González-Castro Ana, Benítez-Andrades José Alberto, González-González Rubén, Prada-García Camino, Leirós-Rodríguez Raquel
Nursing and Physical Therapy Department, Universidad de León, Ponferrada, Spain.
SALBIS Research Group, Department of Electric, Systems and Automatics Engineering, Universidad de León, León, Spain.
Digit Health. 2025 Mar 28;11:20552076251331752. doi: 10.1177/20552076251331752. eCollection 2025 Jan-Dec.
Accurate prediction of fall risk in older adults is essential to prevent injuries and improve quality of life. This study evaluates the predictive performance of various machine learning models using accelerometric data, non-accelerometric data, aiming to improve predictive accuracy and identify key contributing variable.
We applied random forest, XGBoost, AdaBoost, LightGBM, support vector regression (SVR), decision trees, and Bayesian ridge regression to a dataset of 146 older adults. Models were trained using accelerometric data (movement patterns) and non-accelerometric data (demographic and clinical variables). Performance was evaluated based on mean squared error (MSE) and coefficient of determination ( ), to assess how combining multiple data types influences prediction accuracy.
Models trained on combined accelerometric and non-accelerometric data consistently outperformed those based on single data types. Bayesian ridge regression achieved the highest accuracy (MSE = 0.6746, = 0.9941), demonstrating superior performance compared to decision trees (MSE = 0.1907, = 0.8991) and SVR (MSE = 1.5243, = 2.2532). Non-accelerometric factors, including age and comorbidities, significantly contributed to fall risk prediction.
Integrating accelerometric and non-accelerometric data improves fall risk prediction accuracy in older adults. Bayesian ridge regression trained on combined datasets provides superior predictive power compared to traditional models. These findings highlight the importance of multi-source data fusion for effective fall prevention strategies. Future work should validate these models in larger, more diverse populations to enhance clinical applicability.
准确预测老年人的跌倒风险对于预防伤害和提高生活质量至关重要。本研究使用加速度计数据和非加速度计数据评估各种机器学习模型的预测性能，旨在提高预测准确性并识别关键影响变量。
我们将随机森林、XGBoost、AdaBoost、LightGBM、支持向量回归（SVR）、决策树和贝叶斯岭回归应用于146名老年人的数据集。使用加速度计数据（运动模式）和非加速度计数据（人口统计学和临床变量）对模型进行训练。基于均方误差（MSE）和决定系数（ ）评估性能，以评估组合多种数据类型如何影响预测准确性。
基于加速度计和非加速度计组合数据训练的模型始终优于基于单一数据类型的模型。贝叶斯岭回归实现了最高的准确性（MSE = 0.6746， = 0.9941），与决策树（MSE = 0.1907， = 0.8991）和SVR（MSE = 1.5243， = 2.2532）相比表现出卓越性能。包括年龄和合并症在内的非加速度计因素对跌倒风险预测有显著贡献。
整合加速度计和非加速度计数据可提高老年人跌倒风险预测的准确性。与传统模型相比，在组合数据集上训练的贝叶斯岭回归具有卓越的预测能力。这些发现凸显了多源数据融合对于有效预防跌倒策略的重要性。未来的工作应在更大、更多样化的人群中验证这些模型，以增强临床适用性。
