Master Program in Long-term Care, College of Nursing, Taipei Medical University, Taipei, Taiwan.
Department of Occupational Therapy, I-Shou University, Kaohsiung, Taiwan.
Phys Ther. 2021 Apr 4;101(4). doi: 10.1093/ptj/pzab036.
The Fugl-Meyer motor scale (FM) is a well-validated measure for assessing upper extremity and lower extremity motor functions in people with stroke. The FM contains numerous items (50), which reduces its clinical usability. The purpose of this study was to develop a short form of the FM for people with stroke using a machine-learning methodology (FM-ML) and compare the efficiency (ie, number of items) and psychometric properties of the FM-ML with those of other FM versions, including the original FM, the 37-item FM, and the 12-item FM.
This observational study with follow-up used secondary data analysis. For developing the FM-ML, the random lasso method of ML was used to select the 10 most informative items (in terms of index of importance). Next, the scores of the FM-ML were calculated using an artificial neural network. Finally, the concurrent validity, predictive validity, responsiveness, and test-retest reliability of all FM versions were examined.
The FM-ML used fewer items (80% fewer than the FM, 73% fewer than the 37-item FM, and 17% fewer than the 12-item FM) to achieve psychometric properties comparable with those of the other FM versions (concurrent validity: Pearson r = 0.95-0.99 vs 0.91-0.97; responsiveness: Pearson r = 0.78-0.91 vs 0.33-0.72; and test-retest reliability: intraclass correlation coefficient = 0.88-0.92 vs 0.93-0.98).
The findings preliminarily support the efficiency and psychometric properties of the 10-item FM-ML.
The FM-ML has potential to substantially improve the efficiency of motor function assessments in patients with stroke.
Fugl-Meyer 运动量表（FM）是一种经过充分验证的评估中风患者上肢和下肢运动功能的工具。FM 包含大量项目（50 项），这降低了其临床可用性。本研究的目的是使用机器学习方法（FM-ML）为中风患者开发 FM 的简短形式，并比较 FM-ML 与其他 FM 版本（包括原始 FM、37 项 FM 和 12 项 FM）的效率（即项目数）和心理测量特性。
这是一项具有随访的观察性研究，使用了二次数据分析。为了开发 FM-ML，使用机器学习的随机套索方法选择 10 项最具信息量的项目（根据重要性指数）。然后，使用人工神经网络计算 FM-ML 的分数。最后，检查了所有 FM 版本的同时效度、预测效度、反应度和重测信度。
FM-ML 使用的项目较少（比 FM 少 80%，比 37 项 FM 少 73%，比 12 项 FM 少 17%），但达到了与其他 FM 版本相当的心理测量特性（同时效度：Pearson r=0.95-0.99 与 0.91-0.97；反应度：Pearson r=0.78-0.91 与 0.33-0.72；重测信度：组内相关系数=0.88-0.92 与 0.93-0.98）。
这些发现初步支持了 10 项 FM-ML 的效率和心理测量特性。
FM-ML 有可能显著提高中风患者运动功能评估的效率。
