Conectar
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.
To construct and evaluate a novel nomogram for predicting the risk of dual dimensional frailty (comorbidity between physical frailty and social frailty) in older maintenance haemodialysis.
A cross-sectional investigation was conducted. A total of 386 older MHD patients were recruited between September and December 2024 from four haemodialysis centres in four tertiary hospitals in Sichuan Province, China. LASSO regression and binary logistic regression were employed to determine the predictors of dual dimensional frailty. The prediction performance of the model was evaluated by discrimination and calibration. The decision curve was utilised to estimate the clinical utility. Internal validation with 1000 bootstrap samples was conducted to minimise overfitting.
In the overall sample (386 cases), a total of 92 (23.8%) of patients exhibited dual dimensional frailty. Five relevant predictors, including physical activity, self-perceived health status, ADL impairment, malnutrition, and self-perceptions of aging, were identified for constructing the nomogram. Internal validation indicated excellent discriminatory power and calibration of the model, while the clinical decision curve demonstrated its remarkable clinical utility.
The novel nomogram constructed in this study holds promise for aiding healthcare professionals in identifying physical and social frailty risks among older patients on maintenance haemodialysis, potentially informing early and targeted interventions.
This nomogram enables nurses to efficiently stratify dual-dimensional frailty risk during routine assessments, facilitating early identification of high-risk patients. Its visual output can guide tailored interventions, such as exercise programmes, nutritional support, and counselling, while optimising resource allocation.
Data were collected from self-reported conditions and patients' clinical information.
STROBE checklist was employed.
FreshRSS 