基于人工智能和临床诊断的上肢康复评估方法研究进展  

Research progress of assessment methods based on artificial intelligence and clinical diagnosis in upper limb rehabilitation

作　　者：王博超 张新峰[1] 

机构地区：[1]北京工业大学,北京100124

出　　处：《北京生物医学工程》2018年第1期103-108,共6页Beijing Biomedical Engineering

基　　金：北京市属高等学校高层次人才引进与培养计划(CIT&TCD201504018)资助

摘　　要：脑卒中导致患者肢体运动功能障碍或缺失,严重影响了患者的生活质量。在上肢康复治疗中,医生需要对患者的上肢进行主观康复评估,但这种方法误差大、成本高。因此,人们将人工智能技术应用到医疗康复领域。本文总结了基于s EMG信号特征、运动轨迹误差特征、关节运动角度特征、关节角速度特征的客观评估方法,以及Brunnstrom等级评价法、上田敏评价法、Fugl-Meyer量表评价法、Wolf运动功能测试评价方法等主观评估方法。最后,本文认为现有的客观评估方法普遍受到训练资料过少、特征单一等因素影响。主观评估方法普遍受到评估时间过长、易受主观影响等因素影响。未来的客观评估算法还应在算法准确性、训练资料规模、多特征融合等方面继续改进。Stoke causes dysfunction of limb and seriously affects the life quality of patients. In the upper limb rehabilitation,doctors need to carry out subjective assessment for upper-limb of patients. But this method has large error and high cost. Therefore,artificial intelligence technology is applied to the field of medical rehabilitation. This paper summarize the objective assessment methods which are base on s EMG signal feature,trajectory error feature,joint angels and joint angular velocity. Subjective assessment methods include Brunnstrom,Ueda,Bin,Fugl-Meyer,and Wolf Motor Function Test. Finally,the paper concludes that existing objective methods are generally affected by the scale of data and the number of feature. Subjective methods are generally limited by the time-consuming and subjective error. In the future,we should improve the objective algorithm from accuracy,scale of data and multi-feature fusion.

关 键 词：脑卒中 上肢康复 评估方法 人工智能 机器学习 特征提取 

分 类 号：R318.04[医药卫生—生物医学工程]