Key words: fall risk diagnostics; gait disorders; balance disorders; movement biomechanics; artificial intelligence.
- Abstract
- References
- How to cite
The aim of the study was to develop an artificial intelligence model for predicting the probability of falls based on the analysis of video recordings of gait patterns.
Materials and Methods. The study involved 187 patients (median age 59 years) with neurological diseases of various etiologies who complained of impaired balance and unsteadiness while walking. All participants underwent video recording of their movements using a smartphone during a 10-meter walk test and Timed Up and Go test. Based on the analysis of 2077 steps recorded in 122 patients, an algorithm for fall risk stratification was developed using the YOLO-NAS Pose M architecture and a two-layer machine learning model.
Results. The final model when analyzing video data achieved 76% accuracy in risk prediction, with an average absolute error of time parameter prediction of 1.445 s. The following parameters were identified as key biomechanical predictors of fall risk: step base width at the ankle joint level, lateral trunk sway, step base width at the knee joint level, vertical foot clearance during the swing phase, and temporal gait characteristics.
1. Hausdorff J.M., Nelson M.E., Kaliton D., Layne J.E., Bernstein M.J., Nuernberger A., Singh M.A. Etiology and modification of gait instability in older adults: a randomized controlled trial of exercise. J Appl Physiol (1985) 2001; 90(6): 2117–2129, https://doi.org/10.1152/jappl.2001.90.6.2117.
2. Ambrose A.F., Paul G., Hausdorff J.M. Risk factors for falls among older adults: a review of the literature. Maturitas 2013; 75(1): 51–61, https://doi.org/10.1016/j.maturitas.2013.02.009.
3. Bergen G., Stevens M.R., Burns E.R. Falls and fall injuries among adults aged ≥65 years — United States, 2014. MMWR Morb Mortal Wkly Rep 2016; 65(37): 993–998, https://doi.org/10.15585/mmwr.mm6537a2.
4. Moreland B., Kakara R., Henry A. Trends in nonfatal falls and fall-related injuries among adults aged ≥65 years — United States, 2012–2018. MMWR Morb Mortal Wkly Rep 2020; 69(27): 875–881, https://doi.org/10.15585/mmwr.mm6927a5. Erratum in: MMWR Morb Mortal Wkly Rep 2023; 72(18): 499, https://doi.org/10.15585/mmwr.mm7218a6.
5. Tkacheva O.N. Aging management and geriatric service development: Russia’s strategy in the era of demographic challenges. Russian Journal of Geriatric Medicine 2025; 2: 88–89.
6. Florence C.S., Bergen G., Atherly A., Burns E., Stevens J., Drake C. Medical costs of fatal and nonfatal falls in older adults. J Am Geriatr Soc 2018; 66(4): 693–698, https://doi.org/10.1111/jgs.15304.
7. Thurman D.J., Stevens J.A., Rao J.K.; Quality Standards Subcommittee of the American Academy of Neurology. Practice parameter: assessing patients in a neurology practice for risk of falls (an evidence-based review): report of the quality standards subcommittee of the American Academy of Neurology. Neurology 2008; 70(6): 473–479, https://doi.org/10.1212/01.wnl.0000299085.18976.20.
8. Ramirez-Zamora A., Tsuboi T. Hospital management of Parkinson disease patients. Clinics in Geriatric Medicine 2020; 36(1): 173–181, https://doi.org/10.1016/j.cger.2019.09.009.
9. Heikkilä A., Lehtonen L., Junttila K. Fall rates by specialties and risk factors for falls in acute hospital: a retrospective study. J Clin Nurs 2022; 32(15–16): 4868–4877, https://doi.org/10.1111/jocn.16594.
10. Saverino A., Moriarty A., Rantell K., Waller D., Ayres R., Playford D. A qualitative description of falls in a neuro-rehabilitation unit: the use of a standardised fall report including the International Classification of Functioning (ICF) to describe activities and environmental factors. Disability and Rehabilitation 2014; 37(4): 355–362, https://doi.org/10.3109/09638288.2014.923520.
11. Benson C., Lusardi P. Neurologic antecedents to patient falls. Journal of Neuroscience Nursing 1995; 27(6): 331–337, https://doi.org/10.1097/01376517-199512000-00003.
12. Kruschke C., Butcher H.K. Evidence-based practice guideline: fall prevention for older adults. J Gerontol Nurs 2017; 43(11): 15–21, https://doi.org/10.3928/00989134-20171016-01.
13. Park S.H. Tools for assessing fall risk in the elderly: a systematic review and meta-analysis. Aging Clin Exp Res 2018; 30(1): 1–16, https://doi.org/10.1007/s40520-017-0749-0.
14. Miura T., Kanoya Y. Fall Risk assessment and prevention strategies in nursing homes: a narrative review. Healthcare 2025; 13(4): 357, https://doi.org/10.3390/healthcare13040357.
15. Jewell V.D., Capistran K., Flecky K., Qi Y., Fellman S. Prediction of falls in acute care using the Morse Fall Risk Scale. Occup Ther Health Care 2020; 34(4): 307–319, https://doi.org/10.1080/07380577.2020.1815928.
16. Huang X., Yan J., Yang T., Yi Q., Shen Z., Yang G. Cost-effectiveness of Morse Fall Scale assessment in fall prevention care in hospitalized patients. Zhong Nan Da Xue Xue Bao Yi Xue Ban 2021; 46(5): 529–535, https://doi.org/10.11817/j.issn.1672-7347.2021.200332.
17. Sardo P.M., Simões C.S., Alvarelhão J.J., Simões J.F., Melo E.M. Fall risk assessment: retrospective analysis of Morse Fall Scale scores in Portuguese hospitalized adult patients. Appl Nurs Res 2016; 31: 34–40, https://doi.org/10.1016/j.apnr.2015.11.013.
18. Tang Y.T., Romero-Ortuno R. Using explainable AI (XAI) for the prediction of falls in the older population. Algorithms 2022; 15(10): 353, https://doi.org/10.3390/a15100353.
19. Eichler N., Raz S., Toledano-Shubi A., Livne D., Shimshoni I., Hel-Or H. Automatic and efficient fall risk assessment based on machine learning. Sensors 2022; 22(4): 1557, https://doi.org/10.3390/s22041557.
20. Singh D.K.A., Goh J.W., Shaharudin M.I., Shahar S. A mobile app (FallSA) to identify fall risk among malaysian community-dwelling older persons: development and validation study. JMIR Mhealth Uhealth 2021; 9(10): e23663, https://doi.org/10.2196/23663.
21. González-Castro A., Leirós-Rodríguez R., Prada-García C., Benítez-Andrades J.A. The applications of artificial intelligence for assessing fall risk: systematic review. J Med Internet Res 2024, 26: e54934, https://doi.org/10.2196/54934.
22. Iseki C., Hayasaka T., Yanagawa H., Komoriya Y., Kondo T., Hoshi M., Fukami T., Kobayashi Y., Ueda S., Kawamae K., Ishikawa M., Yamada S., Aoyagi Y., Ohta Y. Artificial intelligence distinguishes pathological gait: the analysis of markerless motion capture gait data acquired by an iOS application (TDPT-GT). Sensors (Basel) 2023; 23(13): 6217, https://doi.org/10.3390/s23136217.
23. Khan M.A., Kadry S., Parwekar P., Damaševičius R., Mehmood A., Khan J.A., Naqvi S.R. Human gait analysis for osteoarthritis prediction: a framework of deep learning and kernel extreme learning machine. Complex Intell Syst 2021; 9(3): 2665–2683, https://doi.org/10.1007/s40747-020-00244-2.
24. Ren M., Tao M., Hu X., Liu X., Li Q., Huang Y. Towards more efficient depression risk recognition via gait. arXiv 2023, https://doi.org/10.48550/arXiv.2310.06283.
25. Zhou L., Meng X., Liu Z., Wu M., Gao Z., Wan P. Human pose-based estimation, tracking and action recognition with deep learning: a survey. arXiv 2023, https://doi.org/10.13140/RG.2.2.13493.45287.
26. Podsiadlo D., Richardson S. The timed “Up & Go”: a test of basic functional mobility for frail elderly persons. J American Geriatrics Society 1991; 39(2): 142–148, https://doi.org/10.1111/j.1532-5415.1991.tb01616.x.
27. Moore J.L., Potter K., Blankshain K., Kaplan S.L., OʼDwyer L.C., Sullivan J.E. A core set of outcome measures for adults with neurologic conditions undergoing rehabilitation: a clinical practice guideline. J Neurol Phys Ther 2018; 42(3): 174–220, https://doi.org/10.1097/NPT.0000000000000229.
28. Cao Z., Simon T., Wei S.-E., Sheikh Y. Realtime multi-person 2D pose estimation using part affinity fields. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA; 2017; p. 1302–1310, https://doi.org/10.1109/CVPR.2017.143.
29. Terven J., Córdova-Esparza D.M., Romero-González J.A. A comprehensive review of YOLO architectures in computer vision: from YOLOv1 to YOLOv8 and YOLO-NAS. MAKE 2023; 5(4): 1680–1716, https://doi.org/10.3390/make5040083.
30. Raja M.A., Loughran R., McCaffery F. Performance analysis of YOLO-NAS SoTA models on CAL tool detection. TechRxiv 2025, https://doi.org/10.36227/techrxiv.170474405.56692658/v2.
31. Bazarevsky V., Grishchenko I., Raveendran K., Zhu T.L., Zhang F., Grundmann M. BlazePose: on-device real-time body pose tracking. arXiv 2020, https://doi.org/10.48550/arXiv.2006.10204.
32. Lin T.Y., Maire M., Belongie S., Hays J., Perona P., Ramanan D., Dollár P., Zitnick C.L. Microsoft COCO: common objects in context. In: Fleet D., Pajdla T., Schiele B., Tuytelaars T. (eds). Computer Vision — ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8693. Springer, Cham; 2014, https://doi.org/10.1007/978-3-319-10602-1_48.
33. Tkacheva O.N., Kotovskaya Yu.V., Runikhina N.K., Frolova E.V., Naumov A.V., Vorobyeva N.M., Ostapenko V.S., Mkhitaryan E.A., Sharashkina N.V., Tyukhmenev E.A., Pereverzev A.P., Dudinskaya E.N. Clinical guidelines on frailty. Russian Journal of Geriatric Medicine 2020; 1: 11–46, https://doi.org/10.37586/2686-8636-1-2020-11-46.
34. Shumway-Cook A., Brauer S., Woollacott M. Predicting the probability for falls in community-dwelling older adults using the timed Up & Go Test. Phys Ther 2000; 80(9): 896–903, https://doi.org/10.1093/ptj/80.9.896.
35. Kirichenko O.A., Slotina A.E., Nuzhnyy E.P., Ikonnikova E.S., Suponeva N.A. Fall risk associated with motor function in patients with hereditary cerebellar ataxias. Neuromuscular Diseases 2025; 15; 3: 22–37, https://doi.org/10.17650/2222-8721-2025-15-3-22-37.
36. Belyankin G.A., Zabello M.A. Sravnitel'nyy analiz podkhodov mashinnogo obucheniya dlya otsenki riska padeniya na osnove kharakteristik shaga. V kn.: Lomonosovskie chteniya [A comparative analysis of machine learning approaches for fall risk assessment based on step characteristics. In: Lomonosov readings]. Moscow; 2025; p. 67–68.
37. Saverino A., Moriarty A., Playford D. The risk of falling in young adults with neurological conditions: a systematic review. Disabil Rehabil 2014; 36(12): 963–977, https://doi.org/10.3109/09638288.2013.829525.
38. Lim Z.K., Connie T., Goh M.K.O., Saedon N.B. Fall risk prediction using temporal gait features and machine learning approaches. Front Artif Intell 2024; 7: 1425713, https://doi.org/10.3389/frai.2024.1425713.
39. Angsuwan C., Agrawal D.K., Usaha W., Pojprapai S., Wattanapan P. Accelerometer-based fall risk prediction in elderly using machine learning: effect of feature combination and balanced dataset. Procedia Computer Science 2024; 235: 326–334, https://doi.org/10.1016/j.procs.2024.04.033.
40. Skvortsov D.V. Klinicheskiy analiz dvizheniy. Analiz pokhodki [Clinical movement analysis. Gait analysis]. Ivanovo; 1996; 344 p.
41. Garcia-de-Villa S., Ruiz L.R., Neira G.G., Alvarez M.N., Huertas-Hoyas E., Del-Ama A.J., Rodriguez M.C., Seco F., Jimenez A.R. Validation of an IMU-based gait analysis method for assessment of fall risk against traditional methods. IEEE J Biomed Health Inform 2025; 29(1): 107–117, https://doi.org/10.1109/JBHI.2024.3434973.
42. Schniepp R., Huppert A., Decker J., Schenkel F., Schlick C., Rasoul A., Dieterich M., Brandt T., Jahn K., Wuehr M. Fall prediction in neurological gait disorders: differential contributions from clinical assessment, gait analysis, and daily-life mobility monitoring. J Neurol 2021; 268(9): 3421–3434, https://doi.org/10.1007/s00415-021-10504-x.
43. Maudsley-Barton S., Yap M.H. Objective falls risk assessment using markerless motion capture and representational machine learning. Sensors (Basel, Switzerland) 2024; 24(14): 4593, https://doi.org/10.3390/s24144593.
44. Sakane N., Yamauchi K., Kutsuna I., Suganuma A., Domichi M., Hirano K., Wada K., Ishimaru M., Hosokawa M., Izawa Y., Matsumura Y., Hozumi J. Application of machine learning for detecting high fall risk in middle-aged workers using video-based analysis of the first 3 steps. J Occup Health 2025; 67(1); uiae075, https://doi.org/10.1093/joccuh/uiae075.