Suppr超能文献

单带与分带:通过微相步态捕捉实现智能跑步机控制用于中风后康复

Single-Belt Versus Split-Belt: Intelligent Treadmill Control via Microphase Gait Capture for Poststroke Rehabilitation.

作者信息

Cao Shengting, Ko Mansoo, Li Chih-Ying, Brown David, Wang Xuefeng, Hu Fei, Gan Yu

机构信息

Electrical and Computer Engineering, University of Alabama, Tuscaloosa, AL 35487 USA.

University of Texas Medical Branch, Mountain Brook, TX 77555-0128 USA.

出版信息

IEEE Trans Hum Mach Syst. 2023 Dec;53(6):1006-1016. doi: 10.1109/thms.2023.3327661. Epub 2023 Nov 21.

Abstract

Stroke is the leading long-term disability and causes a significant financial burden associated with rehabilitation. In poststroke rehabilitation, individuals with hemiparesis have a specialized demand for coordinated movement between the paretic and the nonparetic legs. The split-belt treadmill can effectively facilitate the paretic leg by slowing down the belt speed for that leg while the patient is walking on a split-belt treadmill. Although studies have found that split-belt treadmills can produce better gait recovery outcomes than traditional single-belt treadmills, the high cost of split-belt treadmills is a significant barrier to stroke rehabilitation in clinics. In this article, we design an AI-based system for the single-belt treadmill to make it act like a split-belt by adjusting the belt speed instantaneously according to the patient's microgait phases. This system only requires a low-cost RGB camera to capture human gait patterns. A novel microgait classification pipeline model is used to detect gait phases in real time. The pipeline is based on self-supervised learning that can calibrate the anchor video with the real-time video. We then use a ResNet-LSTM module to handle temporal information and increase accuracy. A real-time filtering algorithm is used to smoothen the treadmill control. We have tested the developed system with 34 healthy individuals and four stroke patients. The results show that our system is able to detect the gait microphase accurately and requires less human annotation in training, compared to the ResNet50 classifier. Our system "Splicer" is boosted by AI modules and performs comparably as a split-belt system, in terms of timely varying left/right foot speed, creating a hemiparetic gait in healthy individuals, and promoting paretic side symmetry in force exertion for stroke patients. This innovative design can potentially provide cost-effective rehabilitation treatment for hemiparetic patients.

摘要

中风是导致长期残疾的主要原因,并给康复带来了巨大的经济负担。在中风后康复中,偏瘫患者对患侧腿和非患侧腿之间的协调运动有特殊需求。分带跑步机可以通过在患者在分带跑步机上行走时减慢患侧腿的皮带速度,有效地促进患侧腿的运动。尽管研究发现分带跑步机比传统的单带跑步机能产生更好的步态恢复效果,但分带跑步机的高成本是临床中风康复的一个重大障碍。在本文中,我们设计了一种基于人工智能的单带跑步机系统,通过根据患者的微步态阶段即时调整皮带速度,使其表现得像分带跑步机。该系统只需要一个低成本的RGB摄像头来捕捉人体步态模式。一种新颖的微步态分类管道模型用于实时检测步态阶段。该管道基于自监督学习,可以将锚定视频与实时视频进行校准。然后我们使用ResNet-LSTM模块来处理时间信息并提高准确性。一种实时滤波算法用于平滑跑步机控制。我们已经用34名健康个体和4名中风患者对开发的系统进行了测试。结果表明,与ResNet50分类器相比,我们的系统能够准确检测步态微阶段,并且在训练中需要的人工标注更少。我们的系统“Splicer”由人工智能模块推动,在及时改变左右脚速度、在健康个体中创造偏瘫步态以及促进中风患者患侧用力对称方面,其性能与分带系统相当。这种创新设计有可能为偏瘫患者提供具有成本效益的康复治疗。

相似文献

1
Single-Belt Versus Split-Belt: Intelligent Treadmill Control via Microphase Gait Capture for Poststroke Rehabilitation.
IEEE Trans Hum Mach Syst. 2023 Dec;53(6):1006-1016. doi: 10.1109/thms.2023.3327661. Epub 2023 Nov 21.
3
Single-belt vs. split-belt treadmill symmetry training: is there a perfect choice for gait rehabilitation post-stroke?
Front Physiol. 2024 Jul 24;15:1409304. doi: 10.3389/fphys.2024.1409304. eCollection 2024.
4
More symmetrical gait after split-belt treadmill walking does not modify dynamic and postural balance in individuals post-stroke.
J Electromyogr Kinesiol. 2018 Aug;41:41-49. doi: 10.1016/j.jelekin.2018.04.008. Epub 2018 Apr 24.
5
Real-time feedback control of split-belt ratio to induce targeted step length asymmetry.
J Neuroeng Rehabil. 2022 Jun 30;19(1):65. doi: 10.1186/s12984-022-01044-0.
6
The Effect of Split-Belt Treadmill Interventions on Step Length Asymmetry in Individuals Poststroke: A Systematic Review With Meta-Analysis.
Neurorehabil Neural Repair. 2021 Jul;35(7):563-575. doi: 10.1177/15459683211011226. Epub 2021 May 12.
8
Step time asymmetry but not step length asymmetry is adapted to optimize energy cost of split-belt treadmill walking.
J Physiol. 2020 Sep;598(18):4063-4078. doi: 10.1113/JP279195. Epub 2020 Jul 28.
9
Split-belt treadmill training poststroke: a case study.
J Neurol Phys Ther. 2010 Dec;34(4):202-7. doi: 10.1097/NPT.0b013e3181fd5eab.
10
Oxygen consumption, oxygen cost, heart rate, and perceived effort during split-belt treadmill walking in young healthy adults.
Eur J Appl Physiol. 2013 Mar;113(3):729-34. doi: 10.1007/s00421-012-2477-7. Epub 2012 Aug 30.

本文引用的文献

1
Assessment Methods of Post-stroke Gait: A Scoping Review of Technology-Driven Approaches to Gait Characterization and Analysis.
Front Neurol. 2021 Jun 8;12:650024. doi: 10.3389/fneur.2021.650024. eCollection 2021.
3
OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields.
IEEE Trans Pattern Anal Mach Intell. 2021 Jan;43(1):172-186. doi: 10.1109/TPAMI.2019.2929257. Epub 2020 Dec 4.
5
Gait Analysis for Post-Stroke Hemiparetic Patient by Multi-Features Fusion Method.
Sensors (Basel). 2019 Apr 11;19(7):1737. doi: 10.3390/s19071737.
6
Automatic real-time gait event detection in children using deep neural networks.
PLoS One. 2019 Jan 31;14(1):e0211466. doi: 10.1371/journal.pone.0211466. eCollection 2019.
7
Repeated split-belt treadmill walking improved gait ability in individuals with chronic stroke: A pilot study.
Physiother Theory Pract. 2018 Feb;34(2):81-90. doi: 10.1080/09593985.2017.1375055. Epub 2017 Sep 13.
8
Gait disorders in adults and the elderly : A clinical guide.
Wien Klin Wochenschr. 2017 Feb;129(3-4):81-95. doi: 10.1007/s00508-016-1096-4. Epub 2016 Oct 21.
9
Delays in Human-Computer Interaction and Their Effects on Brain Activity.
PLoS One. 2016 Jan 8;11(1):e0146250. doi: 10.1371/journal.pone.0146250. eCollection 2016.
10
The Split-Belt Walking Paradigm: Exploring Motor Learning and Spatiotemporal Asymmetry Poststroke.
Phys Med Rehabil Clin N Am. 2015 Nov;26(4):703-13. doi: 10.1016/j.pmr.2015.06.010. Epub 2015 Sep 26.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验