Conectar
To identify different longitudinal trajectories of hypoglycaemia problem-solving ability in patients with diabetes mellitus (DM) and explore their predictive factors. To examine the impact of these heterogeneous trajectories on quality of life.
This study adopted a prospective longitudinal design.
A total of 272 patients who completed follow-up were longitudinally assessed for their hypoglycaemia problem-solving abilities over 6 months. Latent class growth modelling (LCGM) was used to identify heterogeneous trajectories of hypoglycaemia problem-solving ability. Multiple logistic regression was conducted to determine predictors, while univariate ANOVA and multiple linear regression analysis were applied to explore the effects of heterogeneous trajectories on quality of life.
The overall level of hypoglycaemia problem-solving ability in DM patients increased from hospitalisation to 1 month after discharge and gradually decreased from 3 to 6 months after discharge. LCGM identified three heterogeneous trajectories of hypoglycaemia problem-solving ability. Results of multinomial logistic regression analysis showed that employment status, monthly income, frequency of blood glucose monitoring, fear of hypoglycaemia, and social support were predictors of heterogeneous trajectories of hypoglycaemia problem-solving ability in DM patients. In addition, hypoglycaemia problem-solving ability positively predicts quality of life.
Our findings establish a critical theoretical foundation for designing and implementing effective interventions tailored to patients' distinct trajectories in diabetes management.
This study explores the trajectories and predictors of hypoglycaemia problem-solving abilities in DM patients, providing a theoretical basis for nurses to guide patients in diabetes management.
Research findings indicate that nurses should regularly assess the hypoglycaemia problem-solving abilities in DM patients, and use trajectory subgroups to identify distinct patient characteristics in hypoglycaemia problem-solving abilities in order to implement personalised interventions.
This study was based on the STROBE guideline.
No patient or public engagement.
To develop and validate a machine learning-based risk prediction model for delirium in older inpatients.
A prospective cohort study.
A prospective cohort study was conducted. Eighteen clinical features were prospectively collected from electronic medical records during hospitalisation to inform the model. Four machine learning algorithms were employed to develop and validate risk prediction models. The performance of all models in the training and test sets was evaluated using a combination of the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, Brier score, and other metrics before selecting the best model for SHAP interpretation.
A total of 973 older inpatient data were utilised for model construction and validation. The AUC of four machine learning models in the training and test sets ranged from 0.869 to 0.992; the accuracy ranged from 0.931 to 0.962; and the sensitivity ranged from 0.564 to 0.997. Compared to other models, the Random Forest model exhibited the best overall performance with an AUC of 0.908 (95% CI, 0.848, 0.968), an accuracy of 0.935, a sensitivity of 0.992, and a Brier score of 0.053.
The machine learning model we developed and validated for predicting delirium in older inpatients demonstrated excellent predictive performance. This model has the potential to assist healthcare professionals in early diagnosis and support informed clinical decision-making.
By identifying patients at risk of delirium early, healthcare professionals can implement preventive measures and timely interventions, potentially reducing the incidence and severity of delirium. The model's ability to support informed clinical decision-making can lead to more personalised and effective care strategies, ultimately benefiting both patients and healthcare providers.
This study was reported in accordance with the TRIPOD statement.
No patient or public contribution.
FreshRSS 