The Role of Artificial Intelligence and Machine Learning in Balance Classification Using Center of Pressure – A Comprehensive Review
DOI:
https://doi.org/10.3991/ijoe.v22i04.59523Keywords:
balance classification, center of pressure, insoles, force plate, Artificial intelligenceAbstract
Balance control is essential for safe daily activities, and impaired postural stability is strongly associated with fall risk, particularly in older adults. This systematic review examined the performance of artificial intelligence (AI) and machine learning (ML) methods for balance classification using Center of Pressure (CoP) data. Following PRISMA guidelines, 47 studies published between 2015 and 2025 were included. Force-platform-based post-urography remained the predominant sensing modality, while wearable technologies increasingly enabled assessment beyond laboratory environments. Support vector machine (SVM) was the most frequently used algorithm, followed by neural network (NN)-based models. Deep learning (DL) architectures, including convolutional neural networks (CNN) and long shortterm memory networks (LSTM), achieved high classification accuracy by capturing complex balance patterns. Traditional ML models also demonstrated strong performance with lower computational demands and greater interpretability, supporting clinical feasibility. However, class imbalance remains a key limitation, often reducing sensitivity in high-risk groups. Future studies should prioritize robust and clinically deployable models for reliable realworld balance assessment and personalized rehabilitation.
References
[1] S. Piriyayotha, A. Keawmalaitip, P. Muneesawang, and P. Lertsinthai, "ExercisePill: An Exercise Application for Balance Problems in the Elderly," Int. J. Online Biomed. Eng., vol. 18, no. 4, pp. 79–93, 2022, doi: https://doi.org/10.3991/ijoe.v18i04.27771.
[2] F. B. Hora, C. L. Shupert, and A. Mirka, "Components of postural dyscontrol in the elderly: A review," Neurobiol. Aging, vol. 10, pp. 727–738, 1989, doi: http://doi.org/10.1016/0197-4580(89)90010-9.
[3] R. J. Peterka, "Sensorimotor integration in human postural control," J. Neurophysiol., vol. 88, no. 3, pp. 1097-1118, 2002, doi: http://doi.org/10.1152/jn.2002.88.3.1097.
[4] M. A. Ali, A. J. Hussain, and A. T. Sadiq, "Human Fall Down Recognition Using Coordinates Key Points Skeleton," Int. J. Online Biomed. Eng., vol. 18, no. 02, pp. 88-104, 2022, doi: https://doi.org/10.3991/ijoe.v18i02.28017.
[5] M. H. Habaebi, S. H. Yusoff, A. N. Ishak, M. R. Islam, J. Chebil, and A. Basahel, "Wearable Smart Phone Sensor Fall Detection System," Int. J. Interact. Mob. Technol., vol. 16, no. 12, pp. 72–93, 2022, doi: https://doi.org/10.3991/ijim.v16i12.30105.
[6] L. Tesio, V. Rota, C. Chessa, and L. Perucca, "The 3D path of body centre of mass during adult human walking on force treadmill," J. Biomech., vol. 43, no. 5, pp. 938-944, 2010, doi: https://doi.org/10.1016/j.jbiomech.2009.10.049.
[7] B. Chen, P. Liu, F. Xiao, Z. Liu, and Y. Wang, "Review of the Upright Balance Assessment Based on the Force Plate," Int J Environ Res Public Health, vol. 18, no. 5, p. 2696, 2021, doi: http://doi.org/10.3390/ijerph18052696.
[8] D. A. Winter, Biomechanics and motor control of human 4th ed. Hoboken, NJ, USA: Wiley, 2009.
[9] F. Scoppa, R. Capra, M. Gallamini, and R. Shiffer, "Clinical stabilometry standardization: Basic definitions, acquisition interval, sampling frequency," Gait & Posture, vol. 37, no. 2, pp. 290-292, 2013, doi: https://doi.org/10.1016/j.gaitpost.2012.07.009.
[10] R. M. Palmieri-Smith, C. Ingersoll, M. B. Stone, and B. A. Krause, "Center-of-Pressure Parameters Used in the Assessment of Postural Control," J. Sport Rehabil., vol. 11, no. 1, pp. 51-66, 2002, doi: http://doi.org/10.1123/jsr.11.1.51.
[11] V. Sanyod et al., "IoT-Based Smart Walking Assistant for Fall Detection in the Elderly," J. Online Biomed. Eng., vol. 21, no. 6, pp. 19-35, 2025, doi: https://doi.org/10.3991/ijoe.v21i06.54443.
[12] A. Rajkomar, J. Dean, and I. Kohane, "Machine Learning in Medicine," N. Engl. J. Med., vol. 380, no. 14, pp. 1347-1358, 2019, doi: http://doi.org/10.1056/NEJMra1814259.
[13] E. J. Topol, "High-performance medicine: the convergence of human and artificial intelligence," Nat Med, vol. 25, no. 1, pp. 44-56, 2019, doi: https://doi.org/10.1038/s41591-018-0300-7.
[14] A. F. M. F. Ismail, M. F. M. Sam, K. A. Bakar, A. Ahamat, S. Adam, and M. I. Qureshi, "Artificial Intelligence in Healthcare Business Ecosystem," J. Online Biomed. Eng., vol. 18, no. 9, pp. 100–114, 2022, doi: https://doi.org/10.3991/ijoe.v18i09.32251.
[15] H. Vega-Huerta et al., "Convolutional Neural Networks on Assembling Classification Models to Detect Melanoma Skin Cancer," Int. J. Online Biomed. Eng., vol. 18, no. 14, pp. 59–76, 2022, doi: https://doi.org/10.3991/ijoe.v18i14.34435.
[16] A. A. Siddique, J. Ferdouse, T. Habib, J. Mia, and M. S. Uddin, "Convolutional Neural Network Modeling for Eye Disease Recognition," Int. J. Online Biomed. Eng., vol. 18, no. 9, pp. 115–130, 2022, doi: https://doi.org/10.3991/ijoe.v18i09.29847.
[17] H. Espinoza Villavicencio, J. Gamboa-Cruzado, J. López-Goycochea, and L. Soto Soto, "The Role of Artificial Intelligence in the Diagnosis of Neoplastic Diseases: A Systematic and Bibliometric Review," Int. J. Online Biomed. Eng., vol. 20, no. 4, pp. 43-68, 2024, doi: http://doi.org/10.3991/ijoe.v20i04.45429.
[18] S. K, A. N. Uday, A. S. J, and A. S, "Gait Analysis—A Tool for Medical Inferences," Int. J. Online Biomed. Eng., vol. 20, no. 6, pp. 153-166, 2024, doi: https://doi.org/10.3991/ijoe.v20i06.45787.
[19] P. Ren et al., "Assessment of Balance Control Subsystems by Artificial Intelligence," IEEE Trans Neural Syst Rehabil Eng, vol. 28, no. 3, pp. 658-668, 2020, doi: http://doi.org/10.1109/TNSRE.2020.2966784.
[20] H.-W. Liang et al., "Fall risk classification with posturographic parameters in community‑dwelling older adults: a machine learning and explainable artificial intelligence approach," J. Neuroeng. Rehabil., vol. 21, no. 15, 2024, doi: https://doi.org/10.1186/s12984-024-01310-3.
[21] A. Mengarelli et al., "A Computer-Aided Screening Solution for the Identification of Diabetic Neuropathy From Standing Balance by Leveraging Multi-Domain Features," IEEE Trans Neural Syst Rehabil Eng, vol. 32, pp. 2388-2397, 2024, doi: http://doi.org/10.1109/TNSRE.2024.3419235.
[22] Y. W. Kim, W. H. Cho, K. L. Joa, H. Y. Jung, and S. Lee, "A New Auto-Scoring Algorithm for Balance Assessment with Wearable IMU Device Based on Nonlinear Model," J. Mech. Med. Biol., vol. 20, no. 10, 2020, doi: https://doi.org/10.1142/S0219519420400114.
[23] F.-Y. Liao, Chun-ChangWu, Yi-ChunWei, Li-WeiChou, and Kang-MingChang, "Analysis of Center of Pressure Signals by Using Decision Tree and Empirical Model Decomposition to Predict Falls among Older Adult," J. Healthcare Eng., vol. 2021, 2021, doi: https://doi.org/10.1155/2021/6252445.
[24] S. R. Pandey, M. M. Oghaz, and J. G. Varghese, "Decoding Diabetic Neuropathy: Tap into Postural Sway for Optimal Feature Detection based on Machine Learning Approach," in 2024 International Conference on Inventive Computation Technologies (ICICT), Lalitpur, Nepal, 2024: IEEE, pp. 1104-1111, doi: http://doi.org/10.1109/ICICT60155.2024.10544768.
[25] P. Lee, T.-B. Chen, S.-Y. Hsu, and C.-H. Liu, "Detection of Postural Control in Young and Elderly Adults Using Deep and Machine Learning Methods with Joint–Node Plots," Sensors, vol. 21, no. 9, p. 3212, 05 May 2021 2021, doi: https://doi.org/10.3390/s21093212.
[26] H. S. Choi, S. Yoon, J. Kim, H. Seo, and J. K. Choi, "Calibrating Low-Cost Smart Insole Sensors with Recurrent Neural Networks for Accurate Prediction of Center of Pressure," Sensors, vol. 24, p. 4765, 2024, doi: https://doi.org/10.3390/s24154765.
[27] M. F. Goethel, U. F. Ervilha, K. M. Becker, F. C. S. Parolini, and J. P. Vilas-Boas, "Development of a Tool for Comprehensive Balance Assessment Based on Artificial Intelligence and Anomaly Detection," Life, vol. 15, p. 632, 2025, doi: https://doi.org/10.3390/life15040632.
[28] K. Barati, S. Behzadipur, M. Borushaki, and Z. Rahmati, "Classification of Faller and Non-Faller Parkinson's Disease Patients using Wavelet-based Multifractal Spectrum of Center of Pressure Signal," in 28th National and 6th International Iranian Conference on Biomedical Engineering (ICBME), Tehran, Iran, Islamic Republic, 2021, pp. 220-227, doi: http://doi.org/10.1109/ICBME54433.2021.9750367.
[29] V. Phan and H. Lee, "Deep Learning: Predicting Environments From Short-Time Observations of Postural Balance," IEEE Trans. Biomed. Eng., vol. 19, no. 11, pp. 3460-3471, Nov 2022, doi: http://doi.org/10.1109/TBME.2022.3170850.
[30] J. Audiffren, I. Bargiotas, N. Vayatis, P.-P. Vidal, and D. Ricard, "A Non Linear Scoring Approach for Evaluating Balance: Classification of Elderly as Fallers and Non-Fallers," PLoS ONE, vol. 11, no. 12, 2016, doi: https://doi.org/10.1371/journal.pone.0167456.
[31] Y. Cheng et al., "A novel classification method for balance differences in elite versus expert athletes based on composite multiscale complexity index and ranking forests," PLoS ONE vol. 20, no. 1, 30 Jan 2025 2025, doi: https://doi.org/10.1371/journal.pone.0315454.
[32] M. J. Page et al., "The PRISMA 2020 statement: An updated guideline for reporting systematic reviews," BMJ, vol. 372, no. 71, 2021, doi: https://doi.org/10.1136/bmj.n160.
[33] P. De-La-Cruz, R. Rojas-Coaquira, H. Vega-Huerta, J. Pérez-Quintanilla, and M. Lagos-Barzola, "A Systematic Review Regarding the Prediction of Academic Performance," . Comput. Sci., vol. 18, no. 2, pp. 1219-1231, 2022, doi: http://doi.org/10.3844/jcssp.2022.1219.1231.
[34] A. Sarmah et al., "Framework for early detection and classification of balance pathologies using posturography and anthropometric variables," Clin. Biomech., vol. 113, 2024, doi: https://doi.org/10.1016/j.clinbiomech.2024.106214.
[35] F. Rojas, I. K. Niazi, P. Maturana-Russel, and D. Taylor, "Exploring the Potential of Machine Learning for the Diagnosis of Balance Disorders Based on Centre of Pressure Analyses," Sensors, vol. 22, p. 9200, 2022, doi: https://doi.org/10.3390/s22239200.
[36] N. Rahimi et al., "Distinguishing among standing postures with machine learning‑based classification algorithms," Exp. Brain Res., vol. 243, no. 3, 2024, doi: https://doi.org/10.1007/s00221-024-06959-9.
[37] K. Wantanajittikul, C. Wiboonsuntharangkoon, B. Chuatrakoon, and S. Kongsawasdi, "Application of Machine Learning to Predict Trajectory of the Center of Pressure (COP) Path of Postural Sway Using a Triaxial Inertial Sensor," Sci. World J., vol. 2022, 2022, doi: https://doi.org/10.1155/2022/9483665.
[38] J. Moon, D. Lee, H. Jung, A. Choi, and J. H. Mun, "Machine Learning Strategies for Low-Cost Insole-Based Prediction of Center of Gravity during Gait in Healthy Males," Sensors, vol. 22, p. 3499, 2022, doi: https://doi.org/10.3390/s22093499.
[39] A. Choi, H. Jung, K. Y. Lee, S. Lee, and J. H. Mun, "Machine learning approach to predict center of pressure trajectories in a complete gait cycle: a feedforward neural network vs. LSTM network," Med. Biol. Eng. Comput., vol. 57, pp. 2693–2703, 2019, doi: https://doi.org/10.1007/s11517-019-02056-0.
[40] F. K. Fuss, A. M. Tan, and Y. Weizman, "Advanced Dynamic Centre of Pressure Diagnostics with Smart Insoles: Comparison of Diabetic and Healthy Persons for Diagnosing Diabetic Peripheral Neuropathy," Bioengineering, vol. 11, p. 1241, 2024, doi: https://doi.org/10.3390/bioengineering11121241.
[41] I. J. Museck, D. L. Brinton, and J. C. Dean, "The Use of Wearable Sensors and Machine Learning Methods to Estimate Biomechanical Characteristics During Standing Posture or Locomotion: A Systematic Review," Sensors vol. 24, p. 7280, 14 Nov 2024 2024, doi: https://doi.org/10.3390/s24227280.
[42] R. Fadil, A. Huether, R. Brunnemer, and K. Tavakolian, "Early Detection of Parkinson’s Disease Using Center of Pressure Data and Machine Learning," in 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2021: ResearchGate, doi: http://doi.org/10.1109/EMBC46164.2021.9630451.
[43] C.-C. Wu, Y.-J. Chen, C.-S. Hsu, Y.-T. Wen, and Y.-J. Lee, "Multiple Inertial Measurement Unit Combination and Location for Center of Pressure Prediction in Gait," Front. Bioeng. Biotechnol, vol. 8, 2020, doi: https://doi.org/10.3389/fbioe.2020.566474.
[44] O. Rivera, E. Castillo-Castaneda, O. F. Avilés, and R. Hernández, "Index of Physical activity and Fall Efficacy scale classification through biomechanical signals and Machine Learning," J. Eng. Res., vol. 11, no. 3A, pp. 91-102, 2022, doi: http://doi.org/10.36909/jer.16527.
[45] E.-T. Jeon, S.-h. Lee, M.-Y. Eun, and J.-M. Jung, "Center of Pressure and Machine Learning-based Gait Score and Clinical Risk Factors for Predicting Functional Outcome in Acute Ischemic Stroke," Arch. Phys. Med. Rehabil., vol. 105, pp. 2277-2285, 2024, doi: https://doi.org/10.1016/j.apmr.2024.08.006.
[46] T. Kamogashir, C. Fujimoto, M. Kinoshita, Y. Kikkawa, TatsuyaYamasob, and S. Iwasaki, "Prediction of Vestibular Dysfunction by Applying Machine Learning Algorithms to Postural Instability," Front. Neurol., vol. 11, no. 7, 5 Feb 2020 2020, doi: https://doi.org/10.3389/fneur.2020.00007.
[47] C. M. Villegas and D. C. Aqueveque, "Diagnosis of neuropathies in diabetic patients by applying machine learning," Ingeniare. Revista chilena de ingeniería, vol. 29, no. 3, pp. 517-530, 2021, doi: http://doi.org/10.4067/S0718-33052021000300517.
[48] A. Montenegro, G. Sosa, N. Figuero, V. Vargas, and H. Franco, "Evaluation of stabilometry descriptors for human balance function classification using diagnostic and statokinesigram data," Biomed. Signal Process. Control, vol. 84, July 2023 2023, doi: https://doi.org/10.1016/j.bspc.2023.104861.
[49] V. R. Chawan, M. Huber, N. Burns, and K. Daniel, "Person Identification And Tinetti Score Prediction Using Balance Parameters : A Machine Learning Approach To Determine Fall Risk," in PETRA '22: The15th International Conference on PErvasive Technologies Related to Assistive Environments, 2022, doi: http://doi.org/10.1145/3529190.3529223.
[50] K. E. Forth, K. L. Wirfel, S. D. Adams, N. J. Rianon, E. L. Aiden, and S. I. Madansingh, "A Postural Assessment Utilizing Machine Learning Prospectively Identifies Older Adults at a High Risk of Falling," Front. Med., vol. 7, 2020, doi: https://doi.org/10.3389/fmed.2020.591517.
[51] X. Ning, Y. Kim, S. D. Min, X. Guo, and J. G. Ho, "Exploring Achilles Tendon Vibration Data Classification for Balance Training: A Wavelet-Based Machine Learning Approach," IEEE Access, vol. 12, pp. 81783-81792, 2024, doi: http://doi.org/10.1109/ACCESS.2024.3411010.
[52] W.-Y. Liao, Y.-H. Chu, F.-Y. Liu, K.-M. Chang, and L.-W. Chou, "Cutoff Point of Mini-Balance Evaluation Systems Test Scores for Elderly Estimated by Center of Pressure Measurements by Linear Regression and Decision Tree Classification," Life, vol. 12, p. 2133, 2022, doi: https://doi.org/10.3390/life12122133.
[53] K. Safi, S. Mohammed, F. Attal, Y. Amirat, L. Oukhellou, and M. Khalil, "Automatic Segmentation of Stabilometric Signals Using Hidden Markov Model Regression," IEEE Trans. Autom. Sci. Eng., vol. 15, no. 2, pp. 545-555, Apr 2018, doi: http://doi.org/10.1109TASE.2016.2637165.
[54] G. Mertes, G. Baldewijns, P.-J. Dingenen, T. Croonenborghs, and B. Vanrumste, "Automatic fall risk estimation using the Nintendo Wii balance board," in International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC), Lisbon, Portugal, January, 2015: ResearchGate.
[55] Z. Rahmati, S. Behzadipour, A. C. Schouten, and G. Taghizadeh, "A Postural Control Model to Assess the Improvement of Balance Rehabilitation in Parkinson's Disease," in 2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob), Enschede, Netherlands, 2018, pp. 1019-1024, doi: http://doi.org/10.1109/BIOROB.2018.8487884.
[56] H. Joutsijoki, J. Rasku, I. Pyykkö, and M. Juhol, "Classification of patients and controls based on stabilogram signal data," Intell. Data Anal., vol. 23, no. 215-226, 2019, doi: http://doi.org/10.3233/IDA-173704.
[57] N. Pisani, M. Russo, M. C. Calabrese, F. D. Filippo, G. Cesarelli, and P. Barone, "Measurements of Postural Sway to Classify Freezing of Gait in Parkinson's Disease," in 2024 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE), St Albans, United Kingdom, 2024, pp. 154-159, doi: http://doi.org/10.1109/MetroXRAINE62247.
[58] E. Araujo, G. E. F. Bentes, and R. Zangaro, "Body sway and global equilibrium condition of the elderly in quiet standing posture by using competitive neural networks," Appl. Soft Comput., vol. 69, pp. 625-633, Aug 2018 2018, doi: https://doi.org/10.1016/j.asoc.2018.05.004.
[59] M. Ghahramani, H. Ismail, and R. Goecke, "A Multidimensional Approach to Develop Sway Index Using Gaussian Mixture Model: A Way of Postural Sway Measurement and Analysis in Different Age Groups," IEEE Trans. Instrum. Meas., vol. 70, pp. 1-11, 2021, doi: http://doi.org/10.1109/TIM.2021.3107012.
[60] C. Chou, S. H. Chou, Y. C. Chen, and C. J. Yang, "Using machine learning methods to detect physical conditions with postural balance," J. Ambient Intell. Humaniz. Comput., vol. 14, pp. 14499–14505, 2020, doi: https://doi.org/10.1007/s12652-020-02261-y.
[61] T. Bao, B. N. Klatt, S. L. Whitney, K. H. Sienko, and J. Wiens, "Automatically Evaluating Balance: A Machine Learning Approach," IEEE Trans. Neural Syst. Rehabil. Eng., vol. 27, no. 2, pp. 179–186, Feb 2019 2019, doi: http://doi.org/10.1109/TNSRE.2019.2891000.
[62] J. Wu et al., "Automated assessment of balance: A neural network approach based on large-scale balance function data," Front. Public Health, vol. 10, 2022, doi: http://doi.org/10.3389/fpubh.2022.882811.
[63] J. Pennone, N. F. Aguero, D. M. Martini, L. Mochizuki, and A. A. d. P. Suaide, "Fall prediction in a quiet standing balance test via machine learning: Is it possible?," PLOS ONE, vol. 20, no. 4, 2024, doi: https://doi.org/10.1371/journal.pone.0296355.
[64] F. Kamran et al., "Automatically evaluating balance using machine learning and data from a single inertial measurement unit," J. Neuroeng. Rehabil., vol. 18, no. 114, 2021, doi: https://doi.org/10.1186/s12984-021-00894-4.
[65] J.-W. Seo et al., "Development and Application of a Stability Index Estimation Algorithm Based on Machine Learning for Elderly Balance Ability Diagnosis in Daily Life," Bioengineering, vol. 10, p. 943, 2023, doi: https://doi.org/10.3390/bioengineering10080943.
[66] M. F. Aqillah, W. A. Cahyadi, H. Mukhtar, S. Indriyanto, and S. Setiyadi, "Optimising Real-Time Fall Detection: A Comparative Study of Machine Learning Algorithms Using IMU Sensor," in The 2025 IEEE International Conference on Artificial Intelligence for Learning and Optimization (ICoAILO), 2025, pp. 13–18, doi: https://doi.org/10.1109/ICOAILO66760.2025.11155939.
[67] F. C. G. D. Zubiena, L. D’Alvia, D. o. M. a. Aeros, L. Liguori, and Z. D. Prete, "Design and development of a neural network based novel sensorized insole for ground reaction force and center of pressure estimation," in Proceedings of the 2025 IEEE Medical Measurements & Applications (MeMeA), 2025, pp. 1-6, doi: https://doi.org/10.1109/MEMEA65319.2025.11068028.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Wittaya Duangnga, Nattadon Pannucharoenwong , Phadungsak Rattanadecho, Wachirathorn Janchomphu , Suphasit Panvichien
This work is licensed under a Creative Commons Attribution 4.0 International License.
