KineFeet: A Novel Depth Camera-Based Web Application for Diagnosing Foot Kinematics Alterations
Abstract
Background: Altered foot kinematics during walking, including reduced tibial inclination (the angle between the tibia and a vertical line during gait), as well as medial longitudinal arch (MLA) flattening and first metatarsophalangeal (MTP1) extension angle have been linked to various musculoskeletal disorders. Such abnormalities can have considerable clinical ramifications; hence, it is essential to identify them accurately.
Aim: We aimed to assess the diagnostic accuracy of KineFeet, a web-based application that employs a depth camera technique to detect foot kinematic changes for human gait analysis.
Methods: KineFeet and Kinovea® gait analysis software were used to diagnose altered foot kinematics in 89 healthy participants in this cross-sectional study. The main kinematic parameters investigated were Ankle Inclination angle at Terminal Stance (AI_TSt), Medial Longitudinal Arch angle at Terminal Stance (MLA_TSt), and Metatarsophalangeal angle 1 at maximal hallux extension (MTP_HE). Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the receiver-operating characteristic area under the curve (AUC) were computed.
Results: KineFeet showed excellent diagnostic performance. AI_TSt had a sensitivity of 88.23% and a specificity of 95.83%, with PPV and NPV values of 83.33% and 97.18%, respectively (AUC = 0.97). MLA_TSt and MTP_HE also had high discriminative abilities, with sensitivities of 79.54% and 79.00%, specificities of 95.55% and 91.30%, and attributed AUCs of 0.94 and 0.91, respectively.
Conclusion: KineFeet was able to accurately detect foot kinematics deformity during human gait. Its high diagnostic accuracy makes it a promising screening and evaluation tool. Further studies on human gait pathologies are warranted.
[2] Farzadi M, Safaeepour Z, Nabavi H, Cham MB, Mousavi ME. Effect of different placements of heel rockers on lower-limb joint biomechanics in healthy individuals. J Am Podiatr Med Assoc. 2018;108:231–235. doi: 10.7547/16-052
[3] Lee DV, Harris SL. Linking gait dynamics to the mechanical cost of legged locomotion. Front Robot AI. 2018;5:111. doi: 10.3389/frobt.2018.00111
[4] Takahashi T, Nagase T, Akatsuka S, Nakanowatari T, Ohtsu H, Yoshida S, et al. Effects of restriction of forefoot rocker functions by immobilisation of metatarsophalangeal joints on kinematics and kinetics during walking. Foot. 2021;49:101743. doi: 10.1016/j.foot.2020.101743
[5] van Kouwenhove L, Verkerke GJ, Postema K, Dekker R, Hijmans JM. Effect of different forefoot rocker radii on lower-limb joint biomechanics in healthy individuals. Gait Posture. 2021;86:150–156. doi: 10.1016/j.gaitpost.2021.03.008
[6] Cimorelli A, Patel A, Karakostas T, Cotton R. Validation of portable in-clinic video-based gait analysis for prosthesis users. Sci Rep. 2024;14:3840. doi: 10.1038/s41598-024-53217-7
[7] Paterson KL, Clark RA, Mullins AK, Bryant AL, Mentiplay BF. Predicting dynamic foot function from static foot posture: comparison between visual assessment, motion analysis, and a commercially available depth camera. J Orthop Sports Phys Ther. 2015;45:789–798. doi: 10.2519/jospt.2015.5616
[8] Kusuda K, Matsubara S, Noguchi D, Kuwahara M, Hamasaki H, Miwa T, et al. Concurrent validity of depth-sensor-based quantification of compensatory movements during the swing phase of gait in healthy individuals. Biomechanics. 2024;4:411–427. doi: 10.3390/biomechanics4030028
[9] Anestherita F, Tulaar A, Rachmawati M, Yunir E, Harbuwono DS, Wedhani R, et al. Reliability and validity of Kinefeet: A prototype web application utilizing depth camera technology for clinically relevant foot kinematics evaluation. SSRN Electron J. 2025; doi:10.2139/ssrn.5289332
[10] Perry J, Burnfield JM. Gait Analysis: Normal and Pathological Function. J Sports Sci Med. 2010;9:353.
[11] Bonnefoy-Mazure A, Armand S. Normal gait. In: Canavese F, Deslandes J, editors. Orthopedic management of children with cerebral palsy. New York: Nova Science Publishers; 2015. p. 567.
[12] Souza RB. An evidence-based videotaped running biomechanics analysis. Phys Med Rehabil Clin N Am. 2015;27:217–236. doi: 10.1016/j.pmr.2015.08.006
[13] Xu R, Zuo H, Ji Y, Li Q, Wang Z, Liu H, et al. Effects of short-term limitation of movement of the first metatarsophalangeal joint on the biomechanics of the ipsilateral hip, knee, and ankle joints during walking. Med Sci Monit. 2021;27:e930081. doi: 10.12659/msm.930081
[14] Man HS, Lam W, Lee J, Capio CM, Leung KL. Is passive metatarsophalangeal joint stiffness related to leg stiffness, vertical stiffness, and running economy during sub-maximal running? Gait Posture. 2016;49:303–308. doi: 10.1016/j.gaitpost.2016.07.004
[15] Mahieu C, Salvia P, Beyer B, Rooze M, Feipel V, Jan JSV. Metatarsal arch deformation and forefoot kinematics during gait in asymptomatic subjects. Int Biomech. 2019;6:75–84. doi: 10.1080/23335432.2019.1642142
[16] Tweed JL, Campbell JA, Thompson R, Curran MJ. The function of the midtarsal joint. Foot. 2008;18:106–112. doi: 10.1016/j.foot.2008.01.002
[17] Cote KP, Brunet ME, Gansneder BM, Shultz SJ. Effects of pronated and supinated foot postures on static and dynamic postural stability. J Athl Train. 2005;40:41–46.
[18] Shin GC, Kim T, Pyi S, Chun W, Park S. The relationship between features of foot posture, thickness of intrinsic foot muscles, and dynamic postural stability. Exerc Sci. 2023;32:275–285. doi: 10.15857/ksep.2023.00108
[19] Ness ME, Long J, Marks RD, Harris GF. Foot and ankle kinematics in patients with posterior tibial tendon dysfunction. Gait Posture. 2009;27:331–339. doi: 10.1016/j.gaitpost.2007.04.014
[20] Morrison KE, Kaminski TW. Foot characteristics in association with inversion ankle injury. J Athl Train. 2007;42:135–142.
[21] Cronin NJ, Rantalainen T, Ahtiainen JP, Hynynen E, Waller B. Markerless motion capture can provide reliable and valid assessments of lower limb kinematics and kinetics in applied settings: A systematic review. Gait Posture. 2025;104:110–22. doi:10.1016/j.gaitpost.2025.01.002.
[22] Brambilla C, Guzzetti S, Folcio T, Brambilla L, Maggioni D, Ferrante S. Performance evaluation of Azure Kinect for dynamic and kinematic measurements. Heliyon. 2023;9(8):e19102. doi:10.1016/j.heliyon.2023.e19102.
[23] Yeung LF, Yang Z, Cheng KC, Du D, Tong KY. Evaluation of the Microsoft Azure Kinect and Orbbec Astra Pro depth cameras for motion capture. Gait Posture. 2021;86:285–92. doi:10.1016/j.gaitpost.2021.03.025.
[24] Thomas J, Yelamarthi K, Dutt V, Aranha VP, Uddin M. Validity of the Azure Kinect for sit-to-stand kinematics compared with a Vicon motion capture system. Gait Posture. 2022;91:42–9. doi:10.1016/j.gaitpost.2021.09.003.
[25] Chun S, Park YJ, Kim J, Kim HS, Kim HY. Measurement of arch parameters from a foot image using an RGB-D camera. Sensors (Basel). 2017;17(3):559. doi:10.3390/s17030559
[26] Rogati G, Leardini A, Berti L, Ortolani M, Caravaggi P. Validation of a Kinect-based 3D foot scanner for clinical and research applications. J Foot Ankle Res. 2019;12:41. doi:10.1186/s13047-019-0349-1.
[27] Fernández-González P, Koutsou A, Cuesta-Gómez A, Carratalá-Tejada M, Miangolarra-Page JC, Molina-Rueda F. Reliability of Kinovea® software and agreement with a three-dimensional motion system for gait analysis in healthy subjects. Sensors. 2020;20:3154. doi: 10.3390/s20113154
[28] Anestherita F, Hasbiandra RA, Kusumaningsih W, Lakmudin A, Handoko H. Inter-observer reliability of Kinovea® software in dynamic foot posture analysis in a healthy population. F1000Research. 2024;13:1533. doi: 10.12688/f1000research.157736.1
| Issue | Articles in Press | |
| Section | Research Article(s) | |
| Keywords | ||
| Gait analysis; Foot; Computer-assisted diagnosis; Kinematics | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |

