Ren Yin-Xia, Wu Bei, Lou Jian-Lin, Zhu Xiao-Rong, Zhang Chen, Lang Qing, Wei Zhu-Qin, Su Li-Ming, Qi Heng-Nian, Wang Li-Na
School of Medicine, Huzhou Key Laboratory of Precise Prevention and Control of Major Chronic Diseases, Huzhou University, Huzhou 313000, Zhejiang Province, China.
Rory Meyers College of Nursing, New York University, New York, NY 10010, United States.
World J Psychiatry. 2025 Sep 19;15(9):109478. doi: 10.5498/wjp.v15.i9.109478.
Older adults with mild cognitive impairment (MCI) often show motor dysfunction, including slower gait and impaired handwriting. While gait and handwriting parameters are promising for MCI screening, their combined potential to distinguish MCI from cognitively normal adults is unclear.
To assess gait and handwriting differences and their potential for screening MCI in older adults.
Ninety-five participants, including 34 with MCI and 61 cognitively normal controls, were assessed for gait using the GAITRite system and handwriting with a dot-matrix pen. Five machine learning models were developed to assess the discriminative power of gait and handwriting data for MCI screening.
Compared to the cognitively normal group, the MCI group had slower gait velocity ( = -2.911, = 0.004), shorter stride and step lengths ( = -3.005, = 0.003; = 2.863, = 0.005), and longer cycle, standing, and double support times ( = -2.274, = 0.025; = -2.376, = 0.018; = -2.717, = 0.007). They also had reduced cadence ( = 2.060, = 0.042) and increased double support time variability ( = -2.614, = 0.009). In handwriting, the MCI group showed lower average pressure (all tasks: Z = -2.135, = 0.033) and decreased accuracy (graphic task: = -2.447, = 0.014; Chinese character task: = -3.078, = 0.002). In the graphic task, they demonstrated longer time in air (Z = -2.865, = 0.004), reduced X-axis maximum velocities ( = -3.237, = 0.001), and lower accelerations (X-axis: = -2.880, = 0.004; Y-axis: = -1.987, = 0.047) and maximum accelerations (X-axis: = -3.998, < 0.001; Y-axis: = -2.050, = 0.040). The multimodal analysis achieved the highest accuracy (74.4%) with the Gradient Boosting Classifier.
Integrating gait and handwriting kinematics parameters provides a viable method for distinguishing MCI, potentially supporting large-scale screening, especially in resource-limited settings.
患有轻度认知障碍（MCI）的老年人常表现出运动功能障碍，包括步态变缓及书写能力受损。虽然步态和书写参数在MCI筛查方面颇具前景，但它们联合起来区分MCI与认知正常成年人的潜力尚不清楚。
评估老年人的步态和书写差异及其在筛查MCI方面的潜力。
95名参与者，包括34名MCI患者和61名认知正常的对照者，使用GAITRite系统评估步态，并用点阵笔评估书写情况。开发了5种机器学习模型，以评估步态和书写数据对MCI筛查的判别能力。
与认知正常组相比，MCI组的步态速度较慢（t = -2.911，P = 0.004），步幅和步长较短（t = -3.005，P = 0.003；t = 2.863，P = 0.005），周期、站立和双支撑时间较长（t = -2.274，P = 0.025；t = -2.376，P = 0.018；t = -2.717，P = 0.007）。他们的步频也降低了（t = 2.060，P = 0.042），双支撑时间变异性增加（t = -2.614，P = 0.009）。在书写方面，MCI组的平均压力较低（所有任务：Z = -2.135，P = 0.033），准确性降低（图形任务：t = -2.447，P = 0.014；汉字任务：t = -3.078，P = 0.002）。在图形任务中，他们在空中停留的时间更长（Z = -2.865，P = 0.004），X轴最大速度降低（t = -3.237，P = 0.001），加速度较低（X轴：t = -2.880，P = 0.004；Y轴：t = -1.987，P = 0.047）以及最大加速度较低（X轴：t = -3.998，P < 0.001；Y轴：t = -2.050，P = 0.040）。多模态分析使用梯度提升分类器达到了最高准确率（74.4%）。
整合步态和书写运动学参数为区分MCI提供了一种可行的方法，可能有助于大规模筛查，尤其是在资源有限的环境中。
