{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T03:05:01Z","timestamp":1775012701800,"version":"3.50.1"},"reference-count":52,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Non-invasive methods for evaluating rehabilitation outcomes in Parkinson\u2019s disease (PD) remain limited. This preliminary study proposes a mechanics-informed machine learning (ML) framework integrating force-plate data with dimensionality reduction, clustering, and statistical analysis to objectively assess motor control and the effects of a targeted intervention. Methods: Twelve PD patients were randomly assigned to a PD control group performing standard exercises or an intervention group incorporating additional transverse-plane trunk motion exercises for 10 weeks. Ground reaction forces and center of pressure (COP) signals were recorded pre- and post-intervention using a force plate, alongside data from six healthy individuals as a benchmark. Features related to postural sway and COP dynamics were extracted and refined using Forward Feature Selection. Dimensionality reduction (t-SNE) and unsupervised clustering (K-means) identified group-level patterns. SHAP values and Cohen\u2019s d quantified feature importance and effect size. Clustering robustness was assessed with bootstrapping, nested cross-validation, and permutation testing. Results: K-means clustering revealed clear pre\/post-intervention separation in five of six intervention patients, with post-intervention states shifting toward the control cluster. Clustering showed strong performance (Silhouette 0.77\u20130.79; Calinski\u2013Harabasz 100.8\u2013184.9; Davies\u2013Bouldin 0.29\u20130.45). The most predictive features (RMS-SML and PL-SAP) showed large effect sizes (Cohen\u2019s d = \u201312.1 and \u20134.53, respectively) distinguishing PD patients from healthy controls. Traditional statistical tests (e.g., ANOVA) failed to detect within-group changes (p &gt; 0.05), but ML-based methods captured subtle, nonlinear postural adaptations. Conclusions: This preliminary mechanics-informed ML framework detects PD-related motor deficits and rehabilitation-induced improvements using force-plate data, warranting validation in larger cohorts.<\/jats:p>","DOI":"10.3390\/diagnostics15222855","type":"journal-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T06:55:04Z","timestamp":1762930504000},"page":"2855","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Preliminary Mechanics-Informed Machine Learning Framework for Objective Assessment of Parkinson\u2019s Disease and Rehabilitation Outcomes"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9593-3935","authenticated-orcid":false,"given":"Amirali","family":"Hanifi","sequence":"first","affiliation":[{"name":"Faculty of Mechanical Engineering, Tarbiat Modares University, Tehran 14115-111, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roozbeh","family":"Abedini-Nassab","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, Tarbiat Modares University, Tehran 14115-111, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammed N.","family":"Ashtiani","sequence":"additional","affiliation":[{"name":"Faculty of Medical Sciences, Tarbiat Modares University, Tehran 14115-111, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1001\/jama.2019.22360","article-title":"Diagnosis and Treatment of Parkinson Disease: A Review","volume":"323","author":"Armstrong","year":"2020","journal-title":"JAMA"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Rinalduzzi, S., Trompetto, C., Marinelli, L., Alibardi, A., Missori, P., Fattapposta, F., Pierelli, F., and Curra, A. (2015). Balance dysfunction in Parkinson\u2019s disease. Biomed. Res. Int., 2015.","DOI":"10.1155\/2015\/434683"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1177\/1545968316656057","article-title":"Neuromuscular Impairments Are Associated with Impaired Head and Trunk Stability During Gait in Parkinson Fallers","volume":"31","author":"Cole","year":"2017","journal-title":"Neurorehabil. Neural Repair."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1016\/S1474-4422(18)30295-3","article-title":"Global, regional, and national burden of Parkinson\u2019s disease, 1990\u20132016: A systematic analysis for the Global Burden of Disease Study 2016","volume":"17","author":"Dorsey","year":"2018","journal-title":"Lancet Neurol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1136\/jnnp.2007.131045","article-title":"Parkinson\u2019s disease: Clinical features and diagnosis","volume":"79","author":"Jankovic","year":"2008","journal-title":"Neurol. Neurosurg. Psychiatry"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1111\/cns.12727","article-title":"Adverse effects produced by different drugs used in the treatment of Parkinson\u2019s disease: A mixed treatment comparison","volume":"23","author":"Li","year":"2017","journal-title":"CNS Neurosci. Ther."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1002\/mds.22554","article-title":"Deep brain stimulation effects on gait variability in Parkinson\u2019s disease","volume":"24","author":"Hausdorff","year":"2009","journal-title":"Mov. Disord."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1038\/nrneurol.2017.128","article-title":"Long-term effects of exercise and physical therapy in people with Parkinson disease","volume":"13","author":"Mak","year":"2017","journal-title":"Nat. Rev. Neurol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1038\/s41531-021-00269-5","article-title":"Behavioural and neuroplastic effects of a double-blind randomised controlled balance exercise trial in people with Parkinson\u2019s disease","volume":"8","author":"Freidle","year":"2022","journal-title":"npj Park. Dis."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Rabini, G., Meli, C., Prodomi, G., Speranza, C., Anzini, F., Funghi, G., Pierotti, E., Saviola, F., Fumagalli, G.G., and Di Giacopo, R. (2024). Tango and physiotherapy interventions in Parkinson\u2019s disease: A pilot study on efficacy outcomes on motor and cognitive skills. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-62786-6"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Toosizadeh, N., Mohler, J., Lei, H., Parvaneh, S., Sherman, S., and Najafi, B. (2015). Motor Performance Assessment in Parkinson\u2019s Disease: Association between Objective In-Clinic, Objective In-Home, and Subjective\/Semi-Objective Measures. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0124763"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"De Pasquale, P., Bonanno, M., De Marchis, C., Pergolizzi, L., Lombardo Facciale, A., Paladina, G., Maggio, M.G., Impellizzeri, F., Ciancarelli, I., and Quartarone, A. (2025). Beyond clinical scales: An observational study on instrumental gait analysis and biomechanical patterns in patients with Parkinson\u2019s disease. Front. Bioeng. Biotechnol., 13.","DOI":"10.3389\/fbioe.2025.1541240"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Seo, H.G., Yun, S.J., Song, Y., Lee, H.S., Kim, D.H., and Chang, W.H. (2024). The Development of a Quantitative Disability Assessment Tool in Patients with Idiopathic Parkinson\u2019s Disease. Diagnostics, 14.","DOI":"10.3390\/diagnostics14182063"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1186\/s41687-023-00577-9","article-title":"Development and early qualitative evidence of two novel patient-reported outcome instruments to assess daily functioning in people with early-stage Parkinson\u2019s","volume":"7","author":"Morel","year":"2023","journal-title":"J. Patient-Rep. Outcomes"},{"key":"ref_15","first-page":"7","article-title":"The Discriminate Analysis and Dimension Reduction Methods of High Dimension","volume":"3","author":"Fu","year":"2015","journal-title":"Open J. Soc. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Jeong, S.M., Kim, S., Lee, E.C., and Kim, H.J. (2024). Exploring Spectrogram-Based Audio Classification for Parkinson\u2019s Disease: A Study on Speech Classification and Qualitative Reliability Verification. Sensors, 24.","DOI":"10.3390\/s24144625"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Srinivasan, S., Ramadass, P., Mathivanan, S.K., Panneer Selvam, K., Shivahare, B.D., and Shah, M.A. (2024). Detection of Parkinson disease using multiclass machine learning approach. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-64004-9"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zheng, L., Zhou, C., Mao, C., Xie, C., You, J., Cheng, W., Liu, C., Huang, P., Guan, X., and Guo, T. (2024). Contrastive machine learning reveals Parkinson\u2019s disease specific features associated with disease severity and progression. Commun. Biol., 7.","DOI":"10.1038\/s42003-024-06648-x"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Priyadharshini, S., Ramkumar, K., Vairavasundaram, S., Narasimhan, K., Venkatesh, S., Madhavasarma, P., and Kotecha, K. (2024). Bio-inspired feature selection for early diagnosis of Parkinson\u2019s disease through optimization of deep 3D nested learning. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-74405-5"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Leal, D.A.B., Dias, C.M.V., Ramos, R.P., and Brys, I. (2023). Prediction of dyskinesia in Parkinson\u2019s disease patients using machine learning algorithms. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-49617-w"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Rehman, R.Z.U., Del Din, S., Guan, Y., Yarnall, A.J., Shi, J.Q., and Rochester, L. (2019). Selecting Clinically Relevant Gait Characteristics for Classification of Early Parkinson\u2019s Disease: A Comprehensive Machine Learning Approach. Sci. Rep., 9.","DOI":"10.1038\/s41598-019-53656-7"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Nawar, A. (2020, January 20\u201324). Topological Descriptors for Parkinson\u2019s Disease Classification and Regression Analysis. Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society, Montreal, QC, Canada.","DOI":"10.1109\/EMBC44109.2020.9176285"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kim, J., Nasir, M., Gupta, R., Van Segbroeck, M., Bone, D., Black, M.P., Skordilis, Z.I., Yang, Z., Georgiou, P.G., and Narayanan, S.S. (2015, January 6\u201310). Automatic estimation of Parkinson\u2019s disease severity from diverse speech tasks. Proceedings of the Interspeech 2015, Dresden, Germany.","DOI":"10.21437\/Interspeech.2015-194"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Sedigh Malekroodi, H., Madusanka, N., Lee, B.I., and Yi, M. (2025). Speech-Based Parkinson\u2019s Detection Using Pre-Trained Self-Supervised Automatic Speech Recognition (ASR) Models and Supervised Contrastive Learning. Bioengineering, 12.","DOI":"10.20944\/preprints202505.1801.v1"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.compbiomed.2018.02.007","article-title":"Wrist sensor-based tremor severity quantification in Parkinson\u2019s disease using convolutional neural network","volume":"95","author":"Kim","year":"2018","journal-title":"Comput. Biol. Med."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Sharma, V., Kaur, S., Kumar, J., and Singh, A.K. (2019, January 15\u201317). A Fast Parkinson\u2019s Disease Prediction Technique using PCA and Artificial Neural Network. Proceedings of the 2019 International Conference on Intelligent Computing and Control Systems (ICCS), Madurai, India.","DOI":"10.1109\/ICCS45141.2019.9065876"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e12472","DOI":"10.1111\/exsy.12472","article-title":"Diagnosis of Parkinson\u2019s disease from electroencephalography signals using linear and self-similarity features","volume":"39","author":"Bhurane","year":"2022","journal-title":"Expert. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Jebakumari, V.S., Shanthi, D., Sridevi, S., and Meha, P. (2017, January 23\u201325). Performance evaluation of various classification algorithms for the diagnosis of Parkinson\u2019s disease. Proceedings of the 2017 IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS), Srivilliputtur, India.","DOI":"10.1109\/ITCOSP.2017.8303089"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1002\/mds.20507","article-title":"Treadmill walking as an external pacemaker to improve gait rhythm and stability in Parkinson\u2019s disease","volume":"20","author":"Giladi","year":"2005","journal-title":"Mov. Disord."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"183","DOI":"10.3233\/NRE-2005-20305","article-title":"Gait and step training to reduce falls in Parkinson\u2019s disease","volume":"20","author":"Protas","year":"2005","journal-title":"NeuroRehabilitation"},{"key":"ref_31","first-page":"CD007830","article-title":"Treadmill training for patients with Parkinson\u2019s disease","volume":"2015","author":"Mehrholz","year":"2015","journal-title":"Cochrane Database Syst. Rev."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1186\/s40814-018-0355-8","article-title":"Effects of yoga on oxidative stress, motor function, and non-motor symptoms in Parkinson\u2019s disease: A pilot randomized controlled trial","volume":"4","author":"Cheung","year":"2018","journal-title":"Pilot. Feasibility Stud."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Rahman, M.A., Tutul, A.A., and Islam, A.B.M.A.A. (2020, January 22\u201324). Solving The Maze of Diagnosing Parkinson\u2019s Disease based on Portable EEG Sensing to be Adaptable to Go In-The-Wild. Proceedings of the 7th International Conference on Networking, Systems and Security, Dhaka, Bangladesh.","DOI":"10.1145\/3428363.3428374"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.patrec.2023.03.011","article-title":"Improving Parkinson\u2019s disease recognition through voice analysis using deep learning","volume":"168","author":"Khaskhoussy","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1749","DOI":"10.1007\/s11682-022-00631-y","article-title":"Deep learning based diagnosis of Parkinson\u2019s Disease using diffusion magnetic resonance imaging","volume":"16","author":"Zhao","year":"2022","journal-title":"Brain Imaging Behav."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2641","DOI":"10.1007\/s10072-023-07154-4","article-title":"Prediction of Parkinson\u2019s disease by transcranial sonography-based deep learning","volume":"45","author":"Ding","year":"2024","journal-title":"Neurol. Sci."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2144","DOI":"10.1002\/mds.28631","article-title":"Detecting Sensitive Mobility Features for Parkinson\u2019s Disease Stages Via Machine Learning","volume":"36","author":"Mirelman","year":"2021","journal-title":"Mov. Disord."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"e49023","DOI":"10.2196\/49023","article-title":"Practical Considerations and Applied Examples of Cross-Validation for Model Development and Evaluation in Health Care: Tutorial","volume":"2","author":"Wilimitis","year":"2023","journal-title":"JMIR AI"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/s12561-015-9125-9","article-title":"Permutation Testing for Treatment-Covariate Interactions and Subgroup Identification","volume":"8","author":"Foster","year":"2016","journal-title":"Stat. Biosci."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1007\/s00415-025-13085-1","article-title":"The experience and perception of wearable devices in Parkinson\u2019s disease patients: A systematic review and meta-synthesis of qualitative studies","volume":"272","author":"Ma","year":"2025","journal-title":"J. Neurol."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Rodriguez-Martin, D., and Perez-Lopez, C. (2024). Commercial symptom monitoring devices in Parkinson\u2019s disease: Benefits, limitations, and trends. Front. Neurol., 15.","DOI":"10.3389\/fneur.2024.1470928"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Kim, J., Kim, K.-C., Tack, G., and Choi, J.-S. (2025). Estimation of 3D Ground Reaction Force and 2D Center of Pressure Using Deep Learning and Load Cells Across Various Gait Conditions. Sensors, 25.","DOI":"10.3390\/s25113357"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Gutowski, T., Stodulska, O., \u0106wikli\u0144ska, A., Gutowska, K., Kope\u0107, K., Betka, M., Antkiewicz, R., Koziorowski, D., and Szlufik, S. (2025). Machine Learning-Based Assessment of Parkinson\u2019s Disease Symptoms Using Wearable and Smartphone Sensors. Sensors, 25.","DOI":"10.3390\/s25164924"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/s41531-024-00678-2","article-title":"Distinguishing features of Parkinson\u2019s disease fallers based on wireless insole plantar pressure monitoring","volume":"10","author":"Herbers","year":"2024","journal-title":"NPJ Park. Dis."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Delafontaine, A., Hansen, C., Marolleau, I., Kratzenstein, S., and Gouelle, A. (2020). Effect of a Concurrent Cognitive Task, with Stabilizing Visual Information and Withdrawal, on Body Sway Adaptation of Parkinsonian\u2019s Patients in an Off-Medication State: A Controlled Study. Sensors, 20.","DOI":"10.3390\/s20185059"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"906","DOI":"10.1177\/15459683251363242","article-title":"Transcranial Direct Current Stimulation on Supplementary Motor Area Enhances the Effects of Exercise Therapy for Proprioception and Balance in People with Parkinson\u2019s: An Exploratory Pilot Trial","volume":"39","author":"Heydarpour","year":"2025","journal-title":"Neurorehabil Neural Repair."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1177\/10538135251317418","article-title":"Effects of Physical Therapy on Ankle Proprioception and Postural Control in People with Parkinson\u2019s: A Semi-experimental Clinical Trial","volume":"56","author":"Taheri","year":"2025","journal-title":"NeuroRehabilitation"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Ferrari, L., Bochicchio, G., Bottari, A., Scarton, A., Lucertini, F., and Pogliaghi, S. (2024). Construct Validity of a Wearable Inertial Measurement Unit (IMU) in Measuring Postural Sway and the Effect of Visual Deprivation in Healthy Older Adults. Biosensors, 14.","DOI":"10.3390\/bios14110529"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Al-Ayyad, M., Owida, H.A., De Fazio, R., Al-Naami, B., and Visconti, P. (2023). Electromyography Monitoring Systems in Rehabilitation: A Review of Clinical Applications, Wearable Devices and Signal Acquisition Methodologies. Electronics, 12.","DOI":"10.3390\/electronics12071520"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Prisco, G., Pirozzi, M.A., Santone, A., Esposito, F., Cesarelli, M., Amato, F., and Donisi, L. (2024). Validity of Wearable Inertial Sensors for Gait Analysis: A Systematic Review. Diagnostics, 15.","DOI":"10.3390\/diagnostics15010036"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Trabassi, D., Castiglia, S.F., Bini, F., Marinozzi, F., Ajoudani, A., Lorenzini, M., Chini, G., Varrecchia, T., Ranavolo, A., and De Icco, R. (2024). Optimizing Rare Disease Gait Classification through Data Balancing and Generative AI: Insights from Hereditary Cerebellar Ataxia. Sensors, 24.","DOI":"10.3390\/s24113613"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Ando, B., Baglio, S., Manenti, M., Finocchiaro, V., Marletta, V., Rajan, S., Nehary, E.A., Dibilio, V., Zappia, M., and Mostile, G. (2025). Investigating Performance of an Embedded Machine Learning Solution for Classifying Postural Behaviors. Sensors, 25.","DOI":"10.3390\/s25144262"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/22\/2855\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T06:58:20Z","timestamp":1762930700000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/22\/2855"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":52,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["diagnostics15222855"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15222855","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,12]]}}}