人工智能人体关键点检测技术在步态运动学分析中的效度

doi:10.3969/j.issn.1006-9771.2025.03.001

Abstract

Abstract:

Objective To develop a multi-parameter gait kinematics analysis and measurement system using artificial intelligence key point detection technology (AI system), and verify the effectiveness of the measurement.

Methods A total of ten inpatients with abnormal gait were selected in Peking University Third Hospital from April to October, 2022, while ten normal subjects were recruited. Their gait data were measured using GaitWatch and AI system simultaneously.

Results Compared with those from GaitWatch, the mean absolute error (MAE) of stride frequency, gait period, stride length and stride speed were little from AI system, with high accuracy (> 95%) and good consistency (ICC > 0.75); however, MAE of hip, knee and ankle angles was larger, and correlation was satisfactory (r> 0.60).

Conclusion The novel gait analysis system is accurate and consistent in measuring spatiotemporal gait parameters, but not well in measuring joint angles, which need to be modified.

Key words: gait analysis system, kinematics, artificial intelligence, key points, validity

CLC Number:

R496

LIU Fangchao, ZHANG Yuanmingfei, WU Meiqi, ZHOU Mouwang, LI Tao. Validity of key points detection technology of artificial intelligence in gait kinematics analysis[J]. Chinese Journal of Rehabilitation Theory and Practice, 2025, 31(3): 249-253.

Figures/Tables 7

Table 1

Figure 1

Table 2

Table 3

Table 4

Table 5

Figure 2

References 26

[1]	MICHAEL W W. Clinical gait analysis: a review[J]. Hum Mov Sci, 1996, 15(3): 369-387.
[2]	GOYAL V, DRAGUNAS A, ASKEW R L, et al. Altered biomechanical strategies of the paretic hip and knee joints during a step-up task[J]. Top Stroke Rehabil, 2023, 30(2): 137-145. doi: 10.1080/10749357.2021.2008596 pmid: 36744516
[3]	SMITH A W, WONG D P. Sagittal and frontal plane gait initiation kinetics in healthy, young subjects[J]. J Human Kinet, 2019, 67: 85-100.
[4]	SCHALLIG W, PIENING M, QUIRIJNEN L, et al. Multi-segment foot kinematics during gait in children with spastic cerebral palsy[J]. Gait Posture, 2024, 110: 144-149. doi: 10.1016/j.gaitpost.2024.03.014 pmid: 38608379
[5]	CELIK Y, STUART S, WOO W L, et al. Gait analysis in neurological populations: progression in the use of wearables[J]. Med Eng Phys, 2021, 87: 9-29. doi: 10.1016/j.medengphy.2020.11.005 pmid: 33461679
[6]	ABE H, KOYANAGI S, KUSUMOTO Y, et al. Intra-rater and inter-rater reliability, minimal detectable change, and construct validity of the Edinburgh Visual Gait Score in children with cerebral palsy[J]. Gait Posture, 2022, 94: 119-123. doi: 10.1016/j.gaitpost.2022.03.004 pmid: 35279565
[7]	RATHINAM C, BATEMAN A, PEIRSON J, et al. Observational gait assessment tools in paediatrics: a systematic review[J]. Gait Posture, 2014, 40(2): 279-285.
[8]	DEL PILAR DUQUE OROZCO M, ABOUSAMRA O, CHURCH C, et al. Reliability and validity of Edinburgh Visual Gait Score as an evaluation tool for children with cerebral palsy[J]. Gait Posture, 2016, 49: 14-18. doi: S0966-6362(16)30096-0 pmid: 27344448
[9]	BERNARDES R A, VENTURA F, NEVES H, et al. Wearable walking assistant for freezing of gait with environmental IoT monitoring: a contribution to the discussion[J]. Front Public Health, 2022, 10: 861621.
[10]	BOUTAAYAMOU M, SCHWARTZ C, STAMATAKIS J, et al. Development and validation of an accelerometer-based method for quantifying gait events[J]. Med Eng Phys, 2015, 37(2): 226-232. doi: 10.1016/j.medengphy.2015.01.001 pmid: 25618221
[11]	JARCHI D, POPE J, LEE T, et al. A review on accelerometry-based gait analysis and emerging clinical applications[J]. IEEE Rev Biomed Eng, 2018, 11: 177-194. doi: 10.1109/RBME.2018.2807182 pmid: 29994786
[12]	ZENI J J, RICHARDS J G, HIGGINSON J S. Two simple methods for determining gait events during treadmill and overground walking using kinematic data[J]. Gait Posture, 2008, 27(4): 710-714. doi: 10.1016/j.gaitpost.2007.07.007 pmid: 17723303
[13]	JURI T, EDUARDO P, STEFANO R, et al. Gait partitioning methods: a systematic review[J]. Sensors, 2016, 16(1): 66
[14]	RIBEIRO R P, GUERRERO F G, CAMARGO E N, et al. Construct validity and reliability of tests for sacroiliac dysfunction: standing flexion test (STFT) and sitting flexion test (SIFT)[J]. J Osteop Med, 2021, 121(11): 849-856.
[15]	WELLS M, GOLDSTEIN L N, WELLS T, et al. Total body weight estimation by 3D camera systems: potential high-tech solutions for emergency medicine applications? A scoping review[J]. J Am Coll Emerg Physicians Open, 2024, 5(5): e13320.
[16]	LIANG J, YUAN Z, LUO X, et al. A study on the 3D reconstruction strategy of a sheep body based on a Kinect v2 depth camera array[J]. Animals (Basel), 2024, 14(17): 2457.
[17]	LU H Y, WANG X, HU C, et al. Home-based guidance training system with interactive visual feedback using Kinect on stroke survivors with moderate to severe motor impairment[J]. J Neuroeng Rehabil, 2024, 21(1): 189.
[18]	WEI S E, RAMAKRISHNA V, KANADE T, et al. Convolutional pose machines[C]. Las Vegas:Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016: 4724-4732.
[19]	BERNAL F, FEIPEL V, PLAZA M. Kinect-based gait analysis system design and concurrent validity in persons with anterolateral shoulder pain syndrome, results from a pilot study[J]. Sensors (Basel), 2024, 24(19): 6351.
[20]	BAWA A, BANITSAS K, ABBOD M. A review on the use of Microsoft Kinect for gait abnormality and postural disorder assessment[J]. J Healthc Eng, 2021, 2021: 4360122.
[21]	ALBERT J A, OWOLABI V, GEBEL A, et al. Evaluation of the pose tracking performance of the Azure Kinect and Kinect v2 for gait analysis in comparison with a gold standard: a pilot study[J]. Sensors (Basel), 2020, 20(18): 5104.
[22]	KOZLOW P, ABID N, YANUSHKEVICH S. Gait type analysis using dynamic Bayesian networks[J]. Sensors (Basel), 2018, 18(10): 3329.
[23]	ISMAIL A, SHOUMAN H, CHERRY A, et al. Torwads real time Kinect analysis system for early diagnosis of gait cycle abnormalities[C]. Beirut, Lebanon:Proceedings of the 2017 Fourth International Conference on Advances in Biomedical Engineering (ICABME), 2017.
[24]	MA Y, MITHRARATNE K, WILSON N, et al. Kinect v2-based gait analysis for children with cerebral palsy: validity and reliability of spatial margin of stability and spatiotemporal variables[J]. Sensors (Basel), 2021, 21(6): 2104.
[25]	ELTOUKHY M, OH J, KUENZE C, et al. Improved Kinect-based spatiotemporal and kinematic treadmill gait assessment[J]. Gait Posture, 2017, 51: 77-83. doi: S0966-6362(16)30602-6 pmid: 27721202
[26]	SPRINGER S, YOGEV S G. Validity of the Kinect for gait assessment: a focused review[J]. Sensors (Basel), 2016, 16(2): 194.

对象	n	性别(男/女)/n	年龄/岁	身高/cm	体质量/kg
健康受试者	10	6/4	44.90±19.15	169.90±9.74	54.1±6.47
步态异常患者	10	5/5	52.40±16.00	168.80±7.50	61.9±8.56

项目	GaitWatch (n = 35)	AI (n = 35)	精确度/%	MAE	ICC
步频/(步·min^-1)	99.60±10.08	99.74±10.60	98.45	1.54	0.975
步态周期/s	1.21±0.13	1.21±0.14	98.28	0.02	0.977
步幅/cm	124.00±9.15	122.62±8.87	96.42	2.63	0.807
步速/(cm·s^-1)	104.22±14.54	102.71±13.71	96.51	4.09	0.958

关节	GaitWatch (n = 140)	AI (n = 140)	MAE	r
髋	17.79±24.73	-2.50±26.94	20.8	0.866
膝	35.86±31.04	30.03±32.37	10.1	0.922
踝	1.18±17.81	-10.55±24.63	16.1	0.778

项目	GaitWatch (n = 35)	AI (n = 35)	精确度/%	MAE	ICC
步频/(步·min^-1)	92.54±10.69	91.60±10.23	97.88	1.91	0.963
步态周期/s	1.31±0.16	1.32±0.16	97.80	0.03	0.961
步幅/cm	108.60±25.28	105.68±26.78	95.10	4.80	0.978
步速/(cm·s^-1)	84.65±26.37	81.80±26.87	95.03	4.06	0.988

关节	GaitWatch (n = 140)	AI (n = 140)	MAE	r
髋	21.09±32.38	7.10±42.53	20.20	0.813
膝	34.17±29.54	30.14±32.09	8.40	0.943
踝	2.68±19.18	-8.89±25.47	16.20	0.785

Validity of key points detection technology of artificial intelligence in gait kinematics analysis

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 26

Related Articles 15

Metrics

Comments

Recommended 0

[1]	YU Boyang, YANG Yanyan, MA Ao, LI Tao, LIU Xiaoxie, LI Zhengyang, DUAN Yajing, LIU Jiaqi, XIE Yuxiao, WANG Cui, HUANG Zhen, ZHANG Lining, LIU Xinyi, JIA Zishan, ZHOU Mouwang. Reliability and validity of assessment tools of Brief ICF Core Sets for Arthroplasty of Knee Osteoarthritis in Perioperative Period [J]. Chinese Journal of Rehabilitation Theory and Practice, 2024, 30(9): 1053-1059.
[2]	JIANG Changhao, JIANG Xianxin, HUANG Chen, ZHONG Xiaoke. Application of artificial intelligence in diagnosis and intervention in sleep disorder for older adults: a scoping review using ICF [J]. Chinese Journal of Rehabilitation Theory and Practice, 2024, 30(8): 922-929.
[3]	SU Rufeng, ZHONG Xiaoke, GAO Xiaoyan, JIANG Changhao. Application of artificial intelligence in anxiety and depression among children and adolescents: a scoping review [J]. Chinese Journal of Rehabilitation Theory and Practice, 2024, 30(5): 513-519.
[4]	WANG Zhenzhou, ZHANG Yang. International researches on artificial intelligence enabled diagnosis and intervention for children with disabilities in the past two decades: a visualized analysis [J]. Chinese Journal of Rehabilitation Theory and Practice, 2024, 30(4): 404-415.
[5]	GENG Limeng, LIU Congcong, LI Ling, LÜ Panpan, WANG Xin, LIU Fang. Psychological and behavioral characteristics of children with autism spectrum disorder using Psycho-educational Profile (Third Edition) [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2023, 29(9): 1035-1039.
[6]	YI Qifeng, HUANG Zhuoer, YANG Guoli, XIE Lihua, XIE Shengfeng, WU Xiaoxia, YAN Jin. Development, and reliability and validity testing of a knowledge needs questionnaire of respiratory rehabilitation training for in-service healthcare workers [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2023, 29(8): 985-992.
[7]	QIU Xiao, LING Junqi, CONG Yangyang, BAI Yulong. Feasibility, reliability and validity of a 3D scanning volume measurement for distal upper limb volume [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2023, 29(3): 364-367.
[8]	TAN Mingdan,FENG Dingyao,CHEN Xi,LIU Hanjun,LI Yongxue. Reliability and validity of Chinese version of Dysarthria Impact Profile for Parkinson's disease [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2022, 28(6): 696-703.
[9]	Lin CHEN,Kai XIA,Xue-tao ZHANG,Si-chuang YANG,Hai-hong PAN. Variable Quasi-circular Gait Planning with Smooth Angular Acceleration for Lower Limb Rehabilitation [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2021, 27(6): 621-626.
[10]	Zhao-wen ZHOU,Cui WANG,Zhen HUANG. Reliability and Validity of the Chinese Version of Weekly Calendar Planning Activity for Executive Function Assessment in Community-dwelling Middle-aged and Elderly Adults [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2021, 27(6): 737-744.
[11]	Wei WU,Bo-ye NI,Jia-jia SHI. Reliability and Validity of Extended Barthel Index for Stroke Patients [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2021, 27(3): 261-268.
[12]	Ming-ming GAO,Ze-jia HE,Xiao-ping YUN,Zhou LONG,Cheng WANG,Xiang-dong WANG. Agreement of Spatiotemporal Gait Characteristics between Gaitboter Gait Analysis System and Noraxon Gait Analysis System [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2021, 27(2): 216-221.
[13]	JIANG Qian-ru,LIU Ke-min. Advance in Scapular Dyskinesis and Its Rehabilitation Management (review) [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2021, 27(11): 1307-1311.
[14]	GUO Ya-wen,LIN Bei-lei,ZHANG Zhen-xiang,WANG Yong-li,FU Bo,QI Bei. Work-ability Support Scale-Chinese Version for Stroke Patients: Reliability and Validity Analysis [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2020, 26(9): 1076-1082.
[15]	WANG Yu-zhong,LIANG Dan-yan,HAO Jiang-hui,WEN Shu-zheng,Wang Ji-hong. Application of Achilles Tendon Total Rupture Score in Acute Achilles Tendon Rupture [J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2020, 26(6): 707-710.