
ABSTRACT Aims This study aimed to develop a predictive model for diabetes self‐management (DSM) using a fully connected neural network (FCNN) architecture. The model's performance was rigorously evaluated using key metrics, including accuracy, precision, recall, and the area under the receiver operating characteristic curve (AUC‐ROC). Design A quantitative, multicenter cross‐sectional design. Methods A systematic literature review identified key psychosocial factors and corresponding validated scales, which formed the initial item pool. A multicenter cross‐sectional study was then conducted to collect data on these items from 2005 participants across five research centers in Hainan, Zhejiang, Jiangsu, and Henan provinces. We chose to develop an FCNN model over traditional approaches including logistic regression and random forest, as it could automatically capture complex, non‐linear relationships among predictors without manual feature engineering. Using this model for gradient‐based feature importance ranking, we selected the most predictive items from the initial pool following preliminary screening of overlapping items. After feature selection, the model was retrained using the selected features, with 80% of the data allocated for training and 20% for testing. Finally, model performance was validated through a two‐week prospective observational study. Results Twenty‐four out of 99 candidate variables were identified as model characteristics for predicting DSM behaviours. The model demonstrated strong performance across all four self‐management domains. For healthy eating, the accuracy, precision, recall, and AUC were 83.34%, 88.56%, 90.05%, and 0.84%, respectively. For medication adherence, these values were 82.14%, 86.60%, 90.27%, and 0.84%, respectively. For regular exercise, they were 82.39%, 82.89%, 86.09%, and 0.89%, respectively. For blood glucose monitoring, they were 83.39%, 85.45%, 89.72%, and 0.87%, respectively. The prospective validation cohort ( n = 50) further confirmed the model's robust performance, yielding AUCs of 0.84, 0.82, 0.83, and 0.89 for diet, exercise, blood glucose monitoring, and medication adherence, respectively. Conclusion The FCNN‐based predictive model demonstrated promising performance in forecasting DSM behaviours, with particularly strong discriminative ability as evidenced by high accuracy and AUC values. These findings suggest that deep learning approaches incorporating psychosocial and clinical variables may help predict DSM behaviours, although the model requires further validation before it can be considered a clinical tool for personalized diabetes care. Although the prospective validation results are encouraging, they should be interpreted as preliminary given the limited sample size ( n = 50); larger‐scale, multicenter external validation studies are warranted to further confirm the model's generalizability and clinical applicability. Impact Predicting core diabetes self‐management behaviours using an FCNN may provide useful insights into individualized adherence patterns and could inform targeted, stepped‐care interventions, although further validation is needed before clinical application. Reporting Method The reporting of this cross‐sectional study followed the STROBE guideline. Patient or Public Contribution Patients with Type 2 diabetes mellitus contributed to this study by completing questionnaires during the model development phase ( n = 2005) and by participating in the prospective validation phase ( n = 50). No patients or public members were involved in study design, data analysis, or interpretation of results. Study findings will be disseminated to participants through their respective endocrinology departments.
ABSTRACT Aims To identify the sociodemographic and clinical factors associated with adherence to blood pressure‐lowering treatment and with illness acceptance in adults with hypertension attending specialist outpatient care. Design Single‐centre cross‐sectional study. Methods We studied 229 adults with physician‐diagnosed hypertension attending routine follow‐up visits at a specialist hypertension clinic. Adherence was measured with the Hill‐Bone Compliance to High Blood Pressure Therapy Scale and illness acceptance with the Acceptance of Illness Scale (AIS). Two multivariable linear regression models with the same 11 sociodemographic and clinical predictors were fitted. Reporting Method STROBE. Results Treatment adherence and illness acceptance were moderately correlated. Medication burden was the only factor independently associated with both poorer treatment adherence and lower illness acceptance. Better adherence was also associated with a higher number of comorbidities, rural residence, and a family history of hypertension, although the latter two associations were less robust after adjustment for multiple testing. Patients with the highest medication burden had the poorest adherence and the lowest illness acceptance. Conclusion Adherence and illness acceptance are related but distinct aspects of living with hypertension. The number of medications was the only factor independently associated with both outcomes, suggesting that medication burden should be considered in individualised care. Implications for the Profession and/or Patient Care Assessing adherence and illness acceptance together may help nurses to separate patients who need education about their treatment from those who need psychological support or a simpler regimen. Impact Adherence and illness acceptance had different determinant profiles in patients with hypertension, with medication burden as the only factor common to both. The findings support individualised nursing assessment and multidisciplinary management of hypertension. Patient or Public Contribution Patients completed validated questionnaires and provided clinical information during routine outpatient visits. They were not involved in the study design, data analysis, interpretation or manuscript preparation.
ABSTRACT Aim To investigate how preventive home visits, and return visits by the same healthcare worker, were associated with mobility, nursing home admission, and mortality among older adults. Design Observational cohort study. Methods Self‐report of preventive home visits and mobility. Nursing home admission and mortality were register‐based. Multivariable logistic regression models with generalized estimating equations. Data Sources The Danish Intervention Study on Preventive Home Visits. Results About half received one or more preventive home visits. The majority had return visits from the same healthcare worker. There were no significant associations between number of visits and return visits, and nursing home admission and mortality, respectively. Compared to receiving multiple preventive home visits by different healthcare workers, receiving no visits was significantly associated with lower odds of mobility limitations. A tendency to better mobility was observed when receiving return visits by the same healthcare worker, but statistically insignificant. Conclusion While a continuous relation to the healthcare worker did not show a significant advantage over intermittent relation, the other results are consistent with healthy user‐bias, suggesting that pre‐existing health drives the observed pattern of receiving preventive home visits. Implications for the Profession and Patient Care A continuous relation to the healthcare worker may potentially benefit those at risk of functional limitations. Impact Heterogeneous findings in previous studies may stem from variations in frequency and content of visits, which are rarely studied. Multi‐disciplinary studies on organization, frequency, and evaluation of preventive home visits are needed. Reporting Method This study was reported in accordance with STROBE guidelines for cohort studies. Patient of Public Contribution No patient of public contribution.
ABSTRACT Aim To explore the illness experience and meaning‐making of patients with pulmonary arterial hypertension from diagnosis to adaptation. Design A qualitative study using a Heideggerian hermeneutic phenomenological design. Methods From July to December 2025, purposive sampling recruited 12 adults with PAH from a teaching hospital in northern Taiwan. Semi‐structured interviews were conducted, with data collection and analysis occurring concurrently. Transcripts were read, compared, and interpreted through the hermeneutic circle, supported by field notes and reflexive notes. Results Six interrelated themes and 15 categories were identified: (1) Cycles of hope and disappointment; (2) Physical decline and disruption to daily life after disease onset; (3) Waiting on the edge of collapse; (4) Information gaps and unmet information needs; (5) Rediscovering possibilities for living; and (6) Finding a place in life within the limits of the disease. Patients experienced diagnostic delays, physical decline, treatment waiting, and information gaps. As treatment stabilised, they shifted from hoping to return to pre‐illness lives to adjusting expectations, roles, and attitudes and engaging in disease management. Adaptation was an ongoing process. Conclusion Participants' retrospective accounts suggest that adaptation to PAH involves more than accepting the illness. Patients continuously reinterpret the illness, themselves, and their future amid physical and daily‐life changes. Family, peers, and healthcare professionals support hope and adaptation. Implications for the Profession and/or Patient Care Care for pulmonary arterial hypertension should extend beyond disease control and symptom management. Nurses can support patients through case management, information, and family and peer support across illness stages. Impact This study highlights illness adaptation as a continuous process of adjusting perspectives on illness, self, and future, suggesting that care for PHA should address patients' long‐term lives alongside disease management. Reporting Method This study was reported in accordance with the COREQ guidelines. Patient or Public Contribution No patient or public contribution.
ABSTRACT Aim This cross‐sectional correlational study aimed to develop a structural equation model (SEM) to elucidate the associations among stressors, family functioning, family resilience and family adaptation in maintenance haemodialysis (MHD) patients. Background The stress burden experienced by patients undergoing MHD has received increasing attention. Stressors may adversely affect family adaptation, making the adaptation process more complex. However, evidence regarding the factors associated with family adaptation among patients undergoing MHD remains limited. Design A cross‐sectional study. Methods A total of 412 patients with MHD were recruited from December 2023 and July 2024 at three hospitals in Hunan Province. Data on stressors, family functioning, family resilience and family adaptation were collected using the haemodialysis stressor scale, APGAR, Shortened Chinese version of the family resilience assessment scale, and the Chinese version of the family adaptability and cohesion evaluation scales. SEM was employed to test the study's hypotheses. This study was reported in accordance with STROBE guidelines. Results The findings revealed that stressors were negatively associated with family functioning, family resilience and family adaptation. Stressors demonstrated an indirect relationship with family adaptation through family functioning and family resilience. Conclusions This study identified the structural relationships among the four variables under investigation. Family functioning and family resilience were found to be potential mediators in the association between stressors and family adaptation. Relevance to Clinical Practice Stressors are an important concern for patients undergoing MHD. Given the associations observed among stressors, family functioning, family resilience and family adaptation in this study, nephrology nurses may consider both patients' individual needs and their perceptions of family‐related factors when assessing adaptation to long‐term dialysis, rather than focusing exclusively on individual patient needs. In routine nephrology nursing practice, assessment of stressors and family‐related factors may help nurses identify patients who may require additional family‐oriented support and facilitate communication with patients and their families. These findings may provide a basis for developing more targeted, evidence‐informed approaches to support patients and their families, while further intervention studies are needed to determine the effectiveness of such approaches. Patient or Public Contribution No patient or public contribution.