Resuscitation plus最新文献

{"title":"Application of multi-feature-based machine learning models to predict neurological outcomes of cardiac arrest","authors":"Peifeng Ni ,&nbsp;Sheng Zhang ,&nbsp;Wei Hu ,&nbsp;Mengyuan Diao","doi":"10.1016/j.resplu.2024.100829","DOIUrl":"10.1016/j.resplu.2024.100829","url":null,"abstract":"<div><div>Cardiac arrest (CA) is a major disease burden worldwide and has a poor prognosis. Early prediction of CA outcomes helps optimize the therapeutic regimen and improve patients’ neurological function. As the current guidelines recommend, many factors can be used to evaluate the neurological outcomes of CA patients. Machine learning (ML) has strong analytical abilities and fast computing speed; thus, it plays an irreplaceable role in prediction model development. An increasing number of researchers are using ML algorithms to incorporate demographics, arrest characteristics, clinical variables, biomarkers, physical examination findings, electroencephalograms, imaging, and other factors with predictive value to construct multi-feature prediction models for neurological outcomes of CA survivors. In this review, we explore the current application of ML models using multiple features to predict the neurological outcomes of CA patients. Although the outcome prediction model is still in development, it has strong potential to become a powerful tool in clinical practice.</div></div>","PeriodicalId":94192,"journal":{"name":"Resuscitation plus","volume":"20 ","pages":"Article 100829"},"PeriodicalIF":2.1,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142698132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Associations of long-term hyperoxemia, survival, and neurological outcomes in extracorporeal cardiopulmonary resuscitation patients undergoing targeted temperature management: A retrospective observational analysis of the SAVE-J Ⅱ study","authors":"Tomoaki Takeda ,&nbsp;Hayato Taniguchi ,&nbsp;Hiroshi Honzawa ,&nbsp;Takeru Abe ,&nbsp;Ichiro Takeuchi ,&nbsp;Akihiko Inoue ,&nbsp;Toru Hifumi ,&nbsp;Tetsuya Sakamoto ,&nbsp;Yasuhiro Kuroda ,&nbsp;the SAVE-J Ⅱ study group","doi":"10.1016/j.resplu.2024.100831","DOIUrl":"10.1016/j.resplu.2024.100831","url":null,"abstract":"<div><h3>Background</h3><div>Extracorporeal cardiopulmonary resuscitation (ECPR) can improve survival rates and neurological outcomes of patients with out-of-hospital cardiac arrest (OHCA). High levels of partial pressure of arterial oxygen (PaO₂) negatively affect survival and neurological outcomes in patients with OHCA. However, research on associations of hyperoxemia with survival and neurological outcomes after ECPR remains limited, especially considering targeted temperature management (TTM) administration to patients. Additionally, few reports have examined the impact of hyperoxemia beyond 24 h. In this study, we aimed to examine the effect of prolonged hyperoxemia on survival and neurological outcomes after ECPR for OHCA in patients undergoing TTM.</div></div><div><h3>Methods</h3><div>We performed a secondary observational analysis of data from the SAVE-J Ⅱ study, a retrospective, multicenter registry study of ECPR of patients with OHCA. Data on arterial PaO₂ after ECPR for intensive care unit days 2–4 were collected and averaged. Patients were divided into two groups: hyperoxic (PaO₂ ≥ 300 mmHg) and non-hyperoxic (PaO₂ &lt; 300 mmHg). Each variable was compared between the groups. Additionally, survival and mortality rates at discharge were compared, and factors associated with survival (primary outcome) and neurological outcomes (secondary outcome) at discharge were examined.</div></div><div><h3>Results</h3><div>The multivariate analysis for survival at discharge showed that age, initial ventricular fibrillation/ventricular tachycardia (VF/VT) waveform, <em>P</em> = 0.0004), and hyperoxemia were significant factors. For neurological outcomes at discharge, significant factors included age, initial VF/VT waveform, hemoglobin level at presentation, and hyperoxemia.</div></div><div><h3>Conclusions</h3><div>Prolonged hyperoxemia was significantly associated with worse survival and neurological outcomes after ECPR for OHCA in patients who underwent TTM.</div></div>","PeriodicalId":94192,"journal":{"name":"Resuscitation plus","volume":"20 ","pages":"Article 100831"},"PeriodicalIF":2.1,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142698083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effect of introduction of a rapid response system and increasing Medical Emergency Team (MET) activity on mortality over a 20-year period in a paediatric specialist hospital","authors":"Jason Acworth ,&nbsp;Connor Ryan ,&nbsp;Elliott Acworth ,&nbsp;Syeda Farah Zahir","doi":"10.1016/j.resplu.2024.100823","DOIUrl":"10.1016/j.resplu.2024.100823","url":null,"abstract":"<div><h3>Background</h3><div>Rapid Response Systems are hospital-wide patient-focused systems aiming to improve recognition of acute deterioration in patients and trigger a rapid response aimed at preventing potentially avoidable adverse events such as cardiac arrest and death. In 1994, the Royal Children’s Hospital in Brisbane, Australia, was one of the first institutions to adopt a paediatric rapid response system (RRS). The purpose of this study was to investigate the impacts of both introduction of a paediatric RRS and increasing RRS activations (MET dose) on hospital mortality.</div></div><div><h3>Methods</h3><div>Prospectively collected data from institutional databases at a specialist paediatric hospital was used to determine hospital mortality rate pre- and post- implementation of the RRS. An interrupted time series model using segmented regression was utilised to assess the pre-intervention trend, as well as immediate and sustained effects of RRS implementation on hospital mortality. Univariate linear regression examined potential effects of MET dose on mortality.</div></div><div><h3>Results</h3><div>Hospital mortality rate did not change significantly over 15 years before RRS implementation. In the first year after implementation, mortality rate fell significantly (−1.4; 95 %CI −2.27 to −0.52; p = 0.0027). For each year that passed after the intervention, there was no significant change in hospital mortality rate (Estimate: −0.08; 95 %CI −0.17 to 0.02; p = 0.11). Univariate linear regression modelling showed that with every unit increase in MET Dose, hospital mortality rate decreased by −0.13 (95 % CI: −0.27 to 0; p = 0.05).</div></div><div><h3>Conclusions</h3><div>Utilising data from one of the earliest and longest duration single-centre cohort of paediatric MET events, this study reaffirms the association between implementation of a paediatric RRS and decreased hospital mortality. The study also provides novel evidence of the impact of MET dose on patient outcome in the paediatric population. It is recommended that factors influencing the benefit of rapid response systems in paediatric populations are further identified so that this life saving initiative can be optimised.</div></div>","PeriodicalId":94192,"journal":{"name":"Resuscitation plus","volume":"20 ","pages":"Article 100823"},"PeriodicalIF":2.1,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prehospital ventilation strategies in out-of-hospital cardiac arrest: A protocol for a randomized controlled trial (PIVOT trial)","authors":"Cheng-Yi Fan ,&nbsp;Sih-Shiang Huang ,&nbsp;Chi-Hsin Chen ,&nbsp;Chih-Wei Sung ,&nbsp;Chin-Hao Chang ,&nbsp;Tung-Hsiu Hung ,&nbsp;Yen-Chen Liu ,&nbsp;Edward Pei-Chuan Huang","doi":"10.1016/j.resplu.2024.100827","DOIUrl":"10.1016/j.resplu.2024.100827","url":null,"abstract":"<div><h3>Aims</h3><div>The PIVOT trial evaluates the clinical outcomes and ventilatory quality of an automatic pneumatic ventilation method compared to a bag-valve-mask ventilation method in patients who have experienced out-of-hospital cardiac arrest and have had an advanced airway placed.</div></div><div><h3>Methods</h3><div>The PIVOT trial is a pragmatic, open-label, multicenter randomized controlled trial. It aims to recruit 514 patients in Hsinchu County, Taiwan. Adult, non-trauma patients who experience out-of-hospital cardiac arrest, are treated by emergency medical services, and have an advanced airway in place will be randomized. Biweekly cluster randomization will assign EMS teams to either the automatic pneumatic ventilation group or the bag-valve-mask group. Informed consent is waived. The primary outcome is the return of spontaneous circulation, either prehospital or in-hospital. Secondary outcomes include survival to discharge, neurological outcomes, prehospital ventilatory quality, and the content of prehospital resuscitation. Participants will be followed until they pass away or are discharged from the hospital.</div></div><div><h3>Conclusion</h3><div>The PIVOT trial will provide new insight on the clinical effectiveness of automatic pneumatic ventilation in patients experienced out-of-hospital cardiac arrest.</div><div><strong>Trial number</strong>: NCT06067204 in <span><span><em>clinicaltrial.gov</em></span><svg><path></path></svg></span></div></div>","PeriodicalId":94192,"journal":{"name":"Resuscitation plus","volume":"20 ","pages":"Article 100827"},"PeriodicalIF":2.1,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cardiopulmonary resuscitation in obese patients: A scoping review","authors":"Julie Considine ,&nbsp;Keith Couper ,&nbsp;Robert Greif ,&nbsp;Gene Yong-Kwang Ong ,&nbsp;Michael A. Smyth ,&nbsp;Kee Chong Ng ,&nbsp;Tracy Kidd ,&nbsp;Theresa Mariero Olasveengen ,&nbsp;Janet Bray ,&nbsp;on behalf of the International Liaison Committee on Resuscitation (ILCOR) Basic Life Support (BLS), Advanced Life Support (ALS), Paediatric Life Support (PLS), and Education, Implementation, Teams (EIT) Task Forces","doi":"10.1016/j.resplu.2024.100820","DOIUrl":"10.1016/j.resplu.2024.100820","url":null,"abstract":"<div><h3>Background</h3><div>Given the increasing global prevalence of obesity, the International Liaison Committee on Resuscitation (ILCOR) commissioned this scoping review to explore current evidence underpinning treatment and outcomes of obese patients (adult and children) in cardiac arrest.</div></div><div><h3>Methods</h3><div>This scoping review, conducted using Arksey and O’Malley’s framework and reported according to PRISMA-ScR guidelines, included studies of CPR in obese patients. ‘Obese’ was defined according to each individual study. Medline, EMBASE and Cochrane were searched from inception to 1 October 2024. Narrative synthesis was guided by Synthesis Without Meta-Analysis (SWiM) reporting guidelines.</div></div><div><h3>Results</h3><div>36 studies were included: 2 paediatric and 34 adult studies. Fourteen studies reported on out-of-hospital cardiac arrest (OHCA), 12 on in-hospital cardiac arrest (IHCA), eight on both OHCA and IHCA: cardiac arrest location was not reported in two studies. The most common outcomes were survival (n = 29), neurological outcome (n = 17) and ROSC (n = 7). In adults there were variable results in neurological outcome, survival to hospital discharge, longer term survival (months to years), and ROSC. In children, there were two studies suggesting that obese children had worse neurological outcomes, lower survival and lower ROSC than normal weight children. Few studies reported resuscitation quality indicators or techniques, and no studies reported adjustments to CPR techniques.</div></div><div><h3>Conclusion</h3><div>The variability in results does not suggest an urgent need to deviate from standard CPR protocols, however there was some evidence that CPR duration may be longer in obese adults, which may have staffing and resource implications.</div></div>","PeriodicalId":94192,"journal":{"name":"Resuscitation plus","volume":"20 ","pages":"Article 100820"},"PeriodicalIF":2.1,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effect of chest compressions in addition to extracorporeal life support on carotid flow in an experimental model of refractory cardiac arrest in pigs","authors":"Sergey Gurevich ,&nbsp;Rajat Kalra ,&nbsp;Marinos Kosmopoulos ,&nbsp;Alexandra M Marquez ,&nbsp;Deborah Jaeger ,&nbsp;Mitchell Bemenderfer ,&nbsp;Danielle Burroughs ,&nbsp;Jason A Bartos ,&nbsp;Demetris Yannopoulos ,&nbsp;Sebastian Voicu","doi":"10.1016/j.resplu.2024.100826","DOIUrl":"10.1016/j.resplu.2024.100826","url":null,"abstract":"<div><h3>Background</h3><div>Extracorporeal life support (ECLS) provides organ perfusion in refractory cardiac arrest but during the initiation of ECLS mean arterial pressure (MAP) and carotid flow may be suboptimal due to hypotension and/or insufficient flow. We hypothesized that cardiopulmonary resuscitation (CPR) in addition to ECLS may increase carotid flow and MAP compared to ECLS alone.</div></div><div><h3>Methods</h3><div>Observational pilot study comparing hemodynamic parameters before and after CPR cessation in pigs supported by ECLS for experimental refractory cardiac arrest. Pigs were anesthetized, ventricular fibrillation was induced for 3 min, automated CPR performed for 30 min, ECLS was initiated then CPR stopped.</div><div>Variables averaged over 3 s were compared between the last 3 s of CPR + ECLS and 3, 6, 30 s, and 5 and 10 min of ECLS alone. Data are expressed as medians (25–75 interquartile range) and compared using paired samples Wilcoxon test.</div></div><div><h3>Results</h3><div>Nine pigs were included, ECLS was initiated at 2.7 (2.3–2.8) L/min. MAP during CPR + ECLS was 56(53.0–59.2) mmHg, <em>versus</em> 50(45–57)mmHg, 52(46–59)mmHg, 61(50–63)mmHg, 57 (54–66)mmHg, 54 (47–58)mmHg of ECLS alone, p = 0.50, 0.61, 0.70, 0.44, 0.73 respectively. Carotid flow was 113(78–119) ml/min during CPR + ECLS <em>versus</em> 99(79–110)ml/min, 100(81–110)ml/min, 96(60–122)ml/min, 118 (101–130)ml/min, 124 (110–141)ml/min, p = 0.41, 0.52, 0.73, 0.33, 0.20 respectively. When ECLS was initiated at lower flow, 1.5 L/min (one pig), MAP decreased from 59 to 45 mmHg, and carotid flow from 78.2 to 32.5 ml/min after 3 s of ECLS alone.</div></div><div><h3>Conclusion</h3><div>Stopping CPR after effective ECLS initiation does not decrease MAP or carotid flow. Future studies may evaluate augmenting low flow ECLS with CPR.</div></div>","PeriodicalId":94192,"journal":{"name":"Resuscitation plus","volume":"20 ","pages":"Article 100826"},"PeriodicalIF":2.1,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Monocyte programmed death-ligand 1 upregulation in early post-out-of-hospital cardiac arrest is associated with increased risk of acute respiratory distress syndrome","authors":"Le An ,&nbsp;Rui Shao ,&nbsp;Chenchen Hang ,&nbsp;Xingsheng Wang ,&nbsp;Luying Zhang ,&nbsp;Hao Cui ,&nbsp;Jingfei Yu ,&nbsp;Zhenyu Shan ,&nbsp;Ziren Tang","doi":"10.1016/j.resplu.2024.100822","DOIUrl":"10.1016/j.resplu.2024.100822","url":null,"abstract":"<div><h3>Background</h3><div>Out-of-hospital cardiac arrest (OHCA) is a major public health problem. Acute respiratory distress syndrome (ARDS) is a common condition in OHCA patients. We investigated the relationship between the expression of programmed death-1 (PD-1) related molecules and the development and prognosis of ARDS.</div></div><div><h3>Methods</h3><div>Between January 2021 and December 2023, post-resuscitated patients were screened for eligibility in the study. PD-1 related molecules expression was measured by flow cytometry at 48 h of admission in patients with OHCA. The prognostic variables were the development of ARDS during hospitalization and the 28-day patient mortality rate. We analyzed the relationship between the expression of PD-1-related molecules and the development of secondary ARDS in OHCA patients, and assessed the correlation of this expression with the prognosis of ARDS patients.</div></div><div><h3>Results</h3><div>In total, 107 consecutive OHCA patients were enrolled in this study. The median age of the enrolled patients was 60 years, with an age range of 53 to 67 years, and 71 % were male. Among the cardiac arrest patients, 44.8 % had a cardiac etiology, 30.8 % were witnessed, 17.8 % received bystander CPR, and 66.4 % had an initial rhythm of asystole. Our results showed that only monocyte ligand programmed death ligand-1 (PD-L1) expression was significantly elevated in the ARDS group of OHCA patients (P &lt; 0.001). Among patients with ARDS, the expression of PD-L1 on monocytes in non-survivors was significantly higher than in survivors (P &lt; 0.05). The Receiver operating characteristic curves analysis demonstrates that monocyte PD-L1 expression has predictive potential for the development and prognosis of ARDS. Multivariate logistic regression analysis showed that monocyte PD-L1 expression was an independent predictor of mortality in OHCA patients with ARDS.</div></div><div><h3>Conclusions</h3><div>This study indicates that patients with increased PD-L1 on monocytes after OHCA may be more likely to develop ARDS. The expression of PD-L1 on monocytes was an independent predictive factor for the incidence of ARDS and mortality rate in OHCA patients.</div></div>","PeriodicalId":94192,"journal":{"name":"Resuscitation plus","volume":"20 ","pages":"Article 100822"},"PeriodicalIF":2.1,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hemoglobin vesicles improve neurological outcomes after cardiac arrest in rats","authors":"Keisuke Tsuruta ,&nbsp;Hidetada Fukushima ,&nbsp;Hiromi Sakai","doi":"10.1016/j.resplu.2024.100819","DOIUrl":"10.1016/j.resplu.2024.100819","url":null,"abstract":"<div><h3>Aim</h3><div>To investigate the effects of hemoglobin vesicles (HbVs) in preventing hypoxic brain injury after cardiac arrest in a rat model of asphyxia-related cardiac arrest.</div></div><div><h3>Methods</h3><div>Male Wistar rats were divided into three groups: HbVs (n = 18), control (n = 29), and sham (n = 7). Respiratory arrest was induced using muscle relaxants under ventilation. Cardiac arrest occurred 3–4 min later. After 8 min, HbVs or saline (5 ml/kg), adrenaline, and sodium bicarbonate were administered, followed by chest compressions and ventilation. Resuscitation was deemed successful with a mean arterial pressure &gt; 60 mmHg sustained for at least 5 min. Behavioral and histopathological evaluations were performed 7 days later.</div></div><div><h3>Results</h3><div>Survival rates were 39 % and 24 % in the HbVs and control groups, respectively (P = 0.308). Motor activity scores and spatial memory were significantly higher in the HbVs group (P &lt; 0.001). Hippocampal CA1 region staining indicated significantly less neuropathy in the HbVs group (P &lt; 0.001).</div></div><div><h3>Conclusion</h3><div>The administration of HbVs during resuscitation was effective in mitigating brain damage after whole-brain ischemia in rats, as demonstrated by improved histopathological and neurological outcomes. This suggests potential neurological benefits for patients during resuscitation, although further research in larger animal models is required to validate these findings.</div></div>","PeriodicalId":94192,"journal":{"name":"Resuscitation plus","volume":"20 ","pages":"Article 100819"},"PeriodicalIF":2.1,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ventilation practices and preparedness of healthcare providers in term newborn resuscitation: A comprehensive survey study in Austrian hospitals","authors":"Eva M. Schwindt ,&nbsp;Reinhold Stockenhuber ,&nbsp;Jens Christian Schwindt","doi":"10.1016/j.resplu.2024.100817","DOIUrl":"10.1016/j.resplu.2024.100817","url":null,"abstract":"<div><h3>Aim of the study</h3><div>Although neonatal resuscitation is rare, and high-risk births usually occur in specialised centres, unexpected resuscitation measures may be necessary during births that are initially considered low-risk. This survey assessed the practices of healthcare providers in Austrian hospitals for postnatal resuscitation and evaluated their self-assessed airway management skills for newborns.</div></div><div><h3>Methods</h3><div>An online survey was distributed to all staff members responsible for the postnatal care of newborns in hospitals with obstetrics in Austria through the heads of departments (paediatrics, obstetrics, and anaesthesiology). The results are presented in terms of hospital care level and birth volume.</div></div><div><h3>Results</h3><div>In total, 79.5 % of all hospitals with maternity units in Austria participated in the survey. Preparedness was found to be improved with the level of care provided by the hospital. Overall, 50.4 % of the respondents did not feel adequately prepared for neonatal emergencies, and 35.0 % rated their face mask ventilation skills as insufficient. According to the survey results in 61.3 % of included hospitals or 52.5 % of births in Austria, safe endotracheal intubation cannot be provided.</div></div><div><h3>Conclusion</h3><div>A significant proportion of healthcare workers in Austria responsible for postnatal newborn care do not feel adequately prepared for newborn emergencies.</div></div>","PeriodicalId":94192,"journal":{"name":"Resuscitation plus","volume":"20 ","pages":"Article 100817"},"PeriodicalIF":2.1,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Feasibility of real-time compression frequency and compression depth assessment in CPR using a “machine-learning” artificial intelligence tool","authors":"Hannes Ecker ,&nbsp;Niels-Benjamin Adams ,&nbsp;Michael Schmitz ,&nbsp;Wolfgang A. Wetsch","doi":"10.1016/j.resplu.2024.100825","DOIUrl":"10.1016/j.resplu.2024.100825","url":null,"abstract":"<div><h3>Background</h3><div>Video assisted cardiopulmonary resuscitation (V-CPR) has demonstrated to be efficient in improving CPR quality and patient outcomes, as Emergency Medical Service (EMS) dispatchers can use the video stream of a caller for diagnostic purposes and give instructions in a CPR scenario. However, the new challenges faced by EMS dispatchers during video-guided CPR (V-CPR)—such as analyzing the video stream, providing feedback to the caller, and managing stress—demand innovative solutions. This study explores the feasibility of incorporating an open-source “machine-learning” tool (artificial intelligence – AI), to evaluate the feasibility and accuracy in correctly detecting the actual compression frequency and compression depth in video footage of a simulated CPR.</div></div><div><h3>Design</h3><div>MediaPipe Pose Landmark Detection (Google LLC, Mountain View, CA, USA), an open-source AI software using “machine-learning” models to detect human bodies in images and videos, was programmed to assess compression frequency an depth in nine videos, showing CPR on a resuscitation manikin. Compression frequency and depth were assessed from compression to compression with AI software and were compared to the manikin’s internal software (QCPR, Laerdal, Stavanger, Norway). After testing for Gaussian distribution, means of non-gaussian data were compared using Wilcoxon matched-pairs signed rank test and the Bland Altman method.</div></div><div><h3>Main results</h3><div>MediaPipe Pose Landmark Detection successfully identified and tracked the person performing CPR in all nine video sequences. There were high levels of agreement between compression frequencies derived from AI and manikin’s software. However, the precision of compression depth showed major inaccuracies and was overall not accurate.</div></div><div><h3>Conclusions</h3><div>This feasibility study demonstrates the potential of open-source “machine-learning” tools in providing real-time feedback on V-CPR video sequences. In this pilot study, an open-source landmark detection AI software was able to assess CPR compression frequency with high agreement to actual frequency derived from the CPR manikin. For compression depth, its performance was not accurate, suggesting the need for adjustment. Since the software used is currently not intended for medical use, further development is necessary before the technology can be evaluated in real CPR.</div></div>","PeriodicalId":94192,"journal":{"name":"Resuscitation plus","volume":"20 ","pages":"Article 100825"},"PeriodicalIF":2.1,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142587356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}