Australian Critical Care最新文献

{"title":"Outcome reporting in neonatal septic shock studies: A systematic review","authors":"Hanmei Peng RN, MSN ,&nbsp;Jing Shi MD, PhD ,&nbsp;Jun Tang MD, PhD ,&nbsp;Ying-Xin Li RN, MSN ,&nbsp;Xia Li RN, MSN ,&nbsp;Xuemei Guo RN, BSN ,&nbsp;Meizhu Lu MD, PhD ,&nbsp;Xingli Wan RN, PhD ,&nbsp;Biru Luo RN, PhD ,&nbsp;Mei Rosemary Fu RN, PhD ,&nbsp;Yuan Li RN, PhD ,&nbsp;Yanling Hu RN, MBA","doi":"10.1016/j.aucc.2025.101227","DOIUrl":"10.1016/j.aucc.2025.101227","url":null,"abstract":"<div><h3>Objectives</h3><div>Neonatal septic shock is a critical condition requiring immediate and individualised intervention. Despite extensive research, there is a significant heterogeneity in outcome reporting across studies which may lead to incomparability of study results and limit evidence synthesis. The aim of this systematic review was to identify and analyse outcomes reported in studies focussing on interventions for neonatal septic shock to inform the development of a core outcome set to standardise outcome reporting for future research and practice.</div></div><div><h3>Methods</h3><div>We conducted this systematic review following the Core Outcome Measures in Effectiveness Trials initiative framework and Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. We systematically searched PubMed, Embase (Ovid), and the Cochrane Library, covering all records until September 2024. Four independent reviewers performed literature screening and data extraction, with disagreements resolved by consensus among two additional reviewers. Extracted outcomes and their definitions were standardised and categorised into core areas and domains using a 38-item standardised taxonomy.</div></div><div><h3>Results</h3><div>From 7139 records, 25 studies involving 4957 neonates were included, yielding 136 outcomes. After consolidation, 66 unique outcomes were identified and classified into four core areas based on the established taxonomy. The most frequently reported area was physiological/clinical outcomes (72%, 18 of 25 studies), encompassing 32 outcomes. This was followed by death (68%, 17/25), resource use (48%, 12/25), and adverse events (36%, 9/25). In addition, outcomes related to life impact were not measured in the included studies.</div></div><div><h3>Conclusions</h3><div>This review demonstrates considerable heterogeneity in outcome reporting across neonatal septic shock studies and highlights the absence of life impact measures. These findings support the need for developing a standardised core outcome set to enhance outcome reporting consistency and clinical relevance.</div></div>","PeriodicalId":51239,"journal":{"name":"Australian Critical Care","volume":"38 4","pages":"Article 101227"},"PeriodicalIF":2.6,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143777671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Corrigendum to “The Paediatric AirWay Suction (PAWS) appropriateness guide for endotracheal suction interventions” [Aust Crit Care 35 (2022) 651–660]","authors":"Jessica Schults RN, PhD ,&nbsp;Karina Charles RN, MN ,&nbsp;Debbie Long RN, PhD ,&nbsp;Georgia Brown MD ,&nbsp;Beverley Copnell RN, PhD ,&nbsp;Peter Dargaville MD ,&nbsp;Kylie Davies RN, PhD ,&nbsp;Simon Erikson MD ,&nbsp;Kate Forrest RN ,&nbsp;Jane Harnischfeger RN, MN ,&nbsp;Adam Irwin MBChB, PhD ,&nbsp;Tina Kendrick RN, BN (Hons), MN ,&nbsp;Anna Lake RN ,&nbsp;George Ntoumenopoulos PT, PhD ,&nbsp;Michaela Waak MD ,&nbsp;Mark Woodard RN, MClinN ,&nbsp;Lyvonne Tume RN, PhD ,&nbsp;Marie Cooke RN, PhD ,&nbsp;Marion Mitchell RN, PhD ,&nbsp;Lisa Hall BTech BiomedSci (Hons), PhD ,&nbsp;Amanda Ullman RN, PhD","doi":"10.1016/j.aucc.2025.101224","DOIUrl":"10.1016/j.aucc.2025.101224","url":null,"abstract":"","PeriodicalId":51239,"journal":{"name":"Australian Critical Care","volume":"38 4","pages":"Article 101224"},"PeriodicalIF":2.6,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Respiratory rate–oxygenation index and National Early Warning Score 2 score are associated with orotracheal intubation in patients with cardiogenic pulmonary oedema","authors":"Isabelle de Almeida Souza BN ,&nbsp;Asiya Shalova BN ,&nbsp;Nayane Maria Vieira MN,&nbsp;João Carlos Clark Barros BN,&nbsp;Gustavo Martins Ferreira BN,&nbsp;Paula Schmidt Azevedo PhD,&nbsp;Bertha Furlan Polegato PhD,&nbsp;Leonardo Antônio Mamede Zornoff PhD,&nbsp;Sérgio Alberto Rupp de Paiva PhD,&nbsp;Taline Lazzarin BN,&nbsp;Marcos Ferreira Minicucci PhD","doi":"10.1016/j.aucc.2025.101222","DOIUrl":"10.1016/j.aucc.2025.101222","url":null,"abstract":"<div><h3>Background</h3><div>This study evaluates the association between the respiratory rate–oxygenation (ROX) index and the National Early Warning Score 2 (NEWS2) score with orotracheal intubation (OTI) and in-hospital mortality in patients with cardiogenic pulmonary oedema (CPE).</div></div><div><h3>Methods</h3><div>This retrospective observational study enrolled patients aged 18 years or older who had developed CPE at admission or during hospital stay. Demographic, clinical, and laboratory data were collected within the first 24 h of CPE onset from the electronic records. The outcomes needed for OTI during 24 h after CPE diagnosis and in-hospital mortality were also collected. The ROX index and NEWS2 were calculated using variables collected at CPE occurrence.</div></div><div><h3>Results</h3><div>Two hundred eighty-six patients with CPE were evaluated; however, 68 patients were excluded due to the absence of variables to calculate the ROX index. Thus, we included 218 patients in the analysis. The mean age was 67.8 ± 14.0 years, 51.8% were female, the median of the ROX index was 9.29 (6.06–13.05), and the median of the NEWS2 was 10.0 (7.0–12.0). Amongst these patients, 28.0% needed OTI 24 h after CPE and 30.3% died. In univariate analysis, lower values of the ROX index and higher values of the NEWS2 were associated with OTI. There was no association with mortality. In logistic regression models, the ROX index and NEWS2 were associated with OTI when adjusted by smoking, time of CPE, and endovenous nitrate and morphine (ROX index: odds ratio [OR] = 0.908, 95% confidence interval [CI] = 0.843–0.979, p = 0.012; NEWS2: OR = 1.261, 95% CI = 1.049–1.514, p = 0.013) and when adjusted by age, sex, and time of CPE (at admission or during hospital stay; ROX index: OR = 0.909, 95% CI = 0.847–0.976, p = 0.008; NEWS2: OR = 1.190, 95% CI = 1.015–1.396, p = 0.032).</div></div><div><h3>Conclusions</h3><div>The ROX index and NEWS2 were associated with OTI in CPE despite no association with mortality.</div></div>","PeriodicalId":51239,"journal":{"name":"Australian Critical Care","volume":"38 3","pages":"Article 101222"},"PeriodicalIF":2.6,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An interprofessional cognitive aid to optimise extubation planning for patients with acute spinal cord injury","authors":"Isabella Lane PT, BPhty(Hons) ,&nbsp;Alison Blunt PT, BPhty ,&nbsp;Alicia Agli PT, BPhty ,&nbsp;Brooke Wadsworth PT, MPhil ,&nbsp;Samuel Pobar RN, BSc(Nurs) ,&nbsp;Peter Kruger MD, PhD ,&nbsp;Elise M. Gane PT, PhD","doi":"10.1016/j.aucc.2025.101206","DOIUrl":"10.1016/j.aucc.2025.101206","url":null,"abstract":"<div><h3>Background</h3><div>Early management of patients in the intensive care unit after acute spinal cord injury is challenging, particularly for patients with cervical injury and tetraplegia who have high rates of pneumonia and extubation failure.</div></div><div><h3>Objectives</h3><div>The primary objective was to evaluate the usability of a new interprofessional cognitive aid to optimise extubation planning for patients with acute tetraplegia. Secondary objectives were to (i) observe and compare clinician behaviour during high-fidelity simulation scenarios and (ii) compare clinician self-ratings of confidence before and after introduction to the cognitive aid.</div></div><div><h3>Methods</h3><div>Dual methods design. Twenty-six intensive care clinicians (doctors, nurses, and physiotherapists) completed two cervical spinal cord–injured patient simulation scenarios in a random order. Between their two scenarios, participants were orientated to the new cognitive aid. Simulations were audiovisually recorded and scored by a blinded observer using a standardised checklist. Pre and post simulation questionnaires and semistructured interviews were completed.</div></div><div><h3>Results</h3><div>The cognitive aid had good usability across all three disciplines (mean score on the System Usability Scale was 74.4). After introduction to the cognitive aid, clinicians had higher confidence with completing an independent respiratory assessment (p &lt; 0.01) and objective outcome measures required for extubation (p &lt; 0.01) and to discuss their objective findings and ongoing management with the multidisciplinary team (p = 0.04). Significantly more factors related to pneumonia (p &lt; 0.001) and extubation readiness (p &lt; 0.01) were identified, and significantly more time was taken to complete the second simulation (p = 0.03). The simulation scenarios were described as realistic, and the cognitive aid was positively perceived.</div></div><div><h3>Conclusions</h3><div>The interprofessional cognitive aid had good usability and enhanced intensive care clinicians’ assessment, confidence, and communication about the extubation readiness of patients with acute cervical spinal cord injury.</div></div>","PeriodicalId":51239,"journal":{"name":"Australian Critical Care","volume":"38 3","pages":"Article 101206"},"PeriodicalIF":2.6,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Concerns about misquoted data in the systematic review and meta-analysis of closed versus open endotracheal suctioning by Liang Z et al.","authors":"Ryuhei Sato RN, PhD,&nbsp;Yusuke Kawai RN, MSN,&nbsp;Masaki Nakane MD, PhD","doi":"10.1016/j.aucc.2025.101220","DOIUrl":"10.1016/j.aucc.2025.101220","url":null,"abstract":"","PeriodicalId":51239,"journal":{"name":"Australian Critical Care","volume":"38 3","pages":"Article 101220"},"PeriodicalIF":2.6,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The effectiveness of a three-dimensional printed model for training novice healthcare professionals in central venous catheter insertion: Comment","authors":"Hinpetch Daungsupawong PhD,&nbsp;Viroj Wiwanitkit MD","doi":"10.1016/j.aucc.2025.101223","DOIUrl":"10.1016/j.aucc.2025.101223","url":null,"abstract":"","PeriodicalId":51239,"journal":{"name":"Australian Critical Care","volume":"38 3","pages":"Article 101223"},"PeriodicalIF":2.6,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Factors influencing the implementation and adherence to volume-based enteral feeding protocols in the critical care setting: A scoping review","authors":"Carolyn Hall MNutrDiet, APD ,&nbsp;Sophie Page MNutDiet, APD ,&nbsp;Noël Kelly NBSC, MDiet ,&nbsp;Karthika Kardaris BNutDiet(Hons), APD ,&nbsp;Lauren Hanna BNutrDiet, PhD, APD","doi":"10.1016/j.aucc.2025.101209","DOIUrl":"10.1016/j.aucc.2025.101209","url":null,"abstract":"<div><h3>Objective</h3><div>Delivery of enteral nutrition is an essential component of care for patients in the intensive care unit (ICU); however, patients only receive approximately 60% of prescribed enteral nutrition. Volume-based feeding (VBF) has been demonstrated as a safe and effective strategy to catch up for missed delivery of enteral nutrition. The aim of this review was to investigate factors influencing the adherence and implementation of VBF in the adult critical care and high-dependency unit settings to inform future implementation of VBF protocols in the ICU.</div></div><div><h3>Methods</h3><div>Systematic searches of databases (MEDLINE, EMBASE, and Emcare) and grey literature repositories (TROVE, TRIP, CPG Infobase, WorldCat, and Google) were conducted to identify original research studies including adults admitted to the ICU, where VBF or catch-up feeding protocols were in place. Studies reporting on barriers, enablers, and acceptability or adherence to VBF protocols were included.</div></div><div><h3>Results</h3><div>A total of 28 studies involving 7057 participants were eligible for inclusion, of which 19 were conducted in the USA, seven in Canada, one in the UK, and one in Australia. Factors enabling the implementation of VBF included management support, multidisciplinary team engagement, a project team, multimodal education, and communication strategies. Embedding the protocol into current work systems increased success. Barriers included a culture of deprioritising nutrition, safety concerns, staff turnover, and failure to embed the changes into work systems including the electronic medical record. VBF was considered acceptable to ICU staff; however, adherence to VBF protocols was variable (between 32.1% and 90%).</div></div><div><h3>Conclusion</h3><div>Successful implementation of a VBF protocol is enabled by strong project leadership, staff education, team engagement, and embedding VBF into current work processes. VBF is acceptable to staff; however, continuous education is recommended to sustain change in practice. Implementation of VBF should be considered as part of an “enhanced” feeding strategy in the ICU setting.</div></div><div><h3>Registration</h3><div>The protocol was developed and registered a priori on Open Science Framework on 8th August 2023 (<span><span>https://doi.org/10.17605/OSF.IO/8DJKY</span><svg><path></path></svg></span>).</div></div>","PeriodicalId":51239,"journal":{"name":"Australian Critical Care","volume":"38 3","pages":"Article 101209"},"PeriodicalIF":2.6,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prevalence and variability in use of physical restraints in intensive care units: A systematic review and meta-analysis","authors":"Akbar Zare-Kaseb MN ,&nbsp;Sogand Sarmadi MN ,&nbsp;Neda Sanaie PhD ,&nbsp;Amir Emami Zeydi PhD","doi":"10.1016/j.aucc.2025.101210","DOIUrl":"10.1016/j.aucc.2025.101210","url":null,"abstract":"<div><h3>Background</h3><div>Given the varying perspectives on the use of physical restraint (PR) over the past decades and the provided protocols to minimise its occurrence in intensive care units (ICUs), a comprehensive study was deemed necessary to examine the prevalence and variation of PR use in ICUs.</div></div><div><h3>Objective</h3><div>The aim of this study was to estimate the overall proportions of PR utilised in adult ICUs whilst examining the various factors contributing to the variability of these estimates.</div></div><div><h3>Methods</h3><div>A search of five databases (PubMed, Cochrane Library, Scopus, Embase, and Web of Science) was performed. Studies published in English and available online from inception to December 18, 2024, were included. A pooled estimate with a 95% confidence interval was calculated, and the data were represented by the random-effect model. Analysis was performed using the STATA statistical software (version 17).</div></div><div><h3>Results</h3><div>The meta-analysis included 39 studies, with a sample size of 21 665 patients. The overall prevalence of patients exposed to PRs was 41.6% (95% confidence interval: 33.8%–49.5%). The heterogeneity was significantly high (I² = 99.61%), and the Q Cochrane test for homogeneity was significant (p value &lt; 0.001), indicating substantial variability between studies. Subgroup analysis regarding the continent and restraint method contributed to a lowered heterogeneity.</div></div><div><h3>Conclusions</h3><div>There was considerable variation in reported estimates of PR prevalence in adult ICUs. Despite valid guidelines and recommendations supporting the reduction of PR, the results of our study show its significant prevalence. Additionally, our study demonstrated a relationship between PR use and delirium, sedation use, and mechanical ventilation. This study emphasises the importance of managing and focussing on PRs in ICUs. Also, it is crucial to evaluate barriers to guideline implementation.</div></div><div><h3>Registration</h3><div>The systematic review protocol has been prospectively registered in the International Prospective Register of Systematic Reviews: CRD42024566480.</div></div>","PeriodicalId":51239,"journal":{"name":"Australian Critical Care","volume":"38 3","pages":"Article 101210"},"PeriodicalIF":2.6,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143637508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of prophylactic non-invasive ventilation on weaning: A systematic review with meta-analysis","authors":"Helder B. Duarte PT ,&nbsp;Ueidson J.S. Batista PT, BPT ,&nbsp;Paula M. Oliveira PT, BPT ,&nbsp;Dimitri Gusmao-Flores MD, PhD ,&nbsp;Bruno P. Martinez PT, PhD","doi":"10.1016/j.aucc.2025.101199","DOIUrl":"10.1016/j.aucc.2025.101199","url":null,"abstract":"<div><h3>Objective</h3><div>The aim of this study was to evaluate the effects of prophylactic non-invasive ventilation (NIV) on reintubation, postextubation respiratory failure, length of stay (LOS), and mortality in the intensive care unit (ICU).</div></div><div><h3>Method</h3><div>A systematic review of the databases followed by meta-analysis was conducted. We included randomised or quasi-randomised clinical trials conducted in adults, with a mechanical ventilation time &gt;48 h, who had good performance in the spontaneous breathing test and compared the use of prophylactic NIV with oxygen supplementation.</div></div><div><h3>Results</h3><div>Eleven studies were included in this review. There was a difference in favour of prophylactic NIV for the outcome reintubation (odds ratio [OR]: 0.49; 95% confidence interval [CI]: 0.32, 0.74), ICU mortality (OR: 0.39; 95% CI: 0.21, 0.71), hospital mortality (OR: 0.53; 95% CI: 0.33, 0.85), ICU LOS (median [MD]: -2.86; 95% CI: −5.47, −0.24), and postextubation respiratory failure development (OR: 0.28; 95 % CI: 0.12, 0.67). There was no difference noted for hospital LOS (MD: -0 0.42; 95% CI: -3.42, 2.59). In the subgroup analysis, the use of rescue NIV, mainly in the control group, showed no statistically significant difference in the outcomes.</div></div><div><h3>Conclusion</h3><div>The use of prophylactic NIV reduced reintubation rates, ICU and hospital LOS, and mortality. These findings support the recommendation for its use in daily practice. Rescue NIV may have reduced the reintubation rate in control group who underwent the procedure.</div></div><div><h3>Prospero registration</h3><div>CRD42022381099.</div></div>","PeriodicalId":51239,"journal":{"name":"Australian Critical Care","volume":"38 3","pages":"Article 101199"},"PeriodicalIF":2.6,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143620237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Harnessing machine learning for predicting successful weaning from mechanical ventilation: A systematic review","authors":"Fatma Refaat Ahmed PhD, RN ,&nbsp;Nabeel Al-Yateem PhD, RN ,&nbsp;Seyed Aria Nejadghaderi MD, MPH ,&nbsp;Ahmad Rajeh Saifan PhD, RN, CNS ,&nbsp;Sally Mohammed Farghaly Abdelaliem PhD, RN, FHEA ,&nbsp;Mohannad Eid AbuRuz PhD, RN","doi":"10.1016/j.aucc.2025.101203","DOIUrl":"10.1016/j.aucc.2025.101203","url":null,"abstract":"<div><h3>Background</h3><div>Machine learning (ML) models represent advanced computational approaches with increasing application in predicting successful weaning from mechanical ventilation (MV). Whilst ML itself has a long history, its application to MV weaning outcomes has emerged more recently. In this systematic review, we assessed the effects of ML on the prediction of successful weaning outcomes amongst adult patients undergoing MV.</div></div><div><h3>Methods</h3><div>PubMed, EMBASE, Scopus, Web of Science, and Google Scholar electronic databases were searched up to May 2024. In addition, ACM Digital Library and IEEE Xplore databases were searched. We included peer-reviewed studies examining ML models for the prediction of successful MV in adult patients. We used a modified version of the Joanna Briggs Institute checklist for quality assessment.</div></div><div><h3>Results</h3><div>Eleven studies (n = 18 336) were included. Boosting algorithms, including extreme gradient boosting (XGBoost) and Light Gradient-Boosting Machine, were amongst the most frequently used methods, followed by random forest, multilayer perceptron, logistic regression, artificial neural networks, and convolutional neural networks, a deep learning model. The most common cross-validation methods included five-fold and 10-fold cross-validation. Model performance varied, with the artificial neural network accuracy ranging from 77% to 80%, multilayer perceptron achieving 87% accuracy and 94% precision, and convolutional neural network showing areas under the curve of 91% and 94%. XGBoost generally outperformed other models in the area under the curve comparisons. Quality assessment indicated that almost all studies had high quality as seven out of 10 studies had full scores.</div></div><div><h3>Conclusions</h3><div>ML models effectively predicted weaning outcomes in adult patients undergoing MV, with XGBoost outperforming other models. However, the absence of studies utilising newer architectures, such as transformer models, highlights an opportunity for further exploration and refinement in this field.</div></div>","PeriodicalId":51239,"journal":{"name":"Australian Critical Care","volume":"38 3","pages":"Article 101203"},"PeriodicalIF":2.6,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143579552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}