Patients with brachial plexus injuries often require long-term follow-up, and the frequent hospital visits can be a burden. Remote monitoring of these patients could be facilitated using Human Pose Estimation algorithms. We evaluated the performance of seven recently released algorithms and developed a WeChat mini-program using the best performing model. The validity of this program was then assessed in brachial plexus injured patients by comparing its results with those of manual goniometry. Our results demonstrated acceptable accuracy of this model, with mean differences of 4° and 7° when compared with manual goniometry in shoulder abduction and elbow flexion, respectively. Remote monitoring using a WeChat mini-program is a reliable and convenient tool for the follow-up of brachial plexus injury patients.
ArmstrongADMacDermidJCChinchalkarSStevensRSKingGJ.
Reliability of range-of-motion measurement in the elbow and forearm. J Shoulder Elbow Surg. 1998,
7: 573–80.
2.
AsgarianAZhaoSAshrafABBrowneMEPrkachinKMMihailidisAHadjistavropoulosTTaatiB.
Limitations and biases in facial landmark detection and an empirical study on older adults with dementia. In: CVPR Workshops, 2019: 28–36.
3.
BandiniARezaeiSGuarínDLKulkarniMLimDBoulosMIZinmanLYunusovaYTaatiB.
A new dataset for facial motion analysis in individuals with neurological disorders. IEEE J Biomed Health Informat. 2020,
25: 1111–9.
4.
BlandJMAltmanDG.Statistical methods for assessing agreement between two methods of clinical measurement. Lancet (London). 1986,
1: 307–10.
5.
BlonnaDZarkadasPCFitzsimmonsJSO’DriscollSW.
Validation of a photography-based goniometry method for measuring joint range of motion. J Shoulder Elbow Surg. 2012,
21: 29–35.
6.
BrownHJohnsonKGilbertAQuickTJ.
The lived experience of motor recovery of elbow flexion following oberlin nerve transfer: a qualitative analysis. Hand Therapy. 2018,
23: 130–8.
7.
ChenHMFengRYWuSFXuHZhouFCLiuZG.
2d human pose estimation: a survey. Multimedia Syst. 2023,
29: 3115–38.
8.
Chen J, Xian Zhang A, Jia Qian S, Jing Wang Y.
Measurement of finger joint motion after flexor tendon repair: Smartphone photography compared with traditional goniometry. J Hand Surg Eur Vol. 2021,
46: 825–9.
9.
Dent PA, Jr., Wilke B, Terkonda S, Luther I, Shi GG.Validation of teleconference-based goniometry for measuring elbow joint range of motion. Cureus. 2020,
12: e6925.
10.
Dorje T, Zhao G, Tso K, Wang J, Chen Y, Tsokey L, Tan BK, Scheer A, Jacques A, Li Z, Wang R, Chow CK, Ge J, Maiorana A.
Smartphone and social media-based cardiac rehabilitation and secondary prevention in China (Smart-cr/sp): a parallel-group, single-blind, randomised controlled trial. Lancet Digit Health. 2019,
1: e363–e74.
11.
Fan J, Gu F, Lv L, Zhang Z, Zhu C, Qi J, Wang H, Liu X, Yang J, Zhu Q.
Reliability of a human pose tracking algorithm for measuring upper limb joints: comparison with photography-based goniometry. BMC Musculoskelet Disord. 2022,
23: 877.
12.
Guarin DL, Yunusova Y, Taati B, Dusseldorp JR, Mohan S, Tavares J, van Veen MM, Fortier E, Hadlock TA, Jowett N.Toward an automatic system for computer-aided assessment in facial palsy. Facial Plast Surg Aesthet Med. 2020,
22: 42–9.
13.
Hahn S, Kroger I, Willwacher S, Augat P.Reliability and validity varies among smartphone apps for range of motion measurements of the lower extremity: a systematic review. Biomed Tech (Berl). 2021,
66: 537–55.
14.
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016: 770–8.
15.
Huang J, Zhu Z, Guo F, Huang G. The devil is in the details: delving into unbiased data processing for human pose estimation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020: 5700–9.
16.
KeoghJWLCoxAAndersonSLiewBOlsenASchramBFurnessJ.
Reliability and validity of clinically accessible smartphone applications to measure joint range of motion: a systematic review. PLoS One. 2019,
14: e0215806.
17.
Li W, Wang Z, Yin B, Peng Q, Du Y, Xiao T, Yu G, Lu H, Wei Y, Sun J. Rethinking on multi-stage networks for human pose estimation. arXiv preprint arXiv:190100148. 2019.
18.
LimthongthangRBachouraASongcharoenPOstermanAL.
Adult brachial plexus injury: Evaluation and management. Orthoped Clin N Am. 2013,
44: 591–603.
19.
LiuPYuNYangYYuYSunXYuHHanJWuJ.
Quantitative assessment of gait characteristics in patients with Parkinson’s disease using 2D video. Parkinsonism Relat Disord. 2022,
101: 49–56.
20.
MagnoGMFlemanCHalliburtonCBosioSPuigdevallMH.
Usefulness of digital measurements for functional evaluation of paediatric elbow range of motion. J Telemed Telecare. 2023,
29: 561–5.
21.
MartiniEBoldoMAldegheriSValeNFilippettiMSmaniaNBertuccoMPicelliABombieriN.
Enabling gait analysis in the telemedicine practice through portable and accurate 3D human pose estimation. Comput Methods Programs Biomed. 2022,
225: 107016.
22.
MateoFCarrascoJJAguilar-RodriguezMSoria-OlivasEBonanadSQuerolFPerez-AlendaS.
Assessment of kinect v2 for elbow range of motion estimation in people with haemophilia using an angle correction model. Haemophilia. 2019,
25: e165–e73.
23.
MeislinMAWagnerERShinAY.
A comparison of elbow range of motion measurements: Smartphone-based digital photography versus goniometric measurements. J Hand Surg Am. 2016,
41: 510–15.e1.
24.
MidhaR.Epidemiology of brachial plexus injuries in a multitrauma population. Neurosurgery. 1997,
40: 1182–9.
25.
Moon Y, Sung J, An R, Hernandez ME, Sosnoff JJ.Gait variability in people with neurological disorders: a systematic review and meta-analysis. Human Movement Sci. 2016,
47: 197–208.
26.
Ozsoy U, Yildirim Y, Karasin S, Sekerci R, Suzen LB.
Reliability and agreement of Azure Kinect and Kinect v2 depth sensors in the shoulder joint range of motion estimation. J Shoulder Elbow Surg. 2022,
31: 2049–56.
27.
Park KW, Lee EJ, Lee JS, Jeong J, Choi N, Jo S, Jung M, Do JY, Kang DW, Lee JG, Chung SJ.
Machine learning-based automatic rating for cardinal symptoms of Parkinson disease. Neurology. 2021,
96: e1761–e9.
28.
Quick TJ and Brown H.
Evaluation of functional outcomes after brachial plexus injury. J Hand Surg Eur Vol. 2020,
45: 28–33.
29.
Russo RR, Burn MB, Ismaily SK, Gerrie BJ, Han S, Alexander J, Lenherr C, Noble PC, Harris JD, McCulloch PC.
Is digital photography an accurate and precise method for measuring range of motion of the shoulder and elbow?Journal of Orthopaedic Science. 2018,
23: 310–5.
30.
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC. Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018: 4510–20.
31.
Shin HI, Shin HI, Bang MS, Kim DK, Shin SH, Kim EK, Kim YJ, Lee ES, Park SG, Ji HM, Lee WH.
Deep learning-based quantitative analyses of spontaneous movements and their association with early neurological development in preterm infants. Sci Rep. 2022,
12: 3138.
32.
Sun K, Xiao B, Liu D, Wang J. Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019: 5693–703.
33.
Taati B, Zhao S, Ashraf AB, Asgarian A, Browne ME, Prkachin KM, Mihailidis A, Hadjistavropoulos T.
Algorithmic bias in clinical populations – evaluating and improving facial analysis technology in older adults with dementia. IEEE Access. 2019,
7: 25527–34.
34.
Trehan SK, Rancy SK, Johnsen PH, Hillstrom HJ, Lee SK, Wolfe SW.
At home photography-based method for measuring wrist range of motion. J Wrist Surg. 2017,
6: 280–4.
35.
Wang Q, Hunter S, Lee RL, Wang X, Chan SW.
Mobile rehabilitation support versus usual care in patients after total hip or knee arthroplasty: study protocol for a randomised controlled trial. Trials. 2022,
23: 553.
Xu YF, Zhang J, Zhang QM, Tao DC.
Vitpose: simple vision transformer baselines for human pose estimation. Adv Neural Inform Process Syst35, 2022 (Neurips 2022).
38.
Zhang F, Zhu X, Dai H, Ye M, Zhu C. Distribution-aware coordinate representation for human pose estimation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020: 7093–102.
