A Risk Prediction Model for Physical Restraints Among Older Chinese Adults in Long-term Care Facilities: Machine Learning Study.

BACKGROUND: Numerous studies have identified risk factors for physical restraint (PR) use in older adults in long-term care facilities. Nevertheless, there is a lack of predictive tools to identify high-risk individuals. OBJECTIVE: We aimed to develop machine learning (ML)-based models to predict the risk of PR in older adults. METHODS: This study conducted a cross-sectional secondary data analysis based on 1026 older adults from 6 long-term care facilities in Chongqing, China, from July 2019 to November 2019. The primary outcome was the use of PR (yes or no), identified by 2 collectors' direct observation. A total of 15 candidate predictors (older adults' demographic and clinical factors) that could be commonly and easily collected from clinical practice were used to build 9 independent ML models: Gaussian Naïve Bayesian (GNB), k-nearest neighbor (KNN), decision tree (DT), logistic regression (LR), support vector machine (SVM), random forest (RF), multilayer perceptron (MLP), extreme gradient boosting (XGBoost), and light gradient boosting machine (Lightgbm), as well as stacking ensemble ML. Performance was evaluated using accuracy, precision, recall, an F score, a comprehensive evaluation indicator (CEI) weighed by the above indicators, and the area under the receiver operating characteristic curve (AUC). A net benefit approach using the decision curve analysis (DCA) was performed to evaluate the clinical utility of the best model. Models were tested via 10-fold cross-validation. Feature importance was interpreted using Shapley Additive Explanations (SHAP). RESULTS: A total of 1026 older adults (mean 83.5, SD 7.6 years; n=586, 57.1% male older adults) and 265 restrained older adults were included in the study. All ML models performed well, with an AUC above 0.905 and an F score above 0.900. The 2 best independent models are RF (AUC 0.938, 95% CI 0.914-0.947) and SVM (AUC 0.949, 95% CI 0.911-0.953). The DCA demonstrated that the RF model displayed better clinical utility than other models. The stacking model combined with SVM, RF, and MLP performed best with AUC (0.950) and CEI (0.943) values, as well as the DCA curve indicated the best clinical utility. The SHAP plots demonstrated that the significant contributors to model performance were related to cognitive impairment, care dependency, mobility decline, physical agitation, and an indwelling tube. CONCLUSIONS: The RF and stacking models had high performance and clinical utility. ML prediction models for predicting the probability of PR in older adults could offer clinical screening and decision support, which could help medical staff in the early identification and PR management of older adults.

An Application of the Theory of Planned Behavior to Predict the Intention and Practice of Nursing Staff Toward Physical Restraint Use in Long-Term Care Facilities: Structural Equation Modeling.

PURPOSE: Understanding the factors that affect nursing staffs' intention and practice of physical restraint (PR) on older adults help develop restraint-reduction programs. This study aimed to identify the relationship between the Theory of Planned Behavior (TPB) constructs and nursing staffs' practice to use PR in long-term care (LTC) facilities. PATIENTS AND METHODS: A cross-sectional survey was conducted via convenience sampling among 316 nursing staff in six Chinese LTC facilities. PR-TPB questionnaire and the practice subscale of the Chinese version of the Staff Knowledge, Attitudes and Practices Questionnaire regarding PR were used to collect the data. Structural equation modeling (SEM) was used to examine the relationship between variables. RESULTS: The SEM fit well with the data (χ2/df =1.639, RMSEA = 0.045, CFI= 0.955, GFI=0.945). Attitude (ß=0.536, P<0.001) and perceived behavioral control (PBC) (ß=0.139, P<0.05) predicted intention (R2 =0.359). PBC was a significant predictor of practice, with R2 accounting for 0.151. CONCLUSION: TPB provided useful insight into better understanding nursing staffs' PR practices, although it did not support all the TPB principles significantly. Prospective studies may be conducted to design and implement multi-component interventions based on TPB and explore the effectiveness of PR reduction in LTC facilities in-depth.

The use of physical restraints in Chinese long-term care facilities and its risk factors: An observational and cross-sectional study.

AIM: To investigate the use of physical restraints among Chinese long-term care facilities older adults and to identify its risk factors. DESIGN: Observational and cross-sectional study. METHODS: A total of 1,026 older adults from six long-term care facilities in Chongqing were recruited by cluster sampling method from July - November 2019. Data on physical restraint use and older adults' characteristics were collected using physical restraints observation forms and older adults' records. Organizational data were collected by questionnaires asking nursing managers. The independent risk factors for physical restraints use were assessed using chi-square test and binary logistic regression. RESULTS: The study found that the prevalence of physical restraints in six long-term care facilities in China was 25.83%. Waist belt (55.47%) and wrist restraint (52.83%) were most frequently used. Only 61.51% of physical restraints were signed with informed consent. 71.70% of physical restraints were caused by the prevention of falls, 89.06% of physical restraints were without nursing documentation, and 13.58% restrained older adults were observed to have physical complications. According to the binary logistic regression analysis, facility type and ownership, older adults per nursing assistant, length of residence, cognitive impairment, care dependency, mobility restriction, fall risk, physical agitation, and indwelling tubes emerged as important risk factors for the use of physical restraints. CONCLUSION: The use of physical restraints among Chinese long-term care facilities older adults was at a relatively high level and lack standardized and regulated practices. Moreover, Physical restraint use was associated with facility type and ownership, older adults per nursing assistant, length of residence, cognitive impairment, care dependency, mobility restriction, fall risks, physical agitation, and indwelling tube. IMPACT: This study will provide an effective reference for nursing staff in long-term care facilities to assess high-risk older adults in their use of physical restraints, which can support them to implement effective minimized restraint approaches to targeted people.