11) had higher MIST scores than teams in lower quartiles (13 [11.25–14.75] vs. 11 [10–13]; p < .01). There were no significant differences in ISS, efficiency, timeliness, or interruptions between top- and lower-quartile groups. Conclusions There is a relationship between EMS MIST completeness and high performance of non-technical skill by trauma teams. Trauma video review (TVR) can help identify modifiable behaviors to improve EMS handoff and resuscitation efforts and therefore trauma team performance.

IntroductionOne of the most challenging aspects of Emergency Medicine (EM) residency is mastering the leadership skills required during a resuscitation. Use of resuscitation video recording for debriefing is gaining popularity in graduate medical education. However, there are limited studies of how video technology can be used to improve leadership skills in the emergency department. We aim to evaluate the utility of video-assisted self-reflection, compared with self-reflection alone, in the setting of resuscitation leadership.MethodsThis was a prospective, randomized, controlled pilot study conducted in 2018 at an urban level 1 trauma center with a three-year EM residency program. The trial included postgraduate year (PGY) 2 and 3 residents (n = 10). Each resident acted as an individual team leader for a live real-time resuscitation in the emergency department. The authors classified a patient as a resuscitation if there was an immediate life- or limb-threatening disease process or an abnormal vital sign with an indication of hypoperfusion. Each resident was recorded as the team leader twice. Both control and intervention groups produced written self-reflection after their first recording. The intervention group viewed their resuscitation recording while completing the written reflection. After their reflection, all participants were recorded for a second resuscitation. Two faculty experts, blinded to the study, scored each video using the Concise Assessment of Leader Management (CALM) scale to measure the leadership skills of the resident team leader.ResultsFive PGY‑3 and five PGY‑2 residents participated. The weighted kappa between the two experts was 0.45 (CI 0.34–0.56, p < 0.0001). The median gain score in the control group was −1.5 (IQR) versus 0.5 in the intervention group (IQR).DiscussionVideo-assisted self-reflection showed positive gain score trends in leadership evaluation for residents during a resuscitation compared with the non-video assisted control group. This tool would be beneficial to implement in EM residency.Supplementary InformationThe online version of this article (10.1007/s40037-021-00690-9) contains supplementary material, which is available to authorized users.

Assessment of temporal variations in adherence to NRP using video recording in the delivery room

Out-of-hospital cardiac arrests are a leading global cause of mortality. The American Heart Association (AHA) promotes several important strategies associated with improved cardiac arrest (CA) outcomes, including decreasing pulse check time and maintaining a chest compression fraction (CCF)>0.80. Video review is a potential tool to improve skills and analyse deficiencies in various situations; however, its use in improving medical resuscitation remains poorly studied in the emergency department (ED). We implemented a quality improvement initiative, which utilised video review of CA resuscitations in an effort to improve compliance with such AHA quality metrics. A cardiopulmonary resuscitation video review team of emergency medicine residents were assembled to analyse CA resuscitations in our urban academic ED. Videos were reviewed by two residents, one of whom was a senior resident (Postgraduate Year 3 or 4), and analysed using Spearman's rank correlation coefficient for numerous quality improvement metrics, including pulse check time, CCF, time to intravenous access and time to patient attached to monitor. We collected data on 94 CA resuscitations between July 2017 and June 2020. Average pulse check time was 13.09 (SD±5.97)seconds, and 38% of pulse checks were <10seconds. After the implementation of the video review process, there was a significant decrease in average pulse check time (P=.01) and a significant increase in CCF (P=.01) throughout the study period. Our study suggests that the video review and feedback process was significantly associated with improvements in AHA quality metrics for resuscitation in CA amongst patients presented to the ED.