Harshit,
Sumit,
Ashish Kumar,
- Student, Department of Physiotherapy, Guru Kashi University, Talwandi Sabo, Bathinda, Punjab, India
- Student, Department of Physiotherapy, Guru Kashi University, Talwandi Sabo, Bathinda, Punjab, India
- Clinical Physiotherapist, Department of Physiotherapy, Guru Kashi University, Talwandi Sabo, Bathinda, Punjab, India
Abstract
This review synthesizes current research on the application of artificial intelligence (AI) in gait and posture analysis, focusing on methodologies, algorithms, and clinical applications. It examines the use of machine learning (ML) and deep learning (DL) techniques to extract relevant features from sensorderived data, offering objective, and automated assessments that surpass traditional methods. A systematic literature review was conducted, analyzing studies that utilized AI for gait and posture analysis with quantitative data from wearable sensors, motion capture systems, or depth cameras. The review highlights the strengths of AI, including its high accuracy and capacity to process large datasets, while acknowledging limitations such as data heterogeneity, interpretability challenges, and generalization issues. Results indicate that ML algorithms, like SVM, RF, and KNN, and DL models like CNN and RNN, are effectively employed for gait and posture classification, parameter estimation, and clinical applications such as Parkinson’s disease monitoring, scoliosis screening, and fall risk assessment. Future research directions emphasize addressing data heterogeneity, developing real-time analysis capabilities, enhancing explainable AI, and integrating personalized analysis into clinical workflows. The integration of AI into clinical practice holds the potential to revolutionize the diagnosis and management of musculoskeletal and neurological disorders, improving patient outcomes and quality of life.
Keywords: Gait, posture, AI, Machine Learning, Deep Learning, wearable devices, sensor, cameras
[This article belongs to Research and Reviews : Journal of Computational Biology ]
Harshit, Sumit, Ashish Kumar. AI Approaches in Gait and Posture Analysis: A Review. Research and Reviews : Journal of Computational Biology. 2025; 14(03):1-3.
Harshit, Sumit, Ashish Kumar. AI Approaches in Gait and Posture Analysis: A Review. Research and Reviews : Journal of Computational Biology. 2025; 14(03):1-3. Available from: https://journals.stmjournals.com/rrjocb/article=2025/view=232801
References
1.Roggio F, Ravalli S, Maugeri G, et al. Technological advancements in the analysis of human motion and posture management through digital devices. World J Orthop. 2021;12(7):467–84.
2.Giannakopoulou KM, Roussaki I, Demestichas K. Internet of things technologies and machine learning methods for Parkinson’s disease diagnosis, monitoring and management: a systematic review. Sensors (Basel). 2022;22(5):1799.
3.Belić M, Bobić V, Badža M, et al. Artificial intelligence for assisting diagnostics and assessment of Parkinson’s disease – a review. Clin Neurol Neurosurg. 2019;184:105442.
4.Wu P, Cao B, Liang Z, Wu M. The advantages of artificial intelligence-based gait assessment in detecting, predicting, and managing Parkinson’s disease. Front Aging Neurosci. 2023;15:1191378.
5.Patel S, Park H, Bonato P, Chan L, Rodgers M. A review of wearable sensors and systems with application in rehabilitation. J Neuroeng Rehabil. 2012;9(1):21.
6.Wang Y, et al. Wearable sensor-based gait analysis using machine learning: a review. Sensors (Basel). 2021;21(11):3704.
7.Hammerla NY, Halloran S, Plötz T. Deep, convolutional, and recurrent models for human activity recognition using wearables. arXiv [Preprint]. 2016. Available from: arXiv:1604.05890.
8.Khan AM, Roy S, Misra R, Littman ML. Gait analysis using deep learning for Parkinson’s disease detection. IEEE J Biomed Health Inform. 2020;24(12):3469–77.
9.Liu Y, et al. Gait analysis based on deep learning: a review of current trends and future directions. J Healthc Eng. 2020;2020:1–13.
10.Alsheakhali M, et al. Deep learning for gait analysis in Parkinson’s disease: a review. J Healthc Eng. 2021;2021:1–13.
11.Zhang K, Liu Y, Chen H, Chen Y. Computer vision based scoliosis screening using deep learning. J Med Imaging Health Inform. 2019;9(7):1599–607.
12.Muro-de-la-Herran S, et al. Deep learning for posture analysis: a review. Sensors (Basel). 2022;22(1):332.
Research and Reviews : Journal of Computational Biology
| Volume | 14 |
| Issue | 03 |
| Received | 29/05/2025 |
| Accepted | 11/09/2025 |
| Published | 26/09/2025 |
| Publication Time | 120 Days |
Login
PlumX Metrics