journal article·2025-12-25Open access

A 2D Hand Pose Estimation System Accuracy for Finger Tapping Test Monitoring: A Pilot Study

Saeid Edriss, Cristian Romagnoli, Rossella Rotondo, Maria Francesca De Pandis, Elvira Padua, Vincenzo Bonaiuto, Giuseppe Annino, Lloyd Smith

Applied Sciences· Volume 16· Issue 1

Abstract

Accurate and accessible motor function quantification is important for monitoring the movement disorders’ progression. Manual muscle testing models and wearable sensors can be costly or reduce degrees of freedom. Artificial intelligence, especially human pose estimation (PE), offers promising alternatives. This work aims to compare the accuracy of a 2D PE tool for the Finger Tapping Test (FTT) with a 3D infrared motion capture system (MoCap). PE tracked three anatomical landmarks (wrist, thumb, index finger), while reflective markers were placed at corresponding locations on both tools to measure wrist-centered angles. Different trials of slow and rapid FTT sessions were statistically analyzed by rank correlation analysis, Friedman, Bland–Altman, and Kruskal–Wallis to assess agreement and repeatability. PE and MoCap measurements showed no significant differences (p > 0.05), with high reliability (ICC 0.87–0.91), low variability (CV 6–8.6%), and negligible effect size. Bland–Altman slopes indicated minor amplitude-dependent bias, while RMSE (2.92–4.48°) and MAPE (6.38–8.22%) errors occurred in slow and rapid conditions. These results demonstrate that 2D PE provides a reliable, accessible, and low-cost alternative for quantifying finger movement. The findings suggest that PE can serve as an assistive method for monitoring motor function. Future studies can be population-level studies with patients with neurological disorders.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Stroke Rehabilitation and Recovery · Motor Control and Adaptation · Muscle activation and electromyography studies

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Sports Engineering Laboratory, Department of Industrial Engineering, University of Rome Tor Vergata, 00133 Rome, Italy

School of Mechanical and Materials Engineering, Washington State University, Pullman, WA 99163, USA

Department of Human Science and Promotion of Quality of Life, San Raffaele Open University, 00166 Rome, Italy

IRCCS San Raffaele Roma, 03043 Cassino, Italy

Human Performance Laboratory, Centre of Space Bio-Medicine, Department of Medicine Systems, University of Rome Tor Vergata, 00133 Rome, Italy

References (49)

Show source-provided references
1. Bohr, A., and Memarzadeh, K. (2020). The Rise of Artificial Intelligence in Healthcare Applications. Artificial Intelligence in Healthcare, Academic Press. Chapter 2.10.1016/B978-0-12-818438-7.00002-2 ↗
2. Artificial Intelligence-Based Video Monitoring of Movement Disorders in the Elderly: A Review on Current and Future Landscapes10.4103/singaporemedj.SMJ-2023-189 ↗
3. di Biase, L., Pecoraro, P.M., and Bugamelli, F. (2025). AI Video Analysis in Parkinson’s Disease: A Systematic Review of the Most Accurate Computer Vision Tools for Diagnosis, Symptom Monitoring, and Therapy Management. Sensors, 25.10.3390/s25206373 ↗
4. Al-Worafi, Y.M. (2024). Patient Care Related Issues in the Developing Countries: Monitoring Parameters. Handbook of Medical and Health Sciences in Developing Countries, Springer.10.1007/978-3-030-74786-2_245-1 ↗
5. The Role of Wearable Devices in Chronic Disease Monitoring and Patient Care: A Comprehensive Review
6. The Importance of Rating Scales in Measuring Patient-Reported Outcomes10.1186/1477-7525-10-80 ↗
7. Don’t Forget the Trunk in Duchenne Muscular Dystrophy Patients: More Muscle Weakness and Compensation than Expected10.1186/s12984-019-0515-y ↗
8. The Clinical Approach to Movement Disorders10.1038/nrneurol.2009.196 ↗
9. Prevalence of Joint Contractures and Muscle Weakness in People with Multiple Sclerosis10.3109/09638288.2013.854841 ↗
10. Review: Parkinson’s Disease: From Synaptic Loss to Connectome Dysfunction10.1111/nan.12297 ↗
11. Tremor and Rigidity in Patients with Parkinson’s Disease: Emphasis on Epidemiology, Pathophysiology and Contributing Factors10.2174/1871527320666211006142100 ↗
12. Progression of Parkinson’s Disease as Evaluated by Hoehn and Yahr Stage Transition Times10.1002/mds.22875 ↗
13. Movement Disorder Society Task Force Report on the Hoehn and Yahr Staging Scale: Status and Recommendations The Movement Disorder Society Task Force on Rating Scales for Parkinson’s Disease10.1002/mds.20213 ↗
14. Rotigotine May Improve Sleep Architecture in Parkinson’s Disease: A Double-Blind, Randomized, Placebo-Controlled Polysomnographic Study10.1016/j.sleep.2016.01.016 ↗
15. PDualNet: A Deep Learning Framework for Joint Prediction of Parkinson’s Disease Progression Subtype and MDS-UPDRS Scores10.1038/s41598-025-25812-9 ↗
16. Castro, K. (2024). Finger Tapping Test (FTT). Clinical Integration of Neuropsychological Test Results, CRC Press.10.1201/9781003309604-10 ↗
17. Grasp and Release Test for Tetraplegic Hand Assessment: An Update of the Grasp and Release Test10.1038/s41393-023-00907-0 ↗
18. Reliability of Manual Muscle Testing: A Systematic Review10.3233/IES-182178 ↗
19. Maggioni, V., Azevedo-Coste, C., Durand, S., and Bailly, F. (2025). Optimisation and Comparison of Markerless and Marker-Based Motion Capture Methods for Hand and Finger Movement Analysis. Sensors, 25.10.3390/s25041079 ↗
20. A Comprehensive Analysis of the Machine Learning Pose Estimation Models Used in Human Movement and Posture Analyses: A Narrative Review10.1016/j.heliyon.2024.e39977 ↗
21. A Comprehensive Survey on Human Pose Estimation Approaches10.1007/s00530-022-00980-0 ↗
22. Advancing Artistic Swimming Officiating and Performance Assessment: A Computer Vision Study Using MediaPipe10.2478/ijcss-2024-0010 ↗
23. Mroz, S., Baddour, N., McGuirk, C., Juneau, P., Tu, A., Cheung, K., and Lemaire, E. (2021, January 8–10). Comparing the Quality of Human Pose Estimation with BlazePose or OpenPose. Proceedings of the 2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART), Paris, France.10.1109/BioSMART54244.2021.9677850 ↗
24. Human Pose Estimation Using Deep Learning: A Systematic Literature Review10.3390/make5040081 ↗
25. Pose Estimation for Pickleball Players’ Kinematic Analysis through MediaPipe-Based Deep Learning: A pilot study10.1080/02640414.2025.2524283 ↗
26. Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., Chang, C.-L., Yong, M.G., and Lee, J. (2024, October 03). MediaPipe: A Framework for Building Perception Pipelines. Available online: https://arxiv.org/abs/1906.08172v1.
27. Characterizing Disease Progression in Parkinson’s Disease from Videos of the Finger Tapping Test10.1109/TNSRE.2024.3416446 ↗
28. Hand Rhythmic Tapping and Timing in Parkinson’s Disease10.1016/j.parkreldis.2003.10.001 ↗
29. Wand-Based Calibration of 3D Kinematic System10.1049/iet-cvi.2009.0004 ↗
30. Shapiro–Wilk Test with Known Mean
31. Compressed SENSE Single-Breath-Hold and Free-Breathing Cine Imaging for Accelerated Clinical Evaluation of the Left Ventricle10.1016/j.crad.2018.12.012 ↗
32. Armitage, P., Berry, G., and Matthews, J.N.S. (2013). Statistical Methods in Medical Research, John Wiley & Sons.
33. Ionan, A.C., Polley, M.-Y.C., McShane, L.M., and Dobbin, K.K. (2014). Comparison of Confidence Interval Methods for an Intra-Class Correlation Coefficient (ICC). BMC Med. Res. Methodol., 14.10.1186/1471-2288-14-121 ↗
34. DCE-MRI of the Liver: Effect of Linear and Non Linear Conversions on Hepatic Perfusion Quantification and Reproducibility10.1002/jmri.24341 ↗
35. Correcting the Effect Size of d for Range Restriction and Unreliability10.1177/109442810141003 ↗
36. Tilak, A., and Arivazhahan, A. (2022). Non-Parametric Tests. Introduction to Basics of Pharmacology and Toxicology: Volume 3: Experimental Pharmacology: Research Methodology and Biostatistics, Springer.10.1007/978-981-19-5343-9_62 ↗
37. Measuring Agreement in Method Comparison Studies10.1177/096228029900800204 ↗
38. When Can the Bland & Altman Limits of Agreement Method Be Used and When It Should Not Be Used10.1016/j.jclinepi.2021.04.004 ↗
39. Paddle Propulsive Force and Power Balance: A New Approach to Performance Assessment in Flatwater Kayaking10.1080/14763141.2022.2109505 ↗
40. Ishizuka, R., and Nagamune, K. (2023, January 1–4). Development of a Quantitative Evaluation System for Bradykinesia Using MediaPipe Hands. Proceedings of the 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Honolulu, HI, USA.10.1109/SMC53992.2023.10394293 ↗
41. Yu, T., Park, K.W., McKeown, M.J., and Wang, Z.J. (2023). Clinically Informed Automated Assessment of Finger Tapping Videos in Parkinson’s Disease. Sensors, 23.10.3390/s23229149 ↗
42. Comparison of Computational Pose Estimation Models for Joint Angles with 3D Motion Capture10.1016/j.jbmt.2024.04.033 ↗
43. Dill, S., Ahmadi, A., Grimmer, M., Haufe, D., Rohr, M., Zhao, Y., Sharbafi, M., and Hoog Antink, C. (2024). Accuracy Evaluation of 3D Pose Reconstruction Algorithms Through Stereo Camera Information Fusion for Physical Exercises with MediaPipe Pose. Sensors, 24.10.3390/s24237772 ↗
44. Finger and Foot Tapping Sensor System for Objective Motor Assessment10.2298/VSP150502323D ↗
45. Deep Learning-Based Human Pose Estimation: A Survey10.1145/3603618 ↗
46. Monje, M.H., Domínguez, S., Vera-Olmos, J., Antonini, A., Mestre, T.A., Malpica, N., and Sánchez-Ferro, Á. (2021). Remote Evaluation of Parkinson’s Disease Using a Conventional Webcam and Artificial Intelligence. Front. Neurol., 12.10.3389/fneur.2021.742654 ↗
47. Demby’s, J., Gao, Y., Shafiekhani, A., and DeSouza, G.N. (2019, January 6–9). Object Detection and Pose Estimation Using CNN in Embedded Hardware for Assistive Technology. Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence (SSCI), Xiamen, China.10.1109/SSCI44817.2019.9002767 ↗
48. Stenum, J., Cherry-Allen, K.M., Pyles, C.O., Reetzke, R.D., Vignos, M.F., and Roemmich, R.T. (2021). Applications of Pose Estimation in Human Health and Performance across the Lifespan. Sensors, 21.10.3390/s21217315 ↗
49. Edriss, S., Romagnoli, C., Caprioli, L., Bonaiuto, V., Padua, E., and Annino, G. (2025). Commercial Vision Sensors and AI-Based Pose Estimation Frameworks for Markerless Motion Analysis in Sports and Exercises: A Mini Review. Front. Physiol., 16.10.3389/fphys.2025.1649330 ↗