Association Rule Mining to Examine Predictors for the Outcome of Gait Rehabilitation Programs in Stroke Survivors.
Association Rule Mining to Examine Predictors for the Outcome of Gait Rehabilitation Programs in Stroke Survivors.
复制标题
DOI：
10.1097/phm.0000000000001912
复制
发表时间：
2022-06-01
影响因子：
3
通讯作者：
Chou, Chun-An
中科院分区：
文献类型：
--
作者：
Yen, Sheng-Che;Wang, Xiaofan;Wang, Inga;Corkery, Marie B.;Chui, Kevin K.;Chou, Chun-An
我们提出了一种新的应用关联规则数据挖掘来确定运动训练和家庭锻炼反应的预测因子，以改善中风后的步态。这项研究是对运动经验应用卒中后试验(LEAPS)数据集的二次数据分析。采用关联规则分析方法对3种干预措施进行分析：(1)早期运动训练(ELT)，(2)晚期运动训练(LLT)，(3)家庭锻炼计划(HEP)。结果变量是参与者中风后在自我选择的舒适步态速度方面是否有大于中位数的改善。调查了三种类型的预测因素：(1)人口统计学；(2)行为和病史；(3)基线的临床评估。当关联规则满足基于数据确定的两个标准时生成：10%的支持度和70%的置信度。确定的规则表明，三种干预措施的反应预测因素不同，这与之前基于传统Logistic回归的报告不一致。然而，这些规则的可信度很高，但支持率很低，这表明它们是可靠的，但在LEAPS数据集中并不经常出现。在将这些规则应用于临床之前，有必要对这些规则进行更大样本量的进一步研究。
We present a novel application of association rule data mining to determine the predictors of the response to locomotor training and home exercise for improving gait following stroke. The study was a secondary data analysis on the Locomotor Experience Applied Post Stroke Trial (LEAPS) dataset. The association rule analysis was applied to analyze three interventions: (1) Early Locomotor Training (ELT), (2) Late Locomotor Training (LLT), and (3) Home Exercise Program (HEP). The outcome variable was whether participants post-stroke had greater than median improvement in the self-selected comfortable gait speed. Three types of predictors were investigated: (1) demographics; (2) behavioral and medical history; (3) clinical assessments at baseline. Association rules were generated when they meet two criteria determined based on the data: 10% of support and 70% of confidence. The identified rules showed that the predictors of the response were different across the three interventions, which was inconsistent with the previous report based on traditional logistic regression. However, the rules were identified with high confidence but low support, indicating they were reliable but did not appear often in the LEAPS dataset. Further investigation of these rules with a larger sample size is warranted before applying them to clinical settings.