Accuracy of Machine Learning Models to Predict In-hospital Cardiac Arrest: A Systematic Review.

PURPOSE/AIMS: Despite advances in healthcare, the incidence of in-hospital cardiac arrest (IHCA) has continued to rise for the past decade. Identifying those patients at risk has proven challenging. Our objective was to conduct a systematic review of the literature to compare the IHCA predictive performance of machine learning (ML) models with the Modified Early Warning Score (MEWS). DESIGN: The systematic review was conducted following the Preferred Reporting Items of Systematic Review and Meta-Analysis guidelines and registered on PROSPERO CRD42020182357. METHOD: Data extraction was completed using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies checklist. The risk of bias and applicability were evaluated using the Prediction model Risk of Bias Assessment Tool. RESULTS: Nine articles were included in this review that developed or validated IHCA prediction models and compared them with the MEWS. The studies by Jang et al and Kim et al showed that their ML models outperformed MEWS to predict IHCA with good to excellent predictive performance. CONCLUSIONS: The ML models presented in this systematic review demonstrate a novel approach to predicting IHCA. All included studies suggest that ML models had similar or better predictive performance compared with MEWS. However, there is substantial variability in performance measures and concerns for risk of bias.

Strategies to promote the implementation of Screening, Brief Intervention, and Referral to Treatment (SBIRT) in healthcare settings: a scoping review.

BACKGROUND: Screening, brief intervention, and referral to treatment (SBIRT), is an approach for the prevention and treatment of substance use disorders, but is often underutilized in healthcare settings. Although the implementation of SBIRT is challenging, the use of multi-faceted and higher intensity strategies are more likely to result in the successful incorporation of SBIRT into practice in primary care settings. SBIRT may be used in different healthcare settings, and the context for implementation and types of strategies used to support implementation may vary by setting. The purpose of this scoping review is to provide an overview regarding the use of strategies to support implementation of SBIRT in all healthcare settings and describe the associated outcomes. METHODS: A scoping review was conducted using CINAHL Complete, HealthBusiness FullTEXT, PsycINFO, PubMed, and Embase to search for articles published in English prior to September 2019. The search returned 462 citations, with 18 articles included in the review. Two independent reviewers extracted data from each article regarding the theory, design, timeline, location, setting, patient population, substance type, provider, sample size and type, implementation strategies, and implementation outcomes. The reviewers entered all extracted data entered into a table and then summarized the results. RESULTS: Most of the studies were conducted in the United States in primary care or emergency department settings, and the majority of studies focused on SBIRT to address alcohol use in adults. The most commonly used strategies to support implementation included training and educating stakeholders or developing stakeholder interrelationships. In contrast, only a few studies engaged patients or consumers in the implementation process. Efforts to support implementation often resulted in an increase in screening, but the evidence regarding the brief intervention is less clear, and most studies did not assess the reach or adoption of the referral to treatment. DISCUSSION: In addition to summarizing the strategies used to increase reach and adoption of SBIRT in healthcare settings, this scoping review identified multiple gaps in the literature. Two major gaps include implementation of SBIRT in acute care settings and the application of implementation theories to inform healthcare efforts to enable use of SBIRT.

Development and use of a toolkit to facilitate implementation of an evidence-based intervention: a descriptive case study.

BACKGROUND: Implementation of evidence-based clinical interventions in real-world settings becomes a futile effort when effective strategies to foster adoption are not used. A toolkit, or a collection of adaptable documents to inform and facilitate implementation, can increase the use of evidence-based interventions. Most available toolkits provide resources about the intervention but lack guidance for adaptation to different contexts or strategies to support implementation. This paper describes the development and use of a toolkit to guide the implementation of an evidence-based intervention to identify and intervene for people with risky substance use. METHODS: A descriptive case study describes the development and use of a toolkit throughout a two-year study. Investigators and site coordinators from 14 acute care hospitals developed tools and engaged external stakeholders as they prepared for implementation, integrated the clinical intervention into practice, and reflected on implementation. RESULTS: The final toolkit included 54 different tools selected or created to define the intervention, engage and communicate with stakeholders, assess for readiness and plan for implementation, train clinical nurses and other stakeholders, evaluate training and implementation effectiveness, create policies and procedures for different contexts, and identify opportunities for reimbursement. Each tool corresponds to one or more implementation strategies. CONCLUSION: The approach used to develop this implementation toolkit may be used to create resources for the implementation of other evidence-based interventions.

The conserved transmembrane RING finger protein PLR-1 downregulates Wnt signaling by reducing Frizzled, Ror and Ryk cell-surface levels in C. elegans.

Wnts control a wide range of essential developmental processes, including cell fate specification, axon guidance and anteroposterior neuronal polarization. We identified a conserved transmembrane RING finger protein, PLR-1, that governs the response to Wnts by lowering cell-surface levels of the Frizzled family of Wnt receptors in Caenorhabditis elegans. Loss of PLR-1 activity in the neuron AVG causes its anteroposterior polarity to be symmetric or reversed because signaling by the Wnts CWN-1 and CWN-2 are inappropriately activated, whereas ectopic PLR-1 expression blocks Wnt signaling and target gene expression. Frizzleds are enriched at the cell surface; however, when PLR-1 and Frizzled are co-expressed, Frizzled is not detected at the surface but instead is colocalized with PLR-1 in endosomes. The Frizzled cysteine-rich domain (CRD) and invariant second intracellular loop lysine are crucial for PLR-1 downregulation. The PLR-1 RING finger and protease-associated (PA) domain are essential for activity. In a Frizzled-dependent manner, PLR-1 reduces surface levels of the Wnt receptors CAM-1/Ror and LIN-18/Ryk. PLR-1 is a homolog of the mammalian transmembrane E3 ubiquitin ligases RNF43 and ZNRF3, which control Frizzled surface levels in an R-spondin-sensitive manner. We propose that PLR-1 downregulates Wnt receptor surface levels via lysine ubiquitylation of Frizzled to coordinate spatial and temporal responses to Wnts during neuronal development.