Automated classification of post-operative gait abnormalities following hip surgery using machine learning

Automated classification of post-operative gait abnormalities following hip surgery using machine learning Md Mohiuddin Soliman http://orcid.org/0000-0002-0268-9978 Moajjem Hossain Chowdhury M Murugappan http://orcid.org/0000-0002-5839-4589 Muhammad E H Chowdhury http://orcid.org/0000-0003-0744-8206 Abstract

An injury, chronic illness, obesity, infection, and more can negatively affect the hip joint. Surgery and implant placement are the standard treatments for moderate to severe hip issues. These treatments, however, can alter a patient’s gait patterns. Gait patterns must be assessed clinically by a qualified physician and a specialized examination is required to detect and monitor these changes. By contrast, Machine Learning (ML) techniques assist in diagnosing a wide variety of anomalies and illnesses. In addition to being extremely accurate, it reduces subjectivity in clinical expert evaluations. Gait anomalies can also be quickly identified and monitored inexpensively and quickly using ML. Three open-source datasets (GaitRec, Gutenberg, and Orthoload) were utilized in this study for the gait cycle conditions for healthy control, hip surgery, and hip implant patients. This study classifies individuals into two classes: Healthy control/Gait Abnormality and three classes: Healthy control/ Hip surgery/ Hip implant by gait cycle conditions using only vertical ground reaction forces (vGRFs) from these datasets, which consist of 3D GRFs. The essential steps in data preparation include filtering, denoising, normalizing, resampling, and augmenting. The purpose of these efforts was to improve the model performance in classification and reduce biases. We used several feature extraction techniques, focusing on excluding highly correlated features. The final analysis utilized five widely recognized feature selection algorithms (Minimum Redundancy Maximum Relevance (mRMR), Neighborhood Component Analysis (NCA), Multi-Cluster Feature Selection (MCFS), Chi-square, and Relief) to arrange the features systematically. Based on a comprehensive examination of five machine learning classifiers (k-nearest neighbor (KNN), artificial neural network (ANN), decision tree (DT), support vector machine (SVM), and Naïve Bayes (NB)), The KNN classifier exhibited the highest level of accuracy. The two and three-class classification’s overall accuracy, precision, sensitivity, and F1 score are 95.48%, 96.13%, 95.48%, 95.63% and 89.18%, 89.30%, 89.18, and 87.15%, respectively. With the proposed solution, clinicians can more easily identify gait abnormalities based on vertical ground reaction forces.
07 02 2025 09 30 2025 035203 10.1088/crossmark-policy iopscience.iop.org Automated classification of post-operative gait abnormalities following hip surgery using machine learning Engineering Research Express paper © 2025 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved. 2024-10-08 2025-06-25 2025-07-02 https://iopscience.iop.org/page/copyright https://iopscience.iop.org/info/page/text-and-data-mining 10.1088/2631-8695/ade84d https://iopscience.iop.org/article/10.1088/2631-8695/ade84d https://iopscience.iop.org/article/10.1088/2631-8695/ade84d/pdf https://iopscience.iop.org/article/10.1088/2631-8695/ade84d/pdf https://iopscience.iop.org/article/10.1088/2631-8695/ade84d/pdf https://iopscience.iop.org/article/10.1088/2631-8695/ade84d/pdf https://iopscience.iop.org/article/10.1088/2631-8695/ade84d https://iopscience.iop.org/article/10.1088/2631-8695/ade84d/pdf https://iopscience.iop.org/article/10.1088/2631-8695/ade84d https://iopscience.iop.org/article/10.1088/2631-8695/ade84d/pdf J. Biomech. Stanhope 10.1016/j.jbiomech.2013.08.017 46 2848 2013 Measuring walking: a handbook of clinical gait analysis: Richard Baker, Mac Keith Ben-Shlomo 2022 The national joint registry 19th Gait Posture. Surmacz 10.1016/j.gaitpost.2024.09.001 2024 Machine learning model identifies patient gait speed throughout the episode of care, generating notifications for clinician evaluation Sensors Belyaev 10.3390/s23208609 23 8609 2023 Entropy-based machine learning model for fast diagnosis and monitoring of parkinson’s disease Algorithms. Yuvaraj 10.3390/a17110503 17 503 2024 A Machine learning framework for classroom eeg recording classification: unveiling learning-style patterns Comput. Biol. Med. Johayra 10.1016/j.compbiomed.2024.109284 184 2025 A novel classical machine learning framework for early sepsis prediction using electronic health record data from ICU patients Karthikeyan 10.1007/978-3-642-35197-6_26 Vol 330 2012 EMG signal based human stress level classification using wavelet packet transform Frontiers in Neuroinformatics Alharthi 10.3389/fninf.2024.1451529 18 2024 Interpretable machine learning comprehensive human gait deterioration analysis Annu Int. Conf. IEEE Eng. Med. Biol. Soc. Alaqtash 10.1109/IEMBS.2011.6090063 2011 453 2011 Automatic classification of pathological gait patterns using ground reaction forces and machine learning algorithms Sensors Hwang 10.3390/s24175571 24 5571 2024 Machine learning based abnormal gait classification with imu considering joint impairment Front. Bioeng. Biotechnol. Bogaert 10.3389/fbioe.2024.1440033 12 2024 Predicting vertical ground reaction force characteristics during running with machine learning IEEE Trans. Biomed. Eng. Mezghani 10.1109/TBME.2007.905388 55 1230 2008 Automatic classification of asymptomatic and osteoarthritis knee gait patterns using kinematic data features and the nearest neighbor classifier J Appl. Biomech. Wu 10.1123/jab.24.1.83 24 83 2008 PCA-based SVM for automatic recognition of gait patterns IEEE Trans. Pattern Anal. Mach. Intell. Bengio 10.1109/TPAMI.2013.50 35 1798 2013 Representation learning: a review and new perspectives Gait & Posture. Giakas 10.1016/S0966-6362(96)01083-1 5 189 1997 Time and frequency domain analysis of ground reaction forces during walking: an investigation of variability and symmetry Clin. Biomech. Lafuente 10.1016/S0268-0033(97)00082-X 13 216 1998 Design and test of neural networks and statistical classifiers in computer-aided movement analysis: a case study on gait analysis Hum. Mov. Sci. Wu 10.1016/j.humov.2007.01.015 26 393 2007 Feature extraction via KPCA for classification of gait patterns Neurosci. Lett. Zeng 10.1016/j.neulet.2016.09.043 633 268 2016 Parkinson’s disease classification using gait analysis via deterministic learning J. Biomech. Begg 10.1016/j.jbiomech.2004.05.002 38 401 2005 A machine learning approach for automated recognition of movement patterns using basic, kinetic and kinematic gait data Int. J. Intell. Syst. Chan 10.1002/int.21568 28 257 2013 Assessing gait patterns of healthy adults climbing stairs employing machine learning techniques Gait Posture. Kaczmarczyk 10.1016/j.gaitpost.2009.04.010 30 207 2009 Gait classification in post-stroke patients using artificial neural networks LeMoyne 10.1109/ICMLA.2014.67 379 2014 Implementation of machine learning for classifying hemiplegic gait disparity through use of a force plate Multimedia Tools Appl. Pogorelc 10.1007/s11042-011-0786-1 58 333 2012 Automatic recognition of gait-related health problems in the elderly using machine learning Prosthet. Orthot. Int. Soares 10.1177/0309364615612634 40 729 2016 Principal component analysis in ground reaction forces and center of pressure gait waveforms of people with transfemoral amputation IEEE Trans. Neural Syst. Rehabil. Eng. Khandoker 10.1109/TNSRE.2007.906961 15 587 2007 Wavelet-based feature extraction for support vector machines for screening balance impairments in the elderly IEEE Journal of Biomedical and Health Informatics Slijepcevic 10.1109/JBHI.2017.2785682 22 1653 2017 Automatic classification of functional gait disorders Ann. Biomed. Eng. Zhang 10.1007/s10439-013-0917-0 42 600 2014 Classifying lower extremity muscle fatigue during walking using machine learning and inertial sensors Front. Bioeng. Biotechnol. Burdack 10.3389/fbioe.2020.00260 8 2020 Systematic comparison of the influence of different data preprocessing methods on the performance of gait classifications using machine learning PLoS One Horst 10.1371/journal.pone.0179738 12 2017 Intra-individual gait patterns across different time-scales as revealed by means of a supervised learning model using kernel-based discriminant regression Scientific Data. Horst 10.1038/s41597-021-01014-6 8 232 2021 Gutenberg gait database, a ground reaction force database of level overground walking in healthy individuals J. Rehabil Res. Dev. Dolatabadi 10.1682/JRRD.2013.12.0263 51 1165 2014 Vision-based approach for long-term mobility monitoring: single case study following total hip replacement Gait Posture. Horst 10.1016/j.gaitpost.2016.07.073 49 309 2016 Daily changes of individual gait patterns identified by means of support vector machines Sci. Rep. Damm 10.1038/s41598-021-95387-8 11 2021 Surgical cup placement affects the heating up of total joint hip replacements Standard Loads Hip Joint Bergmann 2023 Scientific Data Horsak 10.1038/s41597-020-0481-z 7 143 2020 GaitRec, a large-scale ground reaction force dataset of healthy and impaired gait Biomed. Signal Process. Control Nazmul Islam Shuzan 10.1016/j.bspc.2022.104448 81 2023 Machine learning-based classification of healthy and impaired gaits using 3D-GRF signals J. Biomech. Mai 10.1016/j.jbiomech.2019.08.005 95 2019 Effects of low-pass filter combinations on lower extremity joint moments in distance running European Journal of Interdisciplinary Studies. Altin 10.26417/ejis.v2i3.p35-44 5 35 2016 Comparison of different time and frequency domain feature extraction methods on elbow gesture’s EMG El Halabi 2018 Blind source separation of single-sensor recordings: application to ground reaction force signals Clin Biomech (Bristol, Avon). Stergiou 10.1016/S0268-0033(02)00072-4 17 615 2002 Frequency domain characteristics of ground reaction forces during walking of young and elderly females Healthc Technol Lett. Doulah 10.1049/htl.2013.0036 1 26 2014 DCT domain feature extraction scheme based on motor unit action potential of EMG signal for neuromuscular disease classification Soubra 10.1109/BIOSMART.2017.8095343 1 2017 A mother wavelet selection study for vertical ground reaction force signals Comput. Biol. Med. Haque 10.1016/j.compbiomed.2021.104954 139 2021 A nomogram-based diabetic sensorimotor polyneuropathy severity prediction using Michigan neuropathy screening instrumentations IEEE Access. Shuzan 10.1109/ACCESS.2021.3095380 9 96775 2021 A novel non-invasive estimation of respiration rate from motion corrupted photoplethysmograph signal using machine learning model J. Artif. Intell. Res. (JAIR Chawla 10.1613/jair.953 16 321 2002 SMOTE: synthetic minority over-sampling technique Inventions. Nascimento 10.3390/inventions7040098 7 98 2022 Development of a human motion analysis system based on sensorized insoles and machine learning algorithms for gait evaluation Biomedicines. Hakkak Moghadam Torbati 10.3390/biomedicines12030472 12 472 2024 Machine learning and texture analysis of [18f]fdg pet/ct images for the prediction of distant metastases in non-small-cell lung cancer patients Applied Sciences Choi 10.3390/app11198940 11 8940 2021 Feature optimization for gait phase estimation with a genetic algorithm and bayesian optimization Neurocomputing Haocong 10.1016/j.neucom.2025.129533 626 2025 A survey of artificial intelligence in gait-based neurodegenerative disease diagnosis Biomed. Phys. Eng. Express Torbati 10.1088/2057-1976/ac6caa 8 2022 Is the Hénon map able to predict the interaction dynamics between the knee and hip joints emerged during sit-to-stand movement? Journal of Human Sport and Exercise Torbati 10.14198/jhse.2017.121.15 12 180 2017 Determination of the best recovery based on muscles synergy patterns and lactic acid The Open Bioinformatics Journal. Torbati 10.2174/1875036201811010052 11 2018 May 14 Clinical model to the analysis of synergy pattern changes of back muscles and its relationship with the occurrence of fatigue Khalil 10.1109/EMBC53108.2024.10781639 1 2024, Enhanced binary classification of gait disorders using a machine learning majority voting approach IEEE Access Slijepcevic 10.1109/ACCESS.2024.3513893 2024 Decoding gait signatures: exploring individual patterns in pathological gait using explainable ai