{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T00:16:09Z","timestamp":1789172169163,"version":"build-2803163510"},"reference-count":45,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Italian Ministry"},{"name":"University of Salento","award":["CUP: F83C22000810006"],"award-info":[{"award-number":["CUP: F83C22000810006"]}]},{"award":["CUP: F83C22000810006"],"award-info":[{"award-number":["CUP: F83C22000810006"]}],"id":[{"id":"https:\/\/ror.org\/03fc1k060","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Introduction: Voice-based digital biomarkers have emerged as a promising approach for distinguishing individuals with neurodegenerative disorders, particularly Parkinson\u2019s disease (PD), from healthy subjects (HS). With the increasing availability of smartphone and web-based recording tools, voice data can be collected efficiently in both clinical and remote settings. However, further validation is required before such approaches can be translated into routine clinical practice. Methods: This study used a cross-sectional analysis at the recording level, treating repeated recordings from the same participant as separate observations collected at Vito Fazzi Hospital in Lecce, Italy. Speech recordings from individuals with Parkinson\u2019s disease (PD) and healthy controls were collected using the dedicated Talia smartphone and web application. Sustained vowel phonation (\/a\/) was analyzed as the primary speech task. Following data acquisition, feature extraction was performed as a crucial step in the speech analysis pipeline, as the quality and relevance of the extracted features directly influence the ability of machine learning models to discriminate between Parkinson\u2019s disease (PD) patients and healthy controls. To capture various aspects of speech impairment associated with PD, a comprehensive set of acoustic features was extracted, including long-term features (pitch, jitter, and shimmer), nonlinear descriptors such as Recurrence Period Density Entropy (RPDE), and short-term feature based on Mel-Frequency Cepstral Coefficients (MFCCs). These features were subsequently used to develop and evaluate machine learning models for the classification of Parkinson\u2019s disease and healthy subjects. Feature selection was performed using SHAP to identify the most informative vocal biomarkers. Model performance was assessed using five independent random train\u2013test splits (70% training and 30% testing), supported by an internal five-fold cross-validation procedure within the training data. Multiple machine learning models were developed and evaluated, including Random Forest, Logistic Regression, Support Vector Machine, Naive Bayes, K-Nearest Neighbors, Decision Tree, Artificial Neural Network, and Gradient Boosting. Results: The evaluated models demonstrated strong recording-level classification performance. Artificial Neural Networks (ANN) and K-Nearest Neighbors (KNN) achieved the highest accuracy scores (0.9545 and 0.9494, respectively), along with superior recall (up to 0.9500), precision (up to 0.9551), and F1-score (up to 0.9525). Both models also exhibited excellent discriminative ability, with ROC-AUC values reaching 0.9882 (ANN) and 0.9893 (KNN). In contrast, Naive Bayes and Decision Tree showed comparatively lower performance across all metrics. Log-loss analysis further confirmed the robustness of ANN and KNN, which achieved the lowest values (0.2552 and 0.2510, respectively), indicating well-calibrated predictions. Overall, the findings highlight the consistency and generalizability of ANN and KNN across cross-validation splits. Conclusions: This study demonstrates that machine learning models, particularly ANN and KNN, can effectively differentiate Parkinson\u2019s disease from healthy conditions using voice recordings. The integration of explainable AI for feature selection enhances model transparency and clinical relevance. However, the reported performance estimates were obtained from a recording-level analysis and should be interpreted as preliminary findings. Further studies involving larger cohorts and participant-level validation strategies are required to determine the generalizability and clinical applicability of these approaches.<\/jats:p>","DOI":"10.3390\/bioengineering13080917","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T11:33:46Z","timestamp":1786620826000},"page":"917","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Pilot Study Employing a Machine Learning Approach as a Potential Method for Predicting Parkinson\u2019s Disease Using Voice as a Digital Biomarker and the SHAP Approach for Feature Engineering"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7452-2715","authenticated-orcid":false,"given":"Mehdi","family":"Rashidi","sequence":"first","affiliation":[{"name":"Department of Mathematics and Physics \u201cE. De Giorgi\u201d, University of Salento, Via Lecce-Arnesano, 73100 Lecce, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syed Adil Hussain","family":"Shah","sequence":"additional","affiliation":[{"name":"PolitoBioMed Lab, Department of Mechanical and Aerospace Engineering, Politecnico di Torino, 10129 Torino, Italy"},{"name":"Department of Research and Development (R&D), GPI SpA, 38123 Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chiara","family":"Coppola","sequence":"additional","affiliation":[{"name":"Department of Experimental Medicine, University of Salento, Via Lecce-Monteroni, 73100 Lecce, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1042-8911","authenticated-orcid":false,"given":"Andrea","family":"Buccoliero","sequence":"additional","affiliation":[{"name":"Department of Research and Development (R&D), GPI SpA, 38123 Trento, Italy"},{"name":"Human Science Department, University of Verona, Lungadige Porta Vittoria, 17, 37129 Verona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Serena","family":"Arima","sequence":"additional","affiliation":[{"name":"Department of Human and Social Sciences, University of Salento, 73100 Lecce, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angela","family":"Lupo","sequence":"additional","affiliation":[{"name":"Division of Neurology, Vito Fazzi Hospital, 73100 Lecce, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Filomena","family":"My","sequence":"additional","affiliation":[{"name":"Division of Neurology, Vito Fazzi Hospital, 73100 Lecce, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marta","family":"Lorenzo","sequence":"additional","affiliation":[{"name":"Division of Neurology, Vito Fazzi Hospital, 73100 Lecce, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcello","family":"Donzella","sequence":"additional","affiliation":[{"name":"Department of Research and Development (R&D), GPI SpA, 38123 Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0665-4534","authenticated-orcid":false,"given":"Michele","family":"Maffia","sequence":"additional","affiliation":[{"name":"Department of Experimental Medicine, University of Salento, Via Lecce-Monteroni, 73100 Lecce, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Rashidi, M., Arima, S., Stetco, A.C., Coppola, C., Musar\u00f2, D., Greco, M., Damato, M., My, F., Lupo, A., and Lorenzo, M. (2025). Prediction of Parkinson Disease Using Long-Term, Short-Term Acoustic Features Based on Machine Learning. Brain Sci., 15.","DOI":"10.20944\/preprints202504.0803.v1"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"17013","DOI":"10.1038\/nrdp.2017.13","article-title":"Parkinson disease","volume":"3","author":"Poewe","year":"2017","journal-title":"Nat. Rev. Dis. Primers"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Macedo, V.F.B., Macedo, V.K.B., de Miranda Coelho, J.A.P., and de Melo Barboza, A.M. (2025). Parkinson\u2019s disease physiopathology\u2014Beyond the \u03b1-synuclein aggregation: A narrative review. Front. Aging Neurosci., 17.","DOI":"10.3389\/fnagi.2025.1664269"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1002\/mds.30067","article-title":"Environmental Risk Factors for Parkinson\u2019s Disease: A Critical Review and Policy Implications","volume":"40","author":"Brolin","year":"2025","journal-title":"Mov. Disord."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"501","DOI":"10.5603\/pjnns.109238","article-title":"Importance of hypoglycemia episodes and glycemic variability in parkinsonian syndromes","volume":"59","author":"Alster","year":"2025","journal-title":"Neurol. Neurochir. Pol."},{"key":"ref_6","first-page":"1322","article-title":"A PLAN to address the Parkinson pandemic","volume":"15","author":"Dorsey","year":"2025","journal-title":"J. Park. Dis."},{"key":"ref_7","first-page":"S3","article-title":"The emerging evidence of the Parkinson pandemic","volume":"8","author":"Dorsey","year":"2018","journal-title":"J. Park. Dis."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s40801-023-00410-1","article-title":"Economic Burden of Parkinson\u2019s Disease: A Multinational, Real-World, Cost-of-Illness Study","volume":"11","author":"Chaudhuri","year":"2024","journal-title":"Drugs Real World Outcomes"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1016\/j.neubiorev.2016.07.010","article-title":"Motor symptoms in Parkinson\u2019s disease: A unified framework","volume":"68","author":"Moustafa","year":"2016","journal-title":"Neurosci. Biobehav. Rev."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"439","DOI":"10.2174\/187152712800792893","article-title":"Motor and Non-Motor Features of Parkinson\u2019s Disease-A Review of Clinical and Experimental Studies","volume":"11","author":"Lima","year":"2012","journal-title":"CNS Neurol. Disord.-Drug Targets"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1125","DOI":"10.1002\/mds.26643","article-title":"Prevalence of anxiety in Parkinson\u2019s disease: A systematic review and meta-analysis","volume":"31","author":"Broen","year":"2016","journal-title":"Mov. Disord."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"e2517","DOI":"10.1002\/brb3.2517","article-title":"The quality of life in patients with Parkinson\u2019s disease: Focus on gender difference","volume":"12","author":"Meng","year":"2022","journal-title":"Brain Behav."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"S87","DOI":"10.1016\/S1353-8020(09)70789-8","article-title":"Non-motor features of Parkinson\u2019s disease: Depression and dementia","volume":"15","author":"Reichmann","year":"2009","journal-title":"Park. Relat. Disord."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1002\/mds.870130606","article-title":"A Community-Based Study of Sleep Disorders in Patients with Parkinson\u2019s Disease","volume":"13","author":"Tandberg","year":"1998","journal-title":"Mov. Disord."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.parkreldis.2010.08.003","article-title":"Gastrointestinal Dysfunction in Parkinson\u2019s Disease","volume":"17","author":"Pfeiffer","year":"2011","journal-title":"Park. Relat. Disord."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/s00702-023-02696-5","article-title":"Constipation and pain in Parkinson\u2019s disease: A clinical analysis","volume":"131","author":"Grillo","year":"2024","journal-title":"J. Neural Transm."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Khedimi, M., Zhang, T., Merzougui, H., Zhao, X., Geng, Y., Djaroudib, K., and Lorenz, P. (2024). Architecture-Aware Augmentation: A Hybrid Deep Learning and Machine Learning Approach for Enhanced Parkinson\u2019s Disease Detection. Bioengineering, 11.","DOI":"10.3390\/bioengineering11121218"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"104013","DOI":"10.1016\/j.bspc.2022.104013","article-title":"Automatic Parkinson\u2019s disease detection based on the combination of long-term acoustic features and Mel frequency cepstral coefficients (MFCC)","volume":"78","author":"Hawi","year":"2022","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Shahbakhti, M., Taherifar, D., and Sorouri, A. (2013). Linear and non-linear speech features for detection of Parkinson\u2019s disease. Proceedings of the BMEiCON 2013: The 6th Biomedical Engineering International Conference, Krabi, Thailand, 23\u201325 October 2013, IEEE.","DOI":"10.1109\/BMEiCon.2013.6687667"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1007\/s12559-017-9497-x","article-title":"Parkinson\u2019s Disease and Aging: Analysis of Their Effect in Phonation and Articulation of Speech","volume":"9","year":"2017","journal-title":"Cogn. Comput."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.compbiomed.2015.07.026","article-title":"Voice data mining for laryngeal pathology assessment","volume":"69","author":"Hemmerling","year":"2016","journal-title":"Comput. Biol. Med."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/1475-925X-6-23","article-title":"Exploiting nonlinear recurrence and fractal scaling properties for voice disorder detection","volume":"6","author":"Little","year":"2007","journal-title":"Biomed. Eng. Online"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"James, G., Witten, D., Hastie, T., Tibshirani, R., and Taylor, J. (2023). An Introduction to Statistics with Python: With Applications in the Life Sciences (Statistics and Computing), Springer Nature.","DOI":"10.1007\/978-3-031-38747-0"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Arrieta","year":"2020","journal-title":"Inf. Fusion"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u2018Why should i trust you?\u2019 Explaining the predictions of any classifier. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"V\u00e1squez-Correa, J.C., Arias-Vergara, T., Rios-Urrego, C.D., Schuster, M., Rusz, J., Orozco-Arroyave, J.R., and N\u00f6th, E. (2020). Convolutional Neural Networks and a Transfer Learning Strategy to Classify Parkinson\u2019s Disease from Speech in Three Different Languages, Springer.","DOI":"10.1007\/978-3-030-33904-3_66"},{"key":"ref_28","unstructured":"(2026, June 10). NT-USB|Professional USB Microphone|R\u00d8DE (AU). Available online: https:\/\/rode.com\/en-au\/products\/nt-usb?utm_source=chatgpt.com."},{"key":"ref_29","unstructured":"(2026, June 10). POHEMA. Available online: https:\/\/svisrvalcme.gpi.it\/DOC\/WIP\/bin\/login-home\/LogOut.pl."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"20615","DOI":"10.1038\/s41598-023-47568-w","article-title":"A machine learning method to process voice samples for identification of Parkinson\u2019s disease","volume":"13","author":"Iyer","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Suppa, A., Costantini, G., Asci, F., Di Leo, P., Al-Wardat, M.S., Di Lazzaro, G., Scalise, S., Pisani, A., and Saggio, G. (2022). Voice in Parkinson\u2019s Disease: A Machine Learning Study. Front. Neurol., 13.","DOI":"10.3389\/fneur.2022.831428"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1186\/s13636-018-0140-x","article-title":"The use of long-term features for GMM- and i-vector-based speaker diarization systems","volume":"2018","author":"Zewoudie","year":"2018","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.1109\/TBME.2008.2005954","article-title":"Suitability of dysphonia measurements for telemonitoring of Parkinson\u2019s disease","volume":"56","author":"Little","year":"2008","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","article-title":"Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences","volume":"28","author":"Davis","year":"1980","journal-title":"IEEE Trans. Acoust."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1109\/TBME.2012.2183367","article-title":"Novel speech signal processing algorithms for high-accuracy classification of Parkinsons disease","volume":"59","author":"Tsanas","year":"2012","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"11687","DOI":"10.1038\/s41598-025-96575-6","article-title":"Explainable artificial intelligence to diagnose early Parkinson\u2019s disease via voice analysis","volume":"15","author":"Shen","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"James, G., Witten, D., Hastie, T., Tibshirani, R., and Taylor, J. (2023). An Introduction to Statistical Learning: With Applications in Python, Springer Nature.","DOI":"10.1007\/978-3-031-38747-0"},{"key":"ref_38","first-page":"2229","article-title":"Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness and Correlation","volume":"2","author":"Powers","year":"2020","journal-title":"J. Mach. Learn. Technol."},{"key":"ref_39","first-page":"101598","article-title":"Developing and testing AI-based voice biomarker models to detect cognitive impairment among community dwelling adults: A cross-sectional study in Japan","volume":"59","author":"Kiyoshige","year":"2025","journal-title":"Lancet Reg. Health West. Pac."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Wroge, T.J., Ozkanca, Y., Demiroglu, C., Si, D., Atkins, D.C., and Ghomi, R.H. (2018, January 1). Parkinson\u2019s Disease Diagnosis Using Machine Learning and Voice. Proceedings of the 2018 IEEE Signal Processing in Medicine and Biology Symposium (SPMB), Philadelphia, PA, USA.","DOI":"10.1109\/SPMB.2018.8615607"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"8624","DOI":"10.1038\/s41598-025-88293-w","article-title":"Enhancing parkinson disease detection through feature based deep learning with autoencoders and neural networks","volume":"15","author":"Valarmathi","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1038\/s41531-025-00953-w","article-title":"Smartphone-derived multidomain features including voice, finger-tapping movement and gait aid early identification of Parkinson\u2019s disease","volume":"11","author":"Lim","year":"2025","journal-title":"npj Park. Dis."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"101524","DOI":"10.1016\/j.imu.2024.101524","article-title":"Hybrid grey wolf and whale optimization for enhanced Parkinson\u2019s prediction based on machine learning models using biomedical sound","volume":"48","year":"2024","journal-title":"Inform. Med. Unlocked"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Costantini, G., Cesarini, V., Di Leo, P., Amato, F., Suppa, A., Asci, F., Pisani, A., Calculli, A., and Saggio, G. (2023). Artificial Intelligence-Based Voice Assessment of Patients with Parkinson\u2019s Disease Off and On Treatment: Machine vs. Deep-Learning Comparison. Sensors, 23.","DOI":"10.3390\/s23042293"},{"key":"ref_45","first-page":"95","article-title":"Machine Learning-Based Classification of Parkinson\u2019s Disease Patients Using Speech Biomarkers","volume":"14","author":"Hossain","year":"2024","journal-title":"J. Park. Dis."}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/8\/917\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T04:25:30Z","timestamp":1786767930000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/8\/917"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":45,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["bioengineering13080917"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering13080917","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]}}}