Conectar
To develop a deep learning-based smart assessment model for pressure injury surface.
Exploratory analysis study.
Pressure injury images from four Guangzhou hospitals were labelled and used to train a neural network model. Evaluation metrics included mean intersection over union (MIoU), pixel accuracy (PA), and accuracy. Model performance was tested by comparing wound number, maximum dimensions and area extent.
From 1063 images, the model achieved 74% IoU, 88% PA and 83% accuracy for wound bed segmentation. Cohen's kappa coefficient for wound number was 0.810. Correlation coefficients were 0.900 for maximum length (mean difference 0.068 cm), 0.814 for maximum width (mean difference 0.108 cm) and 0.930 for regional extent (mean difference 0.527 cm2).
The model demonstrated exceptional automated estimation capabilities, potentially serving as a crucial tool for informed decision-making in wound assessment.
This study promotes precision nursing and equitable resource use. The AI-based assessment model serves clinical work by assisting healthcare professionals in decision-making and facilitating wound assessment resource sharing.
The STROBE checklist guided study reporting.
Patients provided image resources for model training.
The main aim of this study is to synthesize the prevalent predictive models for pressure injuries in hospitalized patients, with the goal of identifying common predictive factors linked to pressure injuries in hospitalized patients. This endeavour holds the potential to provide clinical nurses with a valuable reference for providing targeted care to high-risk patients.
Pressure injuries (PIs) are a frequently occurring health problem throughout the world. There are mounting studies about risk prediction model of PIs reported and published. However, the prediction performance of the models is still unclear.
Systematic review and meta-analysis: The Cochrane Library, PubMed, Embase, CINAHL, Web of Science and Chinese databases including CNKI (China National Knowledge Infrastructure), Wanfang Database, Weipu Database and CBM (China Biology Medicine).
This systematic review was conducted following PRISMA recommendations. The databases of Cochrane Library, PubMed, Embase, CINAHL, Web of Science, and CNKI, Weipu Database, Wanfang Database and CBM were searched for all studies published before September 2023. We included studies with cohort, case–control designs, reporting the development of risk model and have been validated externally and internally among the hospitalized patients. Two researchers selected the retrieved studies according to the inclusion and exclusion criteria, and critically evaluated the quality of studies based on the CHARMS checklist. The PRISMA guideline was used to report the systematic review and meta-analysis.
Sixty-two studies were included, which contained 99 pressure injuries risk prediction models. The AUC (area under ROC curve) of modelling in 32 prediction models were reported ranged from .70 to .99, while the AUC of verification in 38 models were reported ranged from .70 to .98. Gender (OR = 1.41, CI: .99 ~ 1.31), age (WMD = 8.81, CI: 8.11 ~ 9.57), diabetes mellitus (OR = 1.64, CI: 1.36 ~ 1.99), mechanical ventilation (OR = 2.71, CI: 2.05 ~ 3.57), length of hospital stay (WMD = 7.65, CI: 7.24 ~ 8.05) were the most common predictors of pressure injuries.
Studies of PIs risk prediction model in hospitalized patients had high research quality, and the risk prediction models also had good predictive performance. However, some of the included studies lacked of internal or external validation in modelling, which affected the stability and extendibility. The aged, male patient in ICU, albumin, haematocrit, low haemoglobin level, diabetes, mechanical ventilation and length of stay in hospital were high-risk factors for pressure injuries in hospitalized patients. In the future, it is recommended that clinical nurses, in practice, select predictive models with better performance to identify high-risk patients based on the actual situation and provide care targeting the high-risk factors to prevent the occurrence of diseases.
The risk prediction model is an effective tool for identifying patients at the risk of developing PIs. With the help of risk prediction tool, nurses can identify the high-risk patients and common predictive factors, predict the probability of developing PIs, then provide specific preventive measures to improve the outcomes of these patients.
CRD42023445258.
To investigate empirically the direct effect and potential mechanism of family resilience on patient-reported outcomes among young stroke dyads in China.
Young patients with stroke have been becoming an important public health issue. According to relevant theories and previous studies, we found that family resilience might play an important role in patient's symptoms. However, it is less clear about the specific relationship and potential mechanisms of these two variables.
We used a prospective cross-sectional design.
A multi-item questionnaire was used to assess the constructs of interest. Researchers progressively constructed and validated conditional process models. The PROCESS macro was used to verify the research hypotheses.
A total of 560 questionnaires were collected in this study. We found that family resilience of stroke patients and their spouses had a direct effect on the physical, psychological and social aspects of patient-reported symptoms. We further revealed that caregiver preparedness partially mediated the relationship between family resilience and patient's symptoms in stroke patient-spouse dyads, while perceived social support moderated the relationship between caregiver preparedness and patient's symptoms. Finally, we observed that the impact of caregiver readiness and social support on patients' symptoms predominantly manifested in physical and physiological outcomes.
Our research provides evidence about the positive impact of family resilience on patient-reported symptoms in young stroke dyads. Meanwhile, it further revealed how caregiver preparedness and perceived social support may play out in the relationship.
Our research introduces a novel perspective and pathway to enhance short-term recovery outcomes for patients. It also furnishes clinicians and nurses with evidence to guide the implementation of interventions aimed at improving patient health outcomes and facilitating smoother transitions from the hospital to home.
What problem did the study address?
Families play a crucial role in a patient's recovery process from illness, with family resilience serving as an important force for families to overcome adversity. However, the impact on patient symptoms and the underlying mechanisms of this relationship are uncertain. Empirical research is required to validate these aspects.
What were the main findings?
Family resilience has a positive impact on the physical, psychological and social aspects of patient-reported symptoms in young stroke dyads. Both the actor effect and partner effect are supported. The impact of caregiver readiness and social support on patient-reported symptoms is primarily observed in physical and physiological outcomes.
Where and on whom will the research have an impact?
This study offers a novel approach to enhance the short-term recovery of stroke patients. The researchers believe that the findings of this study will play an even more significant role during patients' transition from the hospital to home.
This study followed the STROBE statement of cross-sectional studies.
The study was conducted by patients, their spouses, healthcare professionals and the research team.
In 2015, the term ‘intrinsic capacity’ (IC) was proposed by the World Health Organisation to promote healthy aging. However, the factors associated with IC are still discrepant and uncertain.
We aim to synthesise the factors connected with IC.
This scoping review followed the five-stage framework of Arksey and O'Malley and was reported using PRISMA-ScR guidelines.
In all, 29 articles were included. IC of older adults is associated with demographic characteristics, socioeconomic factors, disease conditions, behavioural factors, and biomarkers. Age, sex, marital status, occupation status, education, income/wealth, chronic diseases, hypertension, diabetes, disability, smoking status, alcohol consumption, and physical activity were emerged as important factors related to the IC of older adults.
This review shows that IC is related to multiple factors. Understanding these factors can provide the healthcare personnel with the theoretical basis for intervening and managing IC in older adults.
The influencing factors identified in the review help to guide older adults to maintain their own intrinsic capacity, thereby promoting their health and well-being. The modifiable factors also provide evidence for healthcare personnel to develop targeted intervention strategies to delay IC decline.
As this is a scoping review, no patient or public contributions are required.
To evaluate the predictive validity and reliability of the Waterlow scale in critically adult hospitalised patients.
A multi-centre cohort study.
This study was conducted in 72 intensive care units (ICUs) in 38 tertiary hospitals in Gansu Province, China. All adults admitted to the ICU for greater than or equal to 24 h without pressure injury (PI) on admission were screened by the Waterlow scale on admission, during ICU stay and ICU discharge from April 2021 to February 2023. Receiver operating characteristic (ROC) curves were used to determine a potential cut-off value for critical adult hospitalised patients. Cut-off values were then determined using Youden's index, and sensitivity, specificity, positive predictive value, negative predictive value and accuracy were calculated based on these cut-off values. Test–retest reliability was used to evaluate inter-rater reliability.
A total of 5874 critical patients on admission were included, and 5125 of them were assessed regularly. The area under curve (AUC) was 0.623 (95% CI, 0.574–0.690), with a cut-off score of 19 showing the best balance among sensitivity of 62.7%, specificity of 57.4%, positive predictive value of 2.07% and negative predictive value of 99.08%. The test–retest reliability between the first assessment and the regular assessment was 0.447.
The Waterlow scale shows insufficient predictive validity and reliability in discriminating critical adults at risk of PI development. To further modify the items of the Waterlow scale, exploring specific risk factors for PI in the ICU and clarifying their impact degree was necessary. Risk predictive models or better tools are inevitable in the future.
Patients or family members supported nurses with PI risk assessment, skin examination and other activities during the inquiry.
FreshRSS