Department of Nursing, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China.
Department of Gynecology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China.
J Med Internet Res. 2023 Apr 6;25:e43815. doi: 10.2196/43815.
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.
We aimed to develop machine learning (ML)-based models to predict the risk of PR in older adults.
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).
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.
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.
大量研究已经确定了长期护理机构中老年人身体约束（PR）使用的风险因素。然而，缺乏预测工具来识别高风险个体。
我们旨在开发基于机器学习（ML）的模型来预测老年人 PR 的风险。
本研究基于 2019 年 7 月至 11 月期间来自中国重庆 6 家长期护理机构的 1026 名老年人进行了横断面二次数据分析。主要结局是使用 PR（是或否），由 2 名收集器通过直接观察确定。使用了 15 个可能的预测因子（老年人的人口统计学和临床因素），这些预测因子可以从临床实践中常见且易于收集，用于构建 9 个独立的 ML 模型：高斯朴素贝叶斯（GNB）、k-最近邻（KNN）、决策树（DT）、逻辑回归（LR）、支持向量机（SVM）、随机森林（RF）、多层感知机（MLP）、极端梯度提升（XGBoost）和轻梯度提升机（Lightgbm），以及堆叠集成 ML。使用准确性、精度、召回率、F 分数、由上述指标加权的综合评估指标（CEI）和接收器工作特征曲线下的面积（AUC）来评估性能。使用决策曲线分析（DCA）进行净收益方法评估最佳模型的临床实用性。通过 10 折交叉验证测试模型。使用 Shapley 加性解释（SHAP）解释特征重要性。
共纳入 1026 名老年人（平均 83.5 岁，标准差 7.6 岁；n=586，57.1%为男性老年人）和 265 名约束老年人。所有 ML 模型表现良好，AUC 均高于 0.905，F 分数均高于 0.900。2 个最佳独立模型是 RF（AUC 0.938，95%CI 0.914-0.947）和 SVM（AUC 0.949，95%CI 0.911-0.953）。DCA 表明 RF 模型比其他模型具有更好的临床实用性。结合 SVM、RF 和 MLP 的堆叠模型表现最佳，AUC（0.950）和 CEI（0.943）值以及 DCA 曲线均表明最佳的临床实用性。SHAP 图表明，对模型性能有重大贡献的因素与认知障碍、护理依赖、活动能力下降、身体躁动和留置管有关。
RF 和堆叠模型具有较高的性能和临床实用性。用于预测老年人 PR 概率的 ML 预测模型可为临床筛查和决策支持提供帮助，有助于医务人员早期识别和 PR 管理老年人。
