Background The extent to which gait and mobility measures predict falls relative to other risk factors is unclear. This study examined predictive accuracy of over 70 baseline risk factors, including gait and mobility, for future falls and syncope using conditional inference forest models. Methods Data from three waves of The Irish Longitudinal Study on Ageing (TILDA), a population-based study of community-dwelling adults aged ≥50 years were used (n=4,706). Outcome variables were recurrent falls, injurious falls, unexplained falls and syncope occurring over four year follow-up. Predictive accuracy was calculated using 5 fold cross-validation; as there was class imbalance, the algorithm was trained using undersampling of the larger class. Classification rate, area under the receiver operating characteristic curve (AUROC) and area under the precision recall curve (PRAUC) assessed predictive accuracy. Results Highest overall accuracy was 69.7% for recurrent falls in 50-64 year olds. AUROC and PRAUC were ≤0.69 and ≤0.39 respectively for all outcomes indicating low predictive accuracy. History of falls, unsteadiness while walking, fear of falling, mobility, medications , mental health and cardiovascular health and function were the most important predictors for most outcomes. Conclusions Conditional inference forest models using over 70 risk factors resulted in low predictive accuracy for future recurrent, injurious and unexplained falls and syncope in community-dwelling adults. Gait and mobility impairments were important predictors of most outcomes but did not discriminate well between fallers and non-fallers. Results highlight the importance of multifactorial risk assessment and intervention and validate key modifiable risk factors for future falls and syncope.

中文翻译：

---

使用条件推理森林检查老年人未来跌倒和晕厥的预测能力：爱尔兰老龄化纵向研究的结果

背景 步态和移动性测量相对于其他风险因素预测跌倒的程度尚不清楚。本研究使用条件推理森林模型检查了 70 多个基线风险因素（包括步态和移动性）对未来跌倒和晕厥的预测准确性。方法 使用了爱尔兰老龄化纵向研究 (TILDA) 的三波数据，这是一项针对 50 岁以上社区居民的基于人群的研究 (n=4,706)。结果变量是反复跌倒、受伤跌倒、无法解释的跌倒和四年随访期间发生的晕厥。使用 5 折交叉验证计算预测准确性；由于存在类不平衡，该算法使用较大类的欠采样进行训练。分类率，受试者工作特征曲线下面积 (AUROC) 和精确召回曲线下面积 (PRAUC) 评估预测准确性。结果 50-64 岁人群反复跌倒的最高总体准确率为 69.7%。所有结果的 AUROC 和 PRAUC 分别≤0.69 和≤0.39，表明预测准确性低。跌倒史、行走不稳、害怕跌倒、行动不便、药物治疗、心理健康以及心血管健康和功能是大多数结果的最重要预测因素。结论 使用 70 多个风险因素的条件推理森林模型导致社区成年人未来复发性、伤害性和不明原因的跌倒和晕厥的预测准确性较低。步态和行动障碍是大多数结果的重要预测指标，但不能很好地区分跌倒者和非跌倒者。结果强调了多因素风险评估和干预的重要性，并验证了未来跌倒和晕厥的关键可改变风险因素。