Does electronic medical record redesign increase screening of risk for pressure injury, falls and substance use in the Emergency Department? An implementation evaluation

A machine learning algorithm-based predictive model for pressure injury risk in emergency patients: A prospective cohort study

OBJECTIVES

To construct pressure injury risk prediction models for emergency patients based on different machine learning algorithms, to optimize the best model, and to provide a suitable assessment tool for preventing the occurrence of pressure injuries in emergency patients.

METHODS

A convenience sampling was used to select 312 patients admitted to the emergency department of a tertiary care hospital in Tianjin, China, from May 2022 to March 2023, and the patients were divided into a modeling group (n = 218) and a validation group (n = 94) in a 7:3 ratio. Based on the results of one-factor logistic regression analysis in the modeling group, three machine learning models, namely, logistic regression, decision tree, and neural network, were used to establish a prediction model for pressure injury in emergency patients and compare their prediction effects. The optimal model was selected for external validation of the model.

RESULTS

The incidence of pressure injuries in emergency patients was 8.97 %, 64.52 % of pressure injuries occurred in the sacrococcygeal region, and 64.52 % were staged as stage 1. Serum albumin level, incontinence, perception, and mobility were independent risk factors for pressure injuries in emergency patients (P < 0.05), and the area under the ROC curve of the three models was 0.944-0.959, sensitivity was 91.8-95.5 %, specificity was 72.2-90.9 %, and the Yoden index was 0.677-0.802; the decision tree was the best model that The area under the ROC curve for the validation group was 0.866 (95 % CI: 0.688-1.000), with a sensitivity of 89.8 %, a specificity of 83.3 %, and a Yoden index of 0.731.

CONCLUSIONS

The decision tree model has the best predictive efficacy and is suitable for individualized risk prediction of pressure injuries in emergency medicine specialties, which provides a reference for the prevention and early intervention of pressure injuries in emergency patients.

Education interventions and emergency nurses' clinical practice behaviours: A scoping review

BACKGROUND

Many education interventions in emergency nursing are aimed at changing nurse behaviours. This scoping review describes and synthesises the published research education interventions and emergency nurses' clinical practice behaviours.

METHODS

Arksey and O'Malley's methodological framework guided this review, which is reported according to Preferred Reporting Items for Systematic reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR). CINAHL, MEDLINE complete, ERIC, and Psycinfo were searched on 3 August 2023. Two pairs of researchers independently conducted all screening. Synthesis was guided by the Behaviour Change Wheel and Bloom's Taxonomy of Educational Objectives.

RESULTS

Twenty-five studies were included. Educational interventions had largely positive effects on emergency nurses' clinical practice behaviours. Ten different interventions were identified, the most common was education sessions (n = 24). Seven studies reported underpinning theoretical frameworks. Of the essential elements of behaviour change, seven interventions addressed capability, four addressed motivation and one addressed opportunity. Mapping against Bloom's taxonomy, thirteen studies addressed analysis, eleven studies addressed synthesis and two studies addressed evaluation.

CONCLUSION

Few studies addressed elements of behaviour change theory or targeted cognitive domains. Future studies should focus on controlled designs, and more rigorous reporting of the education intervention(s) tested, and theoretical underpinning for intervention(s) selected.

Barriers and enablers to nurses' use of harm prevention strategies for older patients in hospital: A cross-sectional survey

BACKGROUND

Preventable harms during hospitalization pose a major challenge for health systems globally. Nurse-led strategies provide comprehensive harm prevention to keep the most vulnerable patients safe in hospital, but gaps in care are common. Nursing roles and activities to prevent harm to patients during acute hospitalization are poorly understood.

AIM

The aim of this study was to identify nurses' perceived enablers and barriers to the implementation of comprehensive harm prevention for older people admitted to an acute hospital setting.

DESIGN

Anonymous, online, cross-sectional survey.

METHODS

The adapted Influences on Patient Safety Behaviours Questionnaire (IPSBQ) was used to collect data from nurses working on five general medicine wards across three hospitals of a single tertiary health service in Australia in 2019. Participants also rated their perceptions of overall quality of care, missed care and awareness of strategies for an eight-factor framework for comprehensive harm prevention. The STROBE reporting checklist was used.

RESULTS

Ward response rates between 35% and 58% resulted in 132 complete questionnaires for analyses. High mean scores for behavioural regulation (3.28), beliefs about capabilities (2.96) and environmental context and resources (2.73) indicated these domains were perceived by nurses as enablers. Low mean scores for the domains of intentions (1.65), beliefs about consequences (1.69), optimism (1.72) and professional role and identity (1.85) indicated these were barriers to comprehensive harm prevention by nurses. High perceived quality of care (scored 9-10/10) (p = .024), and awareness of strategies for the eight-factor framework (p = .019) were significant enablers of comprehensive harm prevention.

CONCLUSION

Targeted evidence-based strategies that include education, persuasion, incentivization, coercion and modelling would be most useful for promoting comprehensive harm prevention by nurses. However, to be most effective the harm prevention strategy may need to be tailored for each ward.