{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T21:45:44Z","timestamp":1788471944704,"version":"build-2803163510"},"reference-count":44,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Parkinson\u2019s disease (PD) is a progressive neurodegenerative disorder that significantly affects motor functions, including speech production. Voice analysis offers a less invasive, faster and more cost-effective approach for diagnosing and monitoring PD over time. This research introduces an automated system to distinguish between PD and non-PD individuals based on speech signals using state-of-the-art signal processing and machine learning (ML) methods. A publicly available voice dataset (Dataset 1, 81 samples) containing speech recordings from PD patients and non-PD individuals was used for model training and evaluation. Additionally, a small supplementary dataset (Dataset 2, 15 samples) was created although excluded from experiment, to illustrate potential future extensions of this work. Features such as Mel-frequency cepstral coefficients (MFCCs), spectrograms, Mel spectrograms and waveform representations were extracted to capture key vocal impairments related to PD, including diminished vocal range, weak harmonics, elevated spectral entropy and impaired formant structures. These extracted features were used to train and evaluate several ML models, including support vector machine (SVM), XGBoost and logistic regression, as well as deep learning (DL)architectures such as deep neural networks (DNN), convolutional neural networks (CNN) combined with long short-term memory (LSTM), CNN + gated recurrent unit (GRU) and bidirectional LSTM (BiLSTM). Experimental results show that DL models, particularly BiLSTM, outperform traditional ML models, achieving 97% accuracy and an AUC of 0.95. The comprehensive feature extraction from both datasets enabled robust classification of PD and non-PD speech signals. These findings highlight the potential of integrating acoustic features with DL methods for early diagnosis and monitoring of Parkinson\u2019s Disease.<\/jats:p>","DOI":"10.3390\/bioengineering12101052","type":"journal-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T12:59:46Z","timestamp":1759150786000},"page":"1052","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Voice-Based Early Diagnosis of Parkinson\u2019s Disease Using Spectrogram Features and AI Models"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5447-4437","authenticated-orcid":false,"given":"Danish","family":"Quamar","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Mizoram University, Mizoram 796004, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7722-2398","authenticated-orcid":false,"given":"V. D.","family":"Ambeth Kumar","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Mizoram University, Mizoram 796004, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Rizwan","sequence":"additional","affiliation":[{"name":"Data Science Research Centre, College of Science & Engineering, University of Derby, Derby DE22 1GB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ovidiu","family":"Bagdasar","sequence":"additional","affiliation":[{"name":"Data Science Research Centre, College of Science & Engineering, University of Derby, Derby DE22 1GB, UK"},{"name":"Department of Mathematics, Faculty of Exact Sciences, \u201c1 Decembrie 1918\u201d University of Alba Iulia, 510009 Alba Iulia, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3110-7164","authenticated-orcid":false,"given":"Manuella","family":"Kadar","sequence":"additional","affiliation":[{"name":"Centre of Research Project Management \u201c1 Decembrie 1918\u201d University of Alba Iulia, 510009 Alba Iulia, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"a008862","DOI":"10.1101\/cshperspect.a008862","article-title":"The history of Parkinson\u2019s disease: Early clinical descriptions and neurological therapies","volume":"1","author":"Goetz","year":"2011","journal-title":"Cold Spring Harb. Perspect. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"46","DOI":"10.3121\/cmr.2009.883","article-title":"Jean-Martin Charcot: The father of neurology","volume":"9","author":"Kumar","year":"2011","journal-title":"Clin. Med. Res."},{"key":"ref_3","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.1007\/s12559-018-9575-8","article-title":"Quantitative Analysis of Relationship Between Hypokinetic Dysarthria and the Freezing of Gait in PD","volume":"10","author":"Mekyska","year":"2018","journal-title":"Cogn. Comput."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e25469","DOI":"10.1016\/j.heliyon.2024.e25469","article-title":"A review of ML and DL algorithms for Parkinson\u2019s disease detection using handwriting and voice datasets","volume":"10","author":"Islam","year":"2024","journal-title":"Heliyon"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1007\/s44250-024-00163-w","article-title":"The role and impact of new technologies on healthcare systems","volume":"3","author":"Sinha","year":"2024","journal-title":"Discov. Health Syst."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Liang, N., Li, H., Zhang, H., Li, H., Yan, L., Hu, Z., Chen, Y., Zhang, Y., and Wang, Y. (2024). Exploring explainable AI features in the vocal biomarkers of lung disease. Comput. Biol. Med., 179.","DOI":"10.1016\/j.compbiomed.2024.108844"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Dixit, S., Bohre, K., Singh, Y., Himeur, Y., Mansoor, W., Atalla, S., and Srinivasan, K. (2023). A Comprehensive Review on AI-Enabled Models for Parkinson\u2019s Disease Diagnosis. Electronics, 12.","DOI":"10.3390\/electronics12040783"},{"key":"ref_9","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_10","doi-asserted-by":"crossref","first-page":"899","DOI":"10.1007\/s44174-023-00068-x","article-title":"Artificial intelligence model for Parkinson disease detection using ML algorithms","volume":"1","author":"Yadav","year":"2023","journal-title":"Biomed. Mater. Devices"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"040010","DOI":"10.1063\/5.0236188","article-title":"Parkinson\u2019s disease detection from voice using artificial intelligence techniques: A review","volume":"3232","author":"Ali","year":"2023","journal-title":"AIP Conf. Proc."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Nijhawan, R., Kumar, M., Arya, S., Mendirtta, N., Kumar, S., Towfek, S.K., Khafaga, D.S., Alkahtani, H.K., and Abdelhamid, A.A. (2023). A novel artificial-intelligence-based approach for classification of Parkinson\u2019s disease using complex and large vocal features. Biomimetics, 8.","DOI":"10.3390\/biomimetics8040351"},{"key":"ref_13","first-page":"28","article-title":"Artificial intelligence-based effective detection of Parkinson\u2019s disease using voice measurements","volume":"82","author":"Rohan","year":"2024","journal-title":"Eng. Proc."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Hoq, M., Uddin, M.N., and Park, S.-B. (2021). Vocal feature extraction-based artificial intelligent model for Parkinson\u2019s disease detection. Diagnostics, 11.","DOI":"10.3390\/diagnostics11061076"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"115013","DOI":"10.1016\/j.eswa.2021.115013","article-title":"Robust automated Parkinson disease detection based on voice signals with transfer learning","volume":"178","author":"Karaman","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Bukhari, S.N.H., and Ogudo, K.A. (2024). Ensemble ML approach for Parkinson\u2019s disease detection using speech signals. Mathematics, 12.","DOI":"10.3390\/math12101575"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1386","DOI":"10.1109\/TASLP.2023.3260709","article-title":"Exemplar-based sparse representations for detection of Parkinson\u2019s disease from speech","volume":"31","author":"Reddy","year":"2023","journal-title":"ACM Trans. Audio Speech Lang. Process."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"109657","DOI":"10.1016\/j.apacoust.2023.109657","article-title":"High-resolution superlet transform based techniques for Parkinson\u2019s disease detection using speech signal","volume":"214","author":"Bhatt","year":"2023","journal-title":"Appl. Acoust."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"103040","DOI":"10.1016\/j.specom.2024.103040","article-title":"Automatic classification of neurological voice disorders using wavelet scattering features","volume":"157","author":"Yagnavajjula","year":"2024","journal-title":"Speech Commun."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"582","DOI":"10.1016\/S1808-8694(15)31261-1","article-title":"Analysis of fundamental frequency, jitter, shimmer and vocal intensity in children with phonological disorders","volume":"71","author":"Wertzner","year":"2005","journal-title":"Braz. J. Otorhinolaryngol."},{"key":"ref_21","first-page":"38","article-title":"Mel frequency cepstral coefficients (MFCC) feature extraction enhancement in the application of speech recognition: A comparison study","volume":"79","author":"Majeed","year":"2015","journal-title":"J. Theor. Appl. Inf. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhu, X.-C., Zhao, D.-H., Zhang, Y.-H., Zhang, X.-J., and Tao, Z. (2022). Multi-Scale Recurrence Quantification Measurements for Voice Disorder Detection. Appl. Sci., 12.","DOI":"10.3390\/app12189196"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Iyer, A., Kemp, A., Rahmatallah, Y., Pillai, L., Glover, A., Prior, F., Larson-Prior, L., and Virmani, T. (2023). A ML method to process voice samples for identification of Parkinson\u2019s disease. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-47568-w"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kumar, E., Surya, K., Varma, K., Akash, A., and Kurapati, N.R. (2023). Noise reduction in audio file using spectral gating and FFT by Python modules. Recent Developments in Electronics and Communication Systems, IOS Press.","DOI":"10.3233\/ATDE221305"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Majda-Zdancewicz, E., Potulska-Chromik, A., Nojszewska, M., and Kostera-Pruszczyk, A. (2024). Speech signal analysis in patients with Parkinson\u2019s disease, taking into account phonation, articulation and prosody of speech. Appl. Sci., 14.","DOI":"10.3390\/app142311085"},{"key":"ref_26","unstructured":"Kua, J.M.K., Thiruvaran, T., Nosrati, H., Ambikairajah, E., and Epps, J. (July, January 28). Investigation of spectral centroid magnitude and frequency for speaker recognition. Proceedings of the Speaker and Language Recognition Workshop, Brno, Czech Republic."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2025","journal-title":"Neural Netw."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e34593","DOI":"10.1016\/j.heliyon.2024.e34593","article-title":"PD-DETECTOR: A sustainable and computationally intelligent mobile application model for Parkinson\u2019s disease severity assessment","volume":"10","author":"Mishra","year":"2024","journal-title":"Heliyon"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Shih, D.-H., Liao, C.-H., Tin-Wei, W., Xu, X.-Y., and Shih, M.-H. (2022). Dysarthria speech detection using convolutional neural networks with gated recurrent unit. Healthcare, 10.","DOI":"10.3390\/healthcare10101956"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Mienye, I.D., Swart, T.G., and Obaido, G. (2024). Recurrent Neural Networks: A Comprehensive Review of Architectures, Variants and Applications. Information, 15.","DOI":"10.20944\/preprints202408.0748.v1"},{"key":"ref_31","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":"2009","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"884","DOI":"10.1109\/TBME.2009.2036000","article-title":"Accurate telemonitoring of Parkinson\u2019s disease progression by noninvasive speech tests","volume":"57","author":"Tsanas","year":"2010","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_33","first-page":"1001","article-title":"Detection of Parkinson\u2019s disease by acoustic analysis: The case of vowels","volume":"25","author":"Ferrer","year":"2009","journal-title":"IFMBE Proc."},{"key":"ref_34","unstructured":"Sakar, C.O., Kursun, O., and Karamzadeh, S. (2020). A comparative study of voice and speech pattern for Parkinson disease detection using ML methods. Comput. Methods Programs Biomed., 197."},{"key":"ref_35","first-page":"1151","article-title":"Quantitative acoustic measurements for characterization of speech and voice disorders in early untreated Parkinson\u2019s disease","volume":"137","author":"Rusz","year":"2015","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_36","unstructured":"Dey, N., Ashour, A., and Balas, V.E. (2020). ML for Speech and Audio Processing in Parkinson\u2019s Disease Diagnosis. Smart Medical Data Sensing and IoT Systems Design in Healthcare, Springer."},{"key":"ref_37","first-page":"584","article-title":"Automatic detection of pathologies in the voice by HMMs","volume":"51","author":"Alonso","year":"2004","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1943","DOI":"10.1109\/TBME.2006.871883","article-title":"Dimensionality reduction of a pathological voice quality assessment system based on Gaussian mixture models and short-term cepstral parameters","volume":"53","year":"2006","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Cohen, J.P., Luck, M., and Honari, S. (2018). Distribution matching losses can hallucinate features in medical image translation. Medical Image Computing and Computer Assisted Intervention (MICCAI), Springer.","DOI":"10.1007\/978-3-030-00928-1_60"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"V\u00e1squez-Correa, J.C., Klumpp, P., Orozco-Arroyave, J.R., and N\u00f6th, E. (2017, January 20\u201324). Convolutional neural network to model articulation impairments in patients with Parkinson\u2019s disease. Proceedings of the Annual Conference of the International Speech Communication Association, Stockholm, Sweden.","DOI":"10.21437\/Interspeech.2017-1078"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"576","DOI":"10.1007\/s42452-024-06295-1","article-title":"Parkinson\u2019s disease detection by using machine learning method based on local classification on class boundary","volume":"6","author":"Du","year":"2024","journal-title":"Discov. Appl. Sci."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1038\/s41531-025-01025-9","article-title":"Machine learning for Parkinson\u2019s disease: A comprehensive review of datasets, algorithms, and challenges","volume":"11","author":"Shokrpour","year":"2025","journal-title":"NPJ Park. Dis."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2023.3284944","article-title":"Detection and classification of early stages of Parkinson\u2019s disease through wearable sensors and machine learning","volume":"72","author":"Shcherbak","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Rahmatallah, Y., Kemp, A.S., Iyer, A., Pillai, L., Larson-Prior, L.J., Virmani, T., and Prior, F. (2025). Pre-trained convolutional neural networks identify Parkinson\u2019s disease from spectrogram images of voice samples. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-92105-6"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/10\/1052\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:35:27Z","timestamp":1759235727000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/10\/1052"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"references-count":44,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["bioengineering12101052"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering12101052","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]}}}