Skip to main content

Advertisement

Automation of observational gait assessment through an optical 3D motion system and transformers

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Assessment of human gait is a useful diagnostic tool for identifying musculoskeletal abnormalities and disorders. Most clinicians use qualitative approaches based on visual observations to analyze gait, leading to repetitive exercises that require subjective evaluation. This study proposes a system to automate and objectify traditional observational gait tests using a transformer encoder network that analyzes data captured with a 3D optical motion system. This preliminary study focused on the Tinetti test, or Performance-Oriented Mobility Assessment for gait evaluation (POMA-G), using data collected with an OptiTrack camera system. An optical motion capture system consisting of eight OptiTrack Prime 13-W cameras, sampled at 60 Hz and synchronized with the Clinical 3D Motion Analysis (3DMA) software was used. Anthropometric measurements of the participants were recorded and their gait movements were captured while simulating various pathologies evaluated in the POMA-G test. The algorithms were designed and implemented in an artificial neural network model based on transformer process information to monitor and classify the gait components. On average, the machine learning models achieved an accuracy of 97.56% ± 4.79%, F1 score of 96.39% ± 7.95%, and area under the receiver operating characteristic curve (AUC-ROC) value of 99.29% ± 1.81%, demonstrating a high capability to identify and classify the gait components evaluated using the POMA-G scale. Automating the observational evaluation of gait using a 3D optical motion system and machine learning methods offers a quantitative and objective approach to gait analysis. This system not only promises to facilitate more accurate diagnoses and effectively monitor gait-related disorders, but also highlights the potential of motion capture technology and machine learning for clinical gait assessment. This study establishes a foundation for future research aimed at improving the accuracy and applicability of automatic gait assessment tools.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Notes

  1. https://optitrack.com

  2. https://www.stt-systems.com/motion-analysis/3d-optical-motion-capture/clinical-3dma/

References

  1. Pearson OR, Busse ME, Van Deursen RWM, Wiles CM (2004) Quantification of walking mobility in neurological disorders. QJM: Int J Med 97(8):463–475. https://doi.org/10.1093/qjmed/hch084

    Article  MATH  Google Scholar 

  2. Alkhatib R, Diab MO, Corbier C, Badaoui ME (2020) Machine learning algorithm for gait analysis and classification on early detection of Parkinson. IEEE Sens Lett 4(6). https://doi.org/10.1109/LSENS.2020.2994938

  3. González I, Navarro FJ, Fontecha J, Cabañero-Gómez L, Hervás R (2019) An Internet of Things infrastructure for gait characterization in assisted living environments and its application in the discovery of associations between frailty and cognition. Int J Distrib Sens Netw 15(10). https://doi.org/10.1177/1550147719883544

  4. Moissenet F, Armand S (2015) Qualitative and quantitative methods of assessing gait disorders. In: Orthopedic management of children with cerebral palsy: a comprehensive approach, pp 215–240

  5. Harris GF, Wertsch JJ (1994) Procedures for gait analysis. Arch Phys Med Rehabil 75(2):216–225. https://doi.org/10.1016/0003-9993(94)90399-9

    Article  MATH  Google Scholar 

  6. Ferrarello F, Bianchi VAM, Baccini M, Rubbieri G, Mossello E, Cavallini MC, Marchionni N, Di Bari M (2013) Tools for observational gait analysis in patients with stroke: a systematic review. Phys Ther 93(12):1673–1685. https://doi.org/10.2522/ptj.20120344

    Article  Google Scholar 

  7. Podsiadlo D (1991) The timed “Up & Go’’: a test of basic functional mobility for frail elderly persons. J Am Geriatr Soc 39(2):142–148. https://doi.org/10.1111/j.1532-5415.1991.tb01616.x

    Article  MATH  Google Scholar 

  8. Daly JJ, Nethery J, McCabe JP, Brenner I, Rogers J, Gansen J, Butler K, Burdsall R, Roenigk K, Holcomb J (2009) Development and testing of the Gait Assessment and Intervention Tool (G.A.I.T.): a measure of coordinated gait components. J Neurosci Methods 178(2):334–339. https://doi.org/10.1016/j.jneumeth.2008.12.016

    Article  Google Scholar 

  9. Wolfson L, Whipple R, Amerman P, Tobin JN (1990) Gait assessment in the elderly: a gait abnormality rating scale and its relation to falls. J Gerontol 45(1):12–19. https://doi.org/10.1093/geronj/45.1.M12

    Article  Google Scholar 

  10. Rodriquez AA, Black PO, Kile KA, Sherman J, Stellberg B, McCormick J, Roszkowski J, Swiggum E (1996) Gait training efficacy using a home-based practice model in chronic hemiplegia. Arch Phys Med Rehabil 77(8):801–805. https://doi.org/10.1016/S0003-9993(96)90260-9

    Article  Google Scholar 

  11. Tinetti ME (1986) Performance-oriented assessment of mobility problems in elderly patients. J Am Geriatr Soc 34(2):119–126. https://doi.org/10.1111/j.1532-5415.1986.tb05480.x

    Article  MATH  Google Scholar 

  12. Abbruzzese LD (1998) The tinetti performance-oriented mobility assessment tool. Am J Nurs 98(12):16–16. https://doi.org/10.1097/00000446-199812000-00012

    Article  MATH  Google Scholar 

  13. Tinetti ME, Franklin Williams T, Mayewski R (1986) Fall risk index for elderly patients based on number of chronic disabilities. Am J Med 80(3):429–434. https://doi.org/10.1016/0002-9343(86)90717-5

    Article  Google Scholar 

  14. Villa Moreno A, Gutiérrez Gutiérrez E, Pérez Moreno JC (2008) Consideraciones para el análisis de la marcha humana. Técnicas de videogrametría, electromiografía y dinamometría. Revista Ingeniería Biomédica 2(3):16–26

    Google Scholar 

  15. Datta D, Heller B, Howitt J (2005) A comparative evaluation of oxygen consumption and gait pattern in amputees using Intelligent Prostheses and conventionally damped knee swing-phase control. Clin Rehabil 19(4):398–403. https://doi.org/10.1191/0269215505cr805oa

    Article  Google Scholar 

  16. McGinley JL, Goldie PA, Greenwood KM, Olney SJ (2003) Accuracy and reliability of observational gait analysis data: jugments of push-off in gait after stroke. Phys Ther 83(2):146–160. https://doi.org/10.1093/ptj/83.2.146

    Article  Google Scholar 

  17. Sharma Y, Cheung L, Patterson KK, Iaboni A (2024) Factors influencing the clinical adoption of quantitative gait analysis technology with a focus on clinical efficacy and clinician perspectives: a scoping review. Gait Posture 108:228–242. https://doi.org/10.1016/j.gaitpost.2023.12.003

    Article  Google Scholar 

  18. Subbiah V (2023) The next generation of evidence-based medicine. Nat Med 29(1):49–58. https://doi.org/10.1038/s41591-022-02160-z

    Article  MATH  Google Scholar 

  19. Aich S, Pradhan PM, Chakraborty S, Kim H-C, Kim H-T, Lee H-G, Kim IH, Joo M-I, Jong Seong S, Park J (2020) Design of a machine learning-assisted wearable accelerometer-based automated system for studying the effect of dopaminergic medicine on gait characteristics of Parkinson’s patients. J Healthc Eng 2020. https://doi.org/10.1155/2020/1823268

  20. Lau H-y, Tong K-y, Zhu H (2009) Support vector machine for classification of walking conditions of persons after stroke with dropped foot. Hum Mov Sci 28(4):504–514. https://doi.org/10.1016/j.humov.2008.12.003

    Article  MATH  Google Scholar 

  21. Yan Q, Huang J, Wu D, Yang Z, Wang Y, Hasegawa Y, Fukuda T (2022) Intelligent Gait analysis and evaluation system based on cane robot. IEEE Trans Neural Syst Rehabil Eng 30:2916–2926. https://doi.org/10.1109/TNSRE.2022.3213823

    Article  MATH  Google Scholar 

  22. Cippitelli E, Gasparrini S, Spinsante S, Gambi E (2015) Kinect as a tool for gait analysis: validation of a real-time joint extraction algorithm working in side view. Sensors (Switzerland) 15(1):1417–1434. https://doi.org/10.3390/s150101417

    Article  Google Scholar 

  23. Wang Y, Zou Q, Tang Y, Wang Q, Ding J, Wang X, Shi C-JR (2022) SAIL: a deep-learning-based system for automatic Gait assessment from TUG videos. IEEE Trans Hum-Mach Syst 52(1):110–122. https://doi.org/10.1109/THMS.2021.3123232

    Article  MATH  Google Scholar 

  24. Soubra R, Mourad-Chehade F, Chkeir A (2023) Automation of the timed up and go test using a doppler radar system for Gait and balance analysis in elderly people. J Healthc Eng 2023. https://doi.org/10.1155/2023/2016262

  25. Li Y, Zhang P, Zhang Y, Miyazaki K (2019) Gait analysis using stereo camera in daily environment. In: Proceedings of the annual international conference of the IEEE engineering in medicine and biology society, EMBS, pp 1471–1475. https://doi.org/10.1109/EMBC.2019.8857494

  26. Zhang Y, Li S, Zhou Y, Liu J (2020) Lower limb motor function assessment based on TensorFlow convolutional neural network and kernel entropy component analysis–local tangent space alignment. Adv Mech Eng 12(7). https://doi.org/10.1177/1687814020942650

  27. Ma J (2023) Predicting TUG score from Gait characteristics with video analysis and machine learning. Lect Notes Electr Eng 1082 LNEE:1–12. https://doi.org/10.1007/978-981-99-6187-0_1

  28. Savoie P, Cameron JAD, Kaye ME, Scheme EJ (2020) Automation of the timed-up-and-go test using a conventional video camera. IEEE J Biomed Health Inform 24(4):1196–1205. https://doi.org/10.1109/JBHI.2019.2934342

    Article  MATH  Google Scholar 

  29. Hsu Y-C, Wang H, Zhao Y, Chen F, Tsui K-L (2021) Automatic recognition and analysis of balance activity in community-dwelling older adults: algorithm validation. J Med Internet Res 23(12). https://doi.org/10.2196/30135

  30. Kadaba MP, Ramakrishnan HK, Wootten ME (1990) Measurement of lower extremity kinematics during level walking. J Orthop Res 8(3):383–392. https://doi.org/10.1002/jor.1100080310

    Article  MATH  Google Scholar 

  31. Hogan PS, Chen SX, Teh WW, Chib VS (2020) Neural mechanisms underlying the effects of physical fatigue on effort-based choice. Nat Commun 11(1). https://doi.org/10.1038/s41467-020-17855-5

  32. Savitzky A, Golay MJE (1964) Smoothing and differentiation of data by simplified least squares procedures. Anal Chem 36(8):1627–1639. https://doi.org/10.1021/ac60214a047

    Article  MATH  Google Scholar 

  33. Davis RB III, Õunpuu S, Tyburski D, Gage JR (1991) A gait analysis data collection and reduction technique. Hum Mov Sci 10(5):575–587. https://doi.org/10.1016/0167-9457(91)90046-Z

    Article  MATH  Google Scholar 

  34. Collins TD, Ghoussayni SN, Ewins DJ, Kent JA (2009) A six degrees-of-freedom marker set for gait analysis: repeatability and comparison with a modified helen hayes set. Gait Posture 30(2):173–180. https://doi.org/10.1016/j.gaitpost.2009.04.004

    Article  MATH  Google Scholar 

  35. Moore KL, Agur AMR, Dalley AF II (2012) Essential clinical anatomy, 4th edn. Essential Clinical Anatomy: Fourth Edition, p 703

  36. González I, Fontecha J, Bravo J (2019) Relationship between stride interval variability and aging: use of linear and non-linear estimators for gait variability assessment in assisted living environments. J Ambient Intell Humaniz Comput 10(6):2095–2109. https://doi.org/10.1007/s12652-017-0608-z

    Article  Google Scholar 

  37. John GH, Kohavi R, Pfleger K (1994) Irrelevant features and the subset selection problem. In: Proceedings of the 11th international conference on machine learning, ICML 1994, pp 121–129. https://doi.org/10.1016/B978-1-55860-335-6.50023-4

  38. Iguyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182

    MATH  Google Scholar 

  39. Sánchez-Maroño N, Alonso-Betanzos A, Tombilla-Sanromán M (2007) Filter methods for feature selection - a comparative study. Lect Notes Comput Sci (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics) 4881 LNCS:178–187. https://doi.org/10.1007/978-3-540-77226-2_19

  40. Kohavi R, John GH (1997) Wrappers for feature subset selection. Artif Intell 97(1–2):273–324. https://doi.org/10.1016/s0004-3702(97)00043-x

    Article  MATH  Google Scholar 

  41. Breiman L (2001) Random forests. Mach Learn 45(1):5–32. https://doi.org/10.1023/A:1010933404324

    Article  MATH  Google Scholar 

  42. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, vol 2017-December, pp 5999–6009

  43. Wen Q, Zhou T, Zhang C, Chen W, Ma Z, Yan J, Sun L (2023) Transformers in time series: a survey. In: IJCAI International Joint Conference on Artificial Intelligence, vol 2023-August, pp 6778–6786

  44. Lee S-E, Yoo H, Chung K (2024) Pose pattern mining using transformer for motion classification. Appl Intell 54(5):3841–3858. https://doi.org/10.1007/s10489-024-05325-0

    Article  MATH  Google Scholar 

  45. Zerveas G, Jayaraman S, Patel D, Bhamidipaty A, Eickhoff C (2021) A transformer-based framework for multivariate time series representation learning. In: Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining, pp 2114–2124. https://doi.org/10.1145/3447548.3467401

  46. Liu Y, Zhang Y, Wang Y, Hou F, Yuan J, Tian J, Zhang Y, Shi Z, Fan J, He Z (2024) A survey of visual transformers. IEEE Trans Neural Netw Learn Syst 35(6):7478–7498. https://doi.org/10.1109/TNNLS.2022.3227717

    Article  MATH  Google Scholar 

  47. Mogan JN, Lee CP, Lim KM, Muthu KS (2022) Gait-ViT: gait recognition with vision transformer. Sensors 22(19). https://doi.org/10.3390/s22197362

  48. Stapor K (2018) Evaluating and comparing classifiers: review some recommendations and limitations. Adv Intell Syst Comput 578:12–21. https://doi.org/10.1007/978-3-319-59162-9_2

  49. Sokolova M, Japkowicz N, Szpakowicz S (2006) Beyond accuracy, f-score and roc: a family of discriminant measures for performance evaluation. In: AAAI workshop - technical report, vol WS-06-06, pp 24–29

Download references

Acknowledgements

We extend our sincere gratitude to all volunteers who participated in this study. Their time, effort, and commitment were instrumental in the success of this research.

Funding

This research was funded by MCIN/AEI/10.13039/501100011033 and “European Union NextGenerationEU/PRTR” through grant PID2022-142388OA-I00 (“Just move!”: Early detection of MCI through human-movement analysis in everyday life JUST-MOVE), running from September 1, 2023, to August 31, 2026; by MINISTERIO DE CIENCIA, INNOVACIÓN Y UNIVERSIDADES and FEDER through grant EQC2019-006053-P (WeCareLab); and by the UNIVERSITY OF CASTILLA-LA MANCHA through the 2022-PRED-20651 predoctoral contract.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to David Carneros-Prado.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix A.   Kinematic parameters

Appendix A.   Kinematic parameters

Table 9 Kinematic parameters and their corresponding planes
Table 10 Input features of the models

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Carneros-Prado, D., González-Velázquez, S., Dobrescu, C.C. et al. Automation of observational gait assessment through an optical 3D motion system and transformers. Appl Intell 55, 250 (2025). https://doi.org/10.1007/s10489-024-06163-w

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10489-024-06163-w

Keywords