Explore the vast range of titles available.

Background Intensive care units (ICUs) face financial, bed management, and staffing constraints. Detailed data covering all aspects of patients’ journeys into and through intensive care are now collected and stored in electronic health records: machine learning has been used to analyse such data in order to provide decision support to clinicians. Methods Systematic review of the applications of machine learning to routinely collected ICU data. Web of Science and MEDLINE databases were searched to identify candidate articles: those on image processing were excluded. The study aim, the type of machine learning used, the size of dataset analysed, whether and how the model was validated, and measures of predictive accuracy were extracted. Results Of 2450 papers identified, 258 fulfilled eligibility criteria. The most common study aims were predicting complications (77 papers [29.8% of studies]), predicting mortality (70 [27.1%]), improving prognostic models (43 [16.7%]), and classifying sub-populations (29 [11.2%]). Median sample size was 488 (IQR 108–4099): 41 studies analysed data on > 10,000 patients. Analyses focused on 169 (65.5%) papers that used machine learning to predict complications, mortality, length of stay, or improvement of health. Predictions were validated in 161 (95.2%) of these studies: the area under the ROC curve (AUC) was reported by 97 (60.2%) but only 10 (6.2%) validated predictions using independent data. The median AUC was 0.83 in studies of 1000–10,000 patients, rising to 0.94 in studies of > 100,000 patients. The most common machine learning methods were neural networks (72 studies [42.6%]), support vector machines (40 [23.7%]), and classification/decision trees (34 [20.1%]). Since 2015 (125 studies [48.4%]), the most common methods were support vector machines (37 studies [29.6%]) and random forests (29 [23.2%]). Conclusions The rate of publication of studies using machine learning to analyse routinely collected ICU data is increasing rapidly. The sample sizes used in many published studies are too small to exploit the potential of these methods. Methodological and reporting guidelines are needed, particularly with regard to the choice of method and validation of predictions, to increase confidence in reported findings and aid in translating findings towards routine use in clinical practice.

IntroductionBrain injury is common following open heart valve surgery. Carbon dioxide insufflation (CDI) has been proposed to reduce the incidence of brain injury by reducing the number of air microemboli entering the bloodstream in surgery. The CO2 Study will evaluate the efficacy and safety of CDI in patients undergoing planned left-sided open heart valve surgery.Methods and analysisThe CO2 Study is a multicentre, blinded, placebo-controlled, randomised controlled trial. Seven-hundred and four patients aged 50 years and over undergoing planned left-sided heart valve surgery will be recruited to the study, from at least eight UK National Health Service hospitals, and randomised in a 1:1 ratio to receive CDI or medical air insufflation (placebo) in addition to standard de-airing. Insufflation will be delivered at a flow rate of 5 L/min from before the initiation of cardiopulmonary bypass until 10 min after cardiopulmonary bypass weaning. Participants will be followed up until 3 months post-surgery. The primary outcome is acute ischaemic brain injury within 10 days post-surgery based on new brain lesions identified with diffusion-weighted MRI or clinical evidence of permanent brain injury according to the current definition of stroke.Ethics and disseminationThe study was approved by the East Midlands–Nottingham 2 Research Ethics Committee in June 2020 and the Medicines and Healthcare products Regulatory Agency in May 2020. All participants will provide written informed consent prior to undertaking any study assessments. Consent will be obtained by the principal investigator or a delegated member of the research team who has been trained in the study and undergone Good Clinical Practice training. Results will be disseminated through peer-reviewed publications and presentations at national and international meetings. Study participants will be informed of results through study notifications and patient organisations.Trial registration numberISRCTN30671536.

Background Multiple corticosteroids and treatment regimens have been used as adjuncts in the treatment of septic shock. Qualitative and quantitative differences exist at cellular and tissular levels between the different drugs and their patterns of delivery. The objective of this study was to elucidate any differences between the drugs and their treatment regimens regarding outcomes for corticosteroid use in adult patients with septic shock. Methods Network meta-analysis of the data used for the recently conducted Cochrane review was performed. Studies that included children and were designed to assess respiratory function in pneumonia and acute respiratory distress syndrome, as well as cross-over studies, were excluded. Network plots were created for each outcome, and all analyses were conducted using a frequentist approach assuming a random-effects model. Results Complete data from 22 studies and partial data from 1 study were included. Network meta-analysis provided no clear evidence that any intervention or treatment regimen is better than any other across the spectrum of outcomes. There was strong evidence of differential efficacy in only one area: shock reversal. Hydrocortisone boluses and infusions were more likely than methylprednisolone boluses and placebo to result in shock reversal. Conclusions There was no clear evidence that any one corticosteroid drug or treatment regimen is more likely to be effective in reducing mortality or reducing the incidence of gastrointestinal bleeding or superinfection in septic shock. Hydrocortisone delivered as a bolus or as an infusion was more likely than placebo and methylprednisolone to result in shock reversal.

IntroductionIntensive care unit (ICU) delirium is an acute brain dysfunction that affects up to 7 out of 10 patients admitted to ICUs. Patients who develop ICU delirium cannot think clearly, have trouble paying attention, do not understand what is happening around them and may see or hear things that are not there. ICU delirium increases the time patients spend in ICUs and hospitals and therefore healthcare costs. ICU delirium is also associated with increased mortality and dementia in the longer term. ICU delirium prevention and management strategies are likely to include both pharmacological and non-pharmacological components as part of a complex intervention, but it is unclear which components should be included. The objective of this meta-review is to systematically map the quantity and certainty of the available evidence from reviews and meta-analyses of randomised controlled trials (RCTs) of pharmacological and non-pharmacological interventions, which will be used to design a multicomponent intervention to prevent and manage ICU delirium.Methods and analysisA systematic search strategy was performed in MEDLINE (Ovid), Embase (Elsevier), Cochrane Database of Systematic Reviews, Scopus, Cumulative Index to Nursing and Allied Health Literature (CINAHL), PsycINFO and Web of Science (from inception to 26 September 2023), as well as Epistemonikos (from inception to 19 July 2023). We will include all critically ill adults (aged≥18 years) and any ICU delirium prevention or management intervention (pharmacological or non-pharmacological). For pharmacological interventions, we will include reviews of RCTs. For non-pharmacological interventions, we will consider reviews of RCTs, quasi-experimental and cohort studies. We will use the International Consensus Study (Del-COrS) core outcome set for research evaluating interventions to prevent or manage ICU delirium and synthesise our findings using quantitative data description methods. We will involve our Patient and Public Involvement group of people who experienced ICU delirium to develop and comment on such aspects as the research question, methodology and which outcomes are most important.Ethics and disseminationNo ethical approval is required for this study. The results of this meta-review will be disseminated through peer-reviewed publications and conferences. They will also form part of an evidence map and logic model for the prevention and management of ICU delirium.PROSPERO registration numberCRD42023473260

Postoperative delirium (POD) is common. It is associated with increased morbidity and mortality. Many cases may be preventable and melatonin offers promise as a preventative agent.ObjectiveThis systematic review provides an up-to-date synthesis of the evidence on the effect of melatonin in preventing POD.DesignA systematic search of randomised controlled trials of melatonin in POD was run across multiple databases (EMBASE, MEDLINE, CINAHL, PsycINFO) and a clinical trials registry (ClinicalTrials.org) (1 January 1990 to 5 April 2022). Studies examining the effects of melatonin on POD incidence in adults are included. Risk of bias was assessed using the Cochrane risk of bias 2 tool.Outcome measuresThe primary outcome is POD incidence. Secondary outcomes are POD duration and length of hospital stay. Data synthesis was undertaken using a random-effects meta-analysis and presented using forest plots. A summary of methodology and outcome measures in included studies is also presented.ResultsEleven studies, with 1244 patients from a range of surgical specialties were included. Seven studies used melatonin, in variable doses, and four used ramelteon. Eight different diagnostic tools were used to diagnose POD. Time points for assessment also varied. Six studies were assessed as low risk of bias and five as some concern. The combined OR of developing POD in the melatonin groups versus control was 0.41 (95% CI 0.21 to 0.80, p=0.01).ConclusionThis review found that melatonin may reduce the incidence of POD in adults undergoing surgery. However, included studies displayed inconsistency in their methodology and outcome reporting. Further work to determine the optimum regime for melatonin administration, along with consensus of how best to evaluate results, would be beneficial.PROSPERO registration numberCRD42021285019.

Background The ProMPT-2 trial ( Pro pofol for M yocardial P rotection T rial #2) aims to compare the safety and efficacy of low- and high-dose propofol supplementation of the cardioplegia solution during adult cardiac surgery versus sham supplementation. This update presents the statistical analysis plan, detailing how the trial data will be analysed and presented. Outlined analyses are in line with the Consolidated Standards of Reporting Trials and the statistical analysis plan has been written prior to database lock and the final analysis of trial data to avoid reporting bias (following recommendations from the International Conference on Harmonisation of Good Clinical Practice). Methods/design ProMPT-2 is a multi-centre, blinded, parallel three-group randomised controlled trial aiming to recruit 240 participants from UK cardiac surgery centres to either sham cardioplegia supplementation, low dose (6 µg/ml) or high dose (12 µg/ml) propofol cardioplegia supplementation. The primary outcome is cardiac-specific troponin T levels (a biomarker of cardiac injury) measured during the first 48 h following surgery. The statistical analysis plan describes the planned analyses of the trial primary and secondary outcomes in detail, including approaches to deal with missing data, multiple testing, violation of model assumptions, withdrawals from the trial, non-adherence with the treatment and other protocol deviations. It also outlines the planned sensitivity analyses and exploratory analyses to be performed. Discussion This manuscript prospectively describes, prior to the completion of data collection and database lock, the analyses to be undertaken for the ProMPT-2 trial to reduce risk of reporting and data-driven analyses. Trial registration ISRCTN ISRCTN15255199. Registered on 26 March 2019.

IntroductionDelirium is a common and serious condition that frequently affects patients in the intensive care unit (ICU). It is characterised by an acute disturbance in cognition, attention and awareness that develops over a short period of time and tends to fluctuate in severity. Patients with ICU delirium (ICUD) may experience confusion, disorientation, difficulty focusing and perceptual disturbances such as hallucinations or delusions. The prevalence of ICUD is high, with estimates suggesting that it can affect up to 70% of ICU patients. The development of ICUD is associated with several adverse outcomes, including prolonged ICU and hospital stays, increased healthcare costs, higher mortality rates and an increased risk of long-term cognitive impairment, including dementia. It is unclear which components should be included in a complex intervention to prevent and manage ICUD. Furthermore, we need to understand how the different components have been implemented and their impact on clinical practice.Methods and analysisThe review will be reported according to the Preferred Reporting Items for Systematic reviews and Meta-Analysis Protocols (PRISMA-P) and the enhancing transparency in reporting the synthesis of qualitative research (ENTREQ) reporting recommendations. We will perform systematic searches to identify relevant interventions and implementation strategies for the prevention or management of ICUD. We will assess primary research, service evaluations and audits for the use of the Standards for QUality Improvement Reporting Excellence (SQUIRE) as a checklist for quality improvement in healthcare. We will extract both qualitative and quantitative data and assess study quality using the Critical Appraisal Skills Programme (CASP) tool. Our findings will be synthesised using a best-fit framework synthesis mapped against the Theoretical Domains Framework (TDF). Our Patient and Public Involvement (PPI) group will contribute to the development of review processes such as the research question and methodology and will help to evaluate which outcomes are most important.Ethics and disseminationNo ethical approval is required for this study. The results of this systematic review of implementation strategies will be disseminated through peer-reviewed publications and conferences. They will also form part of an evidence map and logic model for factors that can improve the implementation of strategies for prevention, identification and management of ICUD.PROSPERO registration numberCRD42024537313.

IntroductionDelirium is a syndrome characterised by a disturbance in attention, awareness and cognition as a result of another physical condition. It occurs in up to 50% of patients after cardiac surgery and is associated with increased mortality, prolonged intensive care and hospital stay and long-term cognitive dysfunction. Identifying effective preventive interventions is important. We will therefore conduct a systematic review to identify all randomised controlled studies that have tested a pharmacological or non-pharmacological intervention to prevent delirium.Methods and analysisWe will search electronic databases (CDSR (Reviews), CENTRAL (Trials), MEDLINE Ovid, Embase Ovid, PsycINFO Ovid) as well as trial registers (clinicaltrials.gov and ISCRTN) for randomised controlled trials of both pharmacological and non-pharmacological interventions designed to prevent delirium after cardiac surgery in adults. Screening of search results and data extraction from included articles will be performed by two independent reviewers using Rayyan. The primary outcome will be the incidence of delirium. Secondary outcomes include: duration of postoperative delirium, all-cause mortality, length of postoperative hospital and intensive care stay, postoperative neurological complications other than delirium, health-related quality of life and intervention-specific adverse events. Studies will be assessed for risk of bias using the Cochrane RoB2 tool. A narrative synthesis of all included studies will be presented and meta-analysis (if appropriate network meta-analysis) will be undertaken where there are sufficient studies (three or more) for pooling results. Results will be reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement.Ethics and disseminationNo ethical approval is required. This review will be disseminated via peer-reviewed manuscript and conferences.PROSPERO registration numberCRD42022369068.

ObjectiveTo model the referral, diagnostic and treatment pathway for cardiovascular disease (CVD) in the English National Health Service (NHS) to provide commissioners and managers with a methodology to optimise patient flow and reduce waiting lists.Study designA systems dynamics approach modelling the CVD healthcare system in England. The model is designed to capture current and predict future states of waiting lists.SettingRoutinely collected, publicly available data streams of primary and secondary care, sourced from NHS Digital, NHS England, the Office of National Statistics and StatsWales.Data collection and extraction methodsThe data used to train and validate the model were routinely collected and publicly available data. It was extracted and implemented in the model using the PySD package in python.ResultsNHS cardiovascular waiting lists in England have increased by over 40% compared with pre- COVID-19 levels. The rise in waiting lists was primarily due to restrictions in referrals from primary care, creating a bottleneck postpandemic. Predictive models show increasing point capacities within the system may paradoxically worsen downstream flow. While there is no simple rate-limiting step, the intervention that would most improve patient flow would be to increase consultant outpatient appointments.ConclusionsThe increase in NHS CVD waiting lists in England can be captured using a systems dynamics approach, as can the future state of waiting lists in the presence of further shocks/interventions. It is important for those planning services to use such a systems-oriented approach because the feed-forward and feedback nature of patient flow through referral, diagnostics and treatment leads to counterintuitive effects of interventions designed to reduce waiting lists.