{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,14]],"date-time":"2026-11-14T01:32:14Z","timestamp":1794619934693,"version":"4.9.1"},"reference-count":80,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100006108","name":"National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["UL1TR003107"],"award-info":[{"award-number":["UL1TR003107"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Foundation, United States","award":["OIA-1946391"],"award-info":[{"award-number":["OIA-1946391"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Machine learning approaches including deep learning models have shown promising performance in the automatic detection of Parkinson\u2019s disease. These approaches rely on different types of data with voice recordings being the most used due to the convenient and non-invasive nature of data acquisition. Our group has successfully developed a novel approach that uses convolutional neural network with transfer learning to analyze spectrogram images of the sustained vowel \/a\/ to identify people with Parkinson\u2019s disease. We tested this approach by collecting a dataset of voice recordings via analog telephone lines, which support limited bandwidth. The convolutional neural network with transfer learning approach showed superior performance against conventional machine learning methods that collapse measurements across time to generate feature vectors. This study builds upon our prior results and presents two novel contributions: First, we tested the performance of our approach on a larger voice dataset recorded using smartphones with wide bandwidth. Our results show that the pre-trained convolutional neural network slightly outperformed other classifiers using the dataset recorded using telephone lines, and slightly underperformed other classifiers in the dataset recorded using smartphones. Important features were different in the two datasets, likely due to the limited bandwidth of analog telephonic lines. Second, we compared the classification performance achieved using linear-scale and mel-scale spectrogram images and showed a small but statistically significant gain using mel-scale spectrograms.<\/jats:p>","DOI":"10.1038\/s41598-025-92105-6","type":"journal-article","created":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T09:40:24Z","timestamp":1740822024000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Pre-trained convolutional neural networks identify Parkinson\u2019s disease from spectrogram images of voice samples"],"prefix":"10.1038","volume":"15","author":[{"given":"Yasir","family":"Rahmatallah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron S.","family":"Kemp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anu","family":"Iyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lakshmi","family":"Pillai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linda J.","family":"Larson-Prior","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuhin","family":"Virmani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fred","family":"Prior","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,1]]},"reference":[{"key":"92105_CR1","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1002\/mds.29317","volume":"38","author":"S Virameteekul","year":"2023","unstructured":"Virameteekul, S., Revesz, T., Jaunmuktane, Z., Warner, T. T. & De Pablo-Fernandez, E. Clinical diagnostic accuracy of Parkinson\u2019s disease: where do we stand?? Mov. Disord. 38, 558\u2013566. https:\/\/doi.org\/10.1002\/mds.29317 (2023).","journal-title":"Mov. Disord"},{"key":"92105_CR2","doi-asserted-by":"publisher","first-page":"1591","DOI":"10.1002\/mds.26424","volume":"30","author":"RB Postuma","year":"2015","unstructured":"Postuma, R. B. et al. MDS clinical diagnostic criteria for Parkinson\u2019s disease. Mov. Disord. 30, 1591\u20131601. https:\/\/doi.org\/10.1002\/mds.26424 (2015).","journal-title":"Mov. Disord"},{"key":"92105_CR3","doi-asserted-by":"publisher","first-page":"2171","DOI":"10.1121\/1.4816541","volume":"134","author":"J Rusz","year":"2013","unstructured":"Rusz, J. et al. Imprecise vowel articulation as a potential early marker of Parkinson\u2019s disease: effect of speaking task. J. Acoust. Soc. Am. 134, 2171\u20132181 (2013).","journal-title":"J. Acoust. Soc. Am."},{"key":"92105_CR4","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1098\/rsif.2010.0456","volume":"8","author":"A Tsanas","year":"2011","unstructured":"Tsanas, A., Little, M. A., McSharry, P. E. & Ramig, L. O. Nonlinear speech analysis algorithms mapped to a standard metric achieve clinically useful quantification of average Parkinson\u2019s disease symptom severity. J. R. Soc. Interface 8, 842\u2013855 (2011).","journal-title":"J. Royal Soc. Interface"},{"key":"92105_CR5","doi-asserted-by":"publisher","first-page":"102418","DOI":"10.1016\/j.bspc.2021.102418","volume":"66","author":"L Moro-Velazquez","year":"2021","unstructured":"Moro-Velazquez, L., Gomez-Garcia, J. A., Arias-Londo\u00f1o, J. D. & Dehak, N. Godino-Llorente, J. I. Advances in Parkinson\u2019s disease detection and assessment using voice and speech: A review of the articulatory and phonatory aspects. Biomed. Signal Process. Control 66, 102418 (2021).","journal-title":"Biomed. Signal Process. Control"},{"key":"92105_CR6","doi-asserted-by":"publisher","first-page":"e0189583","DOI":"10.1371\/journal.pone.0189583","volume":"12","author":"J Godino-Llorente","year":"2017","unstructured":"Godino-Llorente, J., Shattuck-Hufnagel, S., Choi, J., Moro-Vel\u00e1zquez, L. & G\u00f3mez-Garc\u00eda, J. Towards the identification of idiopathic Parkinson\u2019s disease from the speech. New articulatory kinetic biomarkers. PloS ONE 12, e0189583 (2017).","journal-title":"PloS One"},{"key":"92105_CR7","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1121\/1.4939739","volume":"139","author":"JR Orozco-Arroyave","year":"2016","unstructured":"Orozco-Arroyave, J. R. et al. Automatic detection of Parkinson\u2019s disease in running speech spoken in three different languages. J. Acoust. Soc. Am. 139, 481\u2013500 (2016).","journal-title":"J. Acoust. Soc. Am."},{"key":"92105_CR8","doi-asserted-by":"publisher","first-page":"105021","DOI":"10.1016\/j.compbiomed.2021.105021","volume":"141","author":"M Hires","year":"2022","unstructured":"Hires, M. et al. Convolutional neural network ensemble for Parkinson\u2019s disease detection from voice recordings. Comput. Biol. Med. 141, 105021 (2022).","journal-title":"Comput. Biol. Med."},{"key":"92105_CR9","doi-asserted-by":"publisher","first-page":"904","DOI":"10.1016\/j.cmpb.2014.01.004","volume":"113","author":"M Hariharan","year":"2014","unstructured":"Hariharan, M., Polat, K. & Sindhu, R. A new hybrid intelligent system for accurate detection of Parkinson\u2019s disease. Comput. Methods Programs Biomed. 113, 904\u2013913 (2014).","journal-title":"Comput. Methods Programs Biomed."},{"key":"92105_CR10","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1016\/j.bspc.2013.02.006","volume":"8","author":"WL Zuo","year":"2013","unstructured":"Zuo, W. L., Wang, Z. Y., Liu, T. & Chen, H. L. Effective detection of Parkinson\u2019s disease using an adaptive fuzzy-nearest neighbor approach. Biomed. Signal. Proces 8, 364\u2013373 (2013).","journal-title":"Biomed. Signal. Proces"},{"key":"92105_CR11","doi-asserted-by":"crossref","unstructured":"Chollet, F. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 1800\u20131807 (2017).","DOI":"10.1109\/CVPR.2017.195"},{"key":"92105_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J. et al. Imagenet: A large-scale hierarchical image database. In IEEE Conference on Computer Vision and Pattern Recognition. 248\u2013255 (2009). (2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"92105_CR13","unstructured":"Venegas, D. A. R. & Dataset_of_vowels. https:\/\/www.kaggle.com\/datasets\/darubiano57\/dataset-of-vowels (2018)."},{"key":"92105_CR14","unstructured":"P\u00fctzer, M., Barry, W. J. & Saarbruecken voice database, Institute of Phonetics, Univ. of Saarland. https:\/\/stimmdb.coli.uni-saarland.de\/ (2007)."},{"key":"92105_CR15","doi-asserted-by":"crossref","unstructured":"Orozco-Arroyave, J. R., Arias-Londo\u00f1o, J. D., Vargas-Bonilla, J. F., Gonzalez-R\u00e1tiva, M. C. & N\u00f6th, E. New Spanish speech corpus database for the analysis of people suffering from Parkinson\u2019s disease. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914). 342\u2013347 (2014).","DOI":"10.63317\/3c643i6hcfzo"},{"key":"92105_CR16","doi-asserted-by":"publisher","first-page":"1618","DOI":"10.1109\/JBHI.2018.2866873","volume":"23","author":"JC Vasquez-Correa","year":"2019","unstructured":"Vasquez-Correa, J. C. et al. Multimodal assessment of Parkinson\u2019s disease: A deep learning approach. IEEE J. Biomed. Health Inf. 23, 1618\u20131630. https:\/\/doi.org\/10.1109\/JBHI.2018.2866873 (2019).","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"92105_CR17","doi-asserted-by":"publisher","first-page":"705","DOI":"10.3233\/THC-220386","volume":"31","author":"D Worasawate","year":"2023","unstructured":"Worasawate, D., Asawaponwiput, W., Yoshimura, N., Intarapanich, A. & Surangsrirat, D. Classification of Parkinson\u2019s disease from smartphone recording data using time-frequency analysis and convolutional neural network. Technol. Health Care 31, 705\u2013718. https:\/\/doi.org\/10.3233\/THC-220386 (2023).","journal-title":"Technol. Health Care"},{"key":"92105_CR18","doi-asserted-by":"publisher","first-page":"160011","DOI":"10.1038\/sdata.2016.11","volume":"3","author":"BM Bot","year":"2016","unstructured":"Bot, B. M. et al. The mPower study, Parkinson disease mobile data collected using researchkit. Sci. Data 3, 160011. https:\/\/doi.org\/10.1038\/sdata.2016.11 (2016).","journal-title":"Sci. Data"},{"key":"92105_CR19","doi-asserted-by":"publisher","unstructured":"Guatelli, R., Aubin, V., Mora, M., Naranjo-Torres, J. & Mora-Olivari, A. Detection of Parkinson\u2019s disease based on spectrograms of voice recordings and extreme learning machine random weight neural networks. Eng. Appl. Artif. Intell. 125 https:\/\/doi.org\/10.1016\/j.engappai.2023.106700 (2023).","DOI":"10.1016\/j.engappai.2023.106700"},{"key":"92105_CR20","doi-asserted-by":"publisher","unstructured":"Zhang, T., Zhang, Y., Cao, Y., Li & Hao, L. Diagnosing Parkinson\u2019s disease with speech signal based on convolutional neural network. Int. J. Comput. Appl. Technol. 63 https:\/\/doi.org\/10.1504\/ijcat.2020.110415 (2020).","DOI":"10.1504\/ijcat.2020.110415"},{"key":"92105_CR21","doi-asserted-by":"publisher","unstructured":"Malekroodi, H. S., Madusanka, N., Lee, B. I. & Yi, M. Leveraging deep learning for fine-grained categorization of Parkinson\u2019s disease progression levels through analysis of vocal acoustic patterns. Bioengineering (Basel) 11. https:\/\/doi.org\/10.3390\/bioengineering11030295 (2024).","DOI":"10.3390\/bioengineering11030295"},{"key":"92105_CR22","doi-asserted-by":"publisher","unstructured":"Jeong, S. M., Kim, S., Lee, E. C. & Kim, H. J. Exploring spectrogram-based audio classification for Parkinson\u2019s disease: A study on speech classification and qualitative reliability verification. Sensors (Basel) 24 https:\/\/doi.org\/10.3390\/s24144625 (2024).","DOI":"10.3390\/s24144625"},{"key":"92105_CR23","doi-asserted-by":"publisher","unstructured":"Farago, P. et al. CNN-based identification of Parkinson\u2019s disease from continuous speech in noisy environments. Bioengineering (Basel) 10 https:\/\/doi.org\/10.3390\/bioengineering10050531 (2023).","DOI":"10.3390\/bioengineering10050531"},{"key":"92105_CR24","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1016\/j.bbe.2022.04.002","volume":"42","author":"CQ Quan","year":"2022","unstructured":"Quan, C. Q., Ren, K., Luo, Z. W., Chen, Z. L. & Ling, Y. End-to-end deep learning approach for Parkinson\u2019s disease detection from speech signals. Biocybern Biomed. Eng. 42, 556\u2013574. https:\/\/doi.org\/10.1016\/j.bbe.2022.04.002 (2022).","journal-title":"Biocybern Biomed. Eng."},{"key":"92105_CR25","doi-asserted-by":"publisher","unstructured":"Er, M. B., Isik, E. & Isik, I. Parkinson\u2019s detection based on combined CNN and LSTM using enhanced speech signals with variational mode decomposition. Biomed. Signal. Proces 70 https:\/\/doi.org\/10.1016\/j.bspc.2021.103006 (2021).","DOI":"10.1016\/j.bspc.2021.103006"},{"key":"92105_CR26","unstructured":"Suhas, B. N. et al. International Conference on Signal Processing and Communications (SPCOM) 1\u20135. (2020)."},{"key":"92105_CR27","doi-asserted-by":"crossref","unstructured":"Rios-Urrego, C. D., V\u00e1squez-Correa, J. C., Orozco-Arroyave, J. R. & N\u00f6th, E. Text, Speech, and Dialogue Lecture Notes in Computer Science Ch. Chapter 36, 331\u2013339 (2020).","DOI":"10.1007\/978-3-030-58323-1_36"},{"key":"92105_CR28","doi-asserted-by":"publisher","first-page":"22719","DOI":"10.1038\/s41598-023-49869-6","volume":"13","author":"V Verma","year":"2023","unstructured":"Verma, V. et al. A novel hybrid model integrating MFCC and acoustic parameters for voice disorder detection. Sci. Rep. Uk 13, 22719 (2023).","journal-title":"Sci. Rep-Uk"},{"key":"92105_CR29","doi-asserted-by":"crossref","unstructured":"Rejaibi, E., Komaty, A., Meriaudeau, F., Agrebi, S. & Othmani, A. MFCC-based recurrent neural network for automatic clinical depression recognition and assessment from speech. Biomed. Signal. Proces 71 (2022).","DOI":"10.1016\/j.bspc.2021.103107"},{"key":"92105_CR30","doi-asserted-by":"crossref","unstructured":"Vashkevich, M. & Rushkevich, Y. Classification of ALS patients based on acoustic analysis of sustained vowel phonations. Biomed. Signal. Proces 65 (2021).","DOI":"10.1016\/j.bspc.2020.102350"},{"key":"92105_CR31","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1098\/rsif.2010.0456","volume":"8","author":"A Tsanas","year":"2011","unstructured":"Tsanas, A., Little, M. A., McSharry, P. E. & Ramig, L. O. Nonlinear speech analysis algorithms mapped to a standard metric achieve clinically useful quantification of average Parkinson\u2019s disease symptom severity. J. R. Soc. Interface 8, 842\u2013855 (2011).","journal-title":"J. R Soc. Interface"},{"key":"92105_CR32","doi-asserted-by":"crossref","unstructured":"Hawi, S. et al. Automatic Parkinson\u2019s disease detection based on the combination of long-term acoustic features and Mel frequency cepstral coefficients (MFCC). Biomed. Signal. Proces 78 (2022).","DOI":"10.1016\/j.bspc.2022.104013"},{"key":"92105_CR33","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.bspc.2018.07.019","volume":"46","author":"SS Upadhya","year":"2018","unstructured":"Upadhya, S. S., Cheeran, A. N. & Nirmal, J. H. Thomson multitaper MFCC and PLP voice features for early detection of Parkinson disease. Biomed. Signal. Proces 46, 293\u2013301 (2018).","journal-title":"Biomed. Signal. Proces"},{"key":"92105_CR34","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.bbe.2019.05.005","volume":"40","author":"B Karan","year":"2020","unstructured":"Karan, B., Sahu, S. S. & Mahto, K. Parkinson disease prediction using intrinsic mode function based features from speech signal. Biocybern Biomed. Eng. 40, 249\u2013264 (2020).","journal-title":"Biocybern Biomed. Eng."},{"key":"92105_CR35","doi-asserted-by":"crossref","unstructured":"Das, A. K. & Naskar, R. A deep learning model for depression detection based on MFCC and CNN generated spectrogram features. Biomed. Signal. Proces 90 (2024).","DOI":"10.1016\/j.bspc.2023.105898"},{"key":"92105_CR36","doi-asserted-by":"publisher","first-page":"17085","DOI":"10.1038\/s41598-021-96446-w","volume":"11","author":"G Gupta","year":"2021","unstructured":"Gupta, G., Kshirsagar, M., Zhong, M., Gholami, S. & Ferres, J. L. Comparing recurrent convolutional neural networks for large scale bird species classification. Sci. Rep. Uk 11, 17085 (2021).","journal-title":"Sci. Rep-Uk"},{"key":"92105_CR37","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1002\/ana.26085","volume":"90","author":"J Rusz","year":"2021","unstructured":"Rusz, J. et al. Speech biomarkers in rapid eye movement sleep behavior disorder and Parkinson disease. Ann. Neurol. 90, 62\u201375. https:\/\/doi.org\/10.1002\/ana.26085 (2021).","journal-title":"Ann. Neurol."},{"key":"92105_CR38","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1186\/s12938-021-00951-y","volume":"20","author":"J Carron","year":"2021","unstructured":"Carron, J., Campos-Roca, Y., Madruga, M. & Perez, C. J. A mobile-assisted voice condition analysis system for Parkinson\u2019s disease: assessment of usability conditions. Biomed. Eng. Online 20, 114. https:\/\/doi.org\/10.1186\/s12938-021-00951-y (2021).","journal-title":"Biomed. Eng. Online"},{"key":"92105_CR39","doi-asserted-by":"publisher","first-page":"1495","DOI":"10.1109\/TNSRE.2018.2851787","volume":"26","author":"J Rusz","year":"2018","unstructured":"Rusz, J. et al. Smartphone allows capture of speech abnormalities associated with high risk of developing Parkinson\u2019s disease. IEEE Trans. Neural Syst. Rehabil. Eng. 26, 1495\u20131507. https:\/\/doi.org\/10.1109\/TNSRE.2018.2851787 (2018).","journal-title":"IEEE Trans. Neural Syst. Rehabil Eng."},{"key":"92105_CR40","doi-asserted-by":"publisher","first-page":"20615","DOI":"10.1038\/s41598-023-47568-w","volume":"13","author":"A Iyer","year":"2023","unstructured":"Iyer, A. et al. A machine learning method to process voice samples for identification of Parkinson\u2019s disease. Sci. Rep. 13, 20615 (2023).","journal-title":"Sci. Rep."},{"key":"92105_CR41","doi-asserted-by":"publisher","first-page":"3391","DOI":"10.1007\/s00405-015-3708-4","volume":"272","author":"V Uloza","year":"2015","unstructured":"Uloza, V. et al. Exploring the feasibility of smart phone microphone for measurement of acoustic voice parameters and voice pathology screening. Eur. Arch. Otorhinolaryngol. 272, 3391\u20133399 (2015).","journal-title":"Eur. Arch. Otorhinolaryngol."},{"key":"92105_CR42","doi-asserted-by":"publisher","first-page":"9687","DOI":"10.1038\/s41598-022-13865-z","volume":"12","author":"ND Pah","year":"2022","unstructured":"Pah, N. D., Motin, M. A. & Kumar, D. K. Phonemes based detection of Parkinson\u2019s disease for telehealth applications. Sci. Rep. 12, 9687. https:\/\/doi.org\/10.1038\/s41598-022-13865-z (2022).","journal-title":"Sci. Rep."},{"key":"92105_CR43","doi-asserted-by":"publisher","first-page":"e133","DOI":"10.1017\/cts.2022.459","volume":"6","author":"T Virmani","year":"2022","unstructured":"Virmani, T. et al. Feasibility of telemedicine research visits in people with Parkinson\u2019s residing in medically underserved areas. J. Clin. Transl. Sci. 6, e133. https:\/\/doi.org\/10.1017\/cts.2022.459 (2022).","journal-title":"J. Clin. Transl Sci."},{"key":"92105_CR44","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1038\/ng.1089","volume":"44","author":"JM Derry","year":"2012","unstructured":"Derry, J. M. et al. Developing predictive molecular maps of human disease through community-based modeling. Nat. Genet. 44, 127\u2013130 (2012).","journal-title":"Nat. Genet."},{"key":"92105_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.wocn.2018.07.001","volume":"71","author":"Y Jadoul","year":"2018","unstructured":"Jadoul, Y., Thompson, B. & de Boer, B. Introducing parselmouth: A python interface to praat. J. Phonetics 71, 1\u201315 (2018).","journal-title":"J. Phonetics"},{"key":"92105_CR46","unstructured":"Rabiner, L. R. & Schafer, R. W. Digital Processing of Speech Signals (Prentice-Hall, 1978)."},{"key":"92105_CR47","doi-asserted-by":"publisher","unstructured":"Molnar, C. & iml An R package for interpretable machine learning. J. Open. Source Softw. 3 https:\/\/doi.org\/10.21105\/joss.00786 (2018).","DOI":"10.21105\/joss.00786"},{"key":"92105_CR48","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1007\/s10115-013-0679-x","volume":"41","author":"E \u0160trumbelj","year":"2013","unstructured":"\u0160trumbelj, E. & Kononenko, I. Explaining prediction models and individual predictions with feature contributions. Knowl. Inf. Syst. 41, 647\u2013665. https:\/\/doi.org\/10.1007\/s10115-013-0679-x (2013).","journal-title":"Knowl. Inf. Syst."},{"key":"92105_CR80","doi-asserted-by":"crossref","unstructured":"Schwab, P. & Karlen, W. Phonemd: Learning to diagnose parkinson\u2019s disease from smartphone data. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, 1118\u20131125 (2019).","DOI":"10.1609\/aaai.v33i01.33011118"},{"key":"92105_CR49","first-page":"235","volume":"21","author":"LK Bowen","year":"2013","unstructured":"Bowen, L. K., Hands, G. L., Pradhan, S. & Stepp, C. E. Effects of Parkinson\u2019s disease on fundamental frequency variability in running speech. J. Med. Speech Lang. Pathol. 21, 235\u2013244 (2013).","journal-title":"J. Med. Speech Lang. Pathol."},{"key":"92105_CR50","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1097\/MOO.0000000000000252","volume":"24","author":"P Gillivan-Murphy","year":"2016","unstructured":"Gillivan-Murphy, P., Carding, P. & Miller, N. Vocal tract characteristics in Parkinson\u2019s disease. Curr. Opin. Otolaryngol. Head Neck Surg. 24, 175\u2013182. https:\/\/doi.org\/10.1097\/MOO.0000000000000252 (2016).","journal-title":"Curr. Opin. Otolaryngol. Head Neck Surg."},{"key":"92105_CR51","unstructured":"Baken, R. J. & Orlikoff, R. F. Clinical Measurement of Speech and Voice second edn, (Singular Thomson Learning, 2000)."},{"key":"92105_CR52","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.neubiorev.2014.04.010","volume":"43","author":"S Vercruysse","year":"2014","unstructured":"Vercruysse, S. et al. Freezing beyond gait in Parkinson\u2019s disease: a review of current neurobehavioral evidence. Neurosci. Biobehav. Rev. 43, 213\u2013227. https:\/\/doi.org\/10.1016\/j.neubiorev.2014.04.010 (2014).","journal-title":"Neurosci. Biobehav Rev."},{"key":"92105_CR53","doi-asserted-by":"publisher","first-page":"1503","DOI":"10.1002\/mds.21549","volume":"22","author":"C Moreau","year":"2007","unstructured":"Moreau, C. et al. Oral festination in Parkinson\u2019s disease: Biomechanical analysis and correlation with festination and freezing of gait. Mov. Disord. 22, 1503\u20131506. https:\/\/doi.org\/10.1002\/mds.21549 (2007).","journal-title":"Mov. Disord"},{"key":"92105_CR54","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1159\/000266222","volume":"45","author":"H Ackermann","year":"1993","unstructured":"Ackermann, H., Grone, B. F., Hoch, G. & Schonle, P. W. Speech freezing in Parkinson\u2019s disease: a kinematic analysis of orofacial movements by means of electromagnetic articulography. Folia Phoniatr. (Basel) 45, 84\u201389. https:\/\/doi.org\/10.1159\/000266222 (1993).","journal-title":"Folia Phoniatr. (Basel)"},{"key":"92105_CR55","doi-asserted-by":"publisher","first-page":"11776","DOI":"10.1038\/s41598-020-68754-0","volume":"10","author":"S Yang","year":"2020","unstructured":"Yang, S. et al. The physical significance of acoustic parameters and its clinical significance of dysarthria in Parkinson\u2019s disease. Sci. Rep. 10, 11776. https:\/\/doi.org\/10.1038\/s41598-020-68754-0 (2020).","journal-title":"Sci. Rep."},{"key":"92105_CR56","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/s00702-012-0853-4","volume":"120","author":"J Rusz","year":"2013","unstructured":"Rusz, J. et al. Evaluation of speech impairment in early stages of Parkinson\u2019s disease: a prospective study with the role of pharmacotherapy. J. Neural Transm. (Vienna) 120, 319\u2013329. https:\/\/doi.org\/10.1007\/s00702-012-0853-4 (2013).","journal-title":"J. Neural Transm (Vienna)"},{"key":"92105_CR57","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1121\/1.3514381","volume":"129","author":"J Rusz","year":"2011","unstructured":"Rusz, J., Cmejla, R., Ruzickova, H. & Ruzicka, E. Quantitative acoustic measurements for characterization of speech and voice disorders in early untreated Parkinson\u2019s disease. J. Acoust. Soc. Am. 129, 350\u2013367. https:\/\/doi.org\/10.1121\/1.3514381 (2011).","journal-title":"J. Acoust. Soc. Am."},{"key":"92105_CR58","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/0021-9924(91)90004-3","volume":"24","author":"P Zwirner","year":"1991","unstructured":"Zwirner, P., Murry, T. & Woodson, G. E. Phonatory function of neurologically impaired patients. J. Commun. Disord. 24, 287\u2013300. https:\/\/doi.org\/10.1016\/0021-9924(91)90004-3 (1991).","journal-title":"J. Commun. Disord"},{"key":"92105_CR59","doi-asserted-by":"publisher","first-page":"e133","DOI":"10.1017\/cts.2022.459","volume":"6","author":"T Virmani","year":"2022","unstructured":"Virmani, T. et al. Feasibility of telemedicine research visits in people with Parkinson\u2019s disease residing in medically underserved areas. J. Clin. Transl. Sci. 6, e133. https:\/\/doi.org\/10.1017\/cts.2022.459 (2022).","journal-title":"J. Clin. Translational Sci."},{"key":"92105_CR60","unstructured":"R Core Team. R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing, Vienna, Austria. https:\/\/www.R-project.org (2021)."},{"key":"92105_CR61","unstructured":"Ooms, J. Working with Audio and Video in R. R package version 0.8.3. https:\/\/CRAN.R-project.org\/package=av (2023)."},{"key":"92105_CR62","unstructured":"Ligges, U., Krey, S., Mersmann, O., Schnackenberg, S. & tuneR analysis of music and speech. https:\/\/CRAN.R-project.org\/package=tuneR (2018)."},{"key":"92105_CR63","unstructured":"Boersma, P. & Weenink, D. Praat: doing phonetics by computer [Computer program]. https:\/\/www.fon.hum.uva.nl\/praat\/v (2022)."},{"key":"92105_CR64","doi-asserted-by":"crossref","unstructured":"Van Boxtel, G. et al. gsignal: Signal processing. https:\/\/github.com\/gjmvanboxtel\/gsignal (2021).","DOI":"10.32614\/CRAN.package.gsignal"},{"key":"92105_CR65","unstructured":"Rabiner, L. R. & Juang, B. H. Fundamentals of Speech Recognition (Prentice Hall, 1993)."},{"key":"92105_CR66","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v028.i05","volume":"28","author":"M Kuhn","year":"2008","unstructured":"Kuhn, M. Building predictive models in R using the caret package. J. Stat. Softw. 28, 1\u201326 (2008).","journal-title":"J. Stat. Softw."},{"key":"92105_CR67","doi-asserted-by":"crossref","unstructured":"Venables, W. N. & Ripley, B. D. Modern Applied Statistics With S. Fourth ed. (Springer, 2002).","DOI":"10.1007\/978-0-387-21706-2"},{"key":"92105_CR68","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. Random forests. Mach. Learn. 45, 5\u201332 (2001).","journal-title":"Mach. Learn."},{"key":"92105_CR69","first-page":"18","volume":"2","author":"A Liaw","year":"2002","unstructured":"Liaw, A. & Wiener, M. Classification and regression by randomforest. R News 2, 18\u201322 (2002).","journal-title":"R News"},{"key":"92105_CR70","doi-asserted-by":"publisher","first-page":"3594","DOI":"10.21105\/joss.03594","volume":"7","author":"DE Kelley","year":"2022","unstructured":"Kelley, D. E., Richards, C. & Layton, C. Oce: an R package for oceanographic analysis. J. Open. Source Softw. 7, 3594 (2022).","journal-title":"J. Open. Source Softw."},{"key":"92105_CR71","unstructured":"Keydana, S., Damiani, A., Falbel, D. & torchaudio R Interface to pytorch\u2019s torchaudio. R package version 0.3.1. https:\/\/CRAN.R-project.org\/package=torchaudio (2023)."},{"key":"92105_CR72","doi-asserted-by":"publisher","first-page":"103362","DOI":"10.1016\/j.jbi.2019.103362","volume":"104","author":"JM Tracy","year":"2020","unstructured":"Tracy, J. M., Ozkanca, Y. & Atkins, D. C. Hosseini Ghomi, R. Investigating voice as a biomarker: deep phenotyping methods for early detection of Parkinson\u2019s disease. J. Biomed. Inf. 104, 103362. https:\/\/doi.org\/10.1016\/j.jbi.2019.103362 (2020).","journal-title":"J. Biomed. Inf."},{"key":"92105_CR73","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. & Wojna, Z. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2818\u20132826 (2016).","DOI":"10.1109\/CVPR.2016.308"},{"key":"92105_CR74","doi-asserted-by":"publisher","first-page":"5930","DOI":"10.3390\/su15075930","volume":"15","author":"AW Salehi","year":"2023","unstructured":"Salehi, A. W. et al. A study of CNN and transfer learning in medical imaging: advantages, challenges, future scope. Sustainability 15, 5930 (2023).","journal-title":"Sustainability"},{"key":"92105_CR75","doi-asserted-by":"publisher","first-page":"146533","DOI":"10.1109\/ACCESS.2019.2946000","volume":"7","author":"C Wang","year":"2019","unstructured":"Wang, C. et al. Pulmonary image classification based on inception-v3 transfer learning model. IEEE Access 7, 146533\u2013146541 (2019).","journal-title":"IEEE Access."},{"key":"92105_CR76","unstructured":"Ioffe, S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on International Conference on Machine Learning. 37 448\u2013456 (2015)."},{"key":"92105_CR77","doi-asserted-by":"publisher","unstructured":"Kim, T. Generalizing MLPs with dropouts, batch normalization, and skip connections. arXiv https:\/\/doi.org\/10.48550\/arXiv.2108.08186 (2021).","DOI":"10.48550\/arXiv.2108.08186"},{"key":"92105_CR78","doi-asserted-by":"publisher","first-page":"3735","DOI":"10.1016\/j.csda.2009.04.009","volume":"53","author":"JH Kim","year":"2009","unstructured":"Kim, J. H. Estimating classification error rate: repeated cross-validation, repeated hold-out and bootstrap. Comput. Stat. Data Anal. 53, 3735\u20133745. https:\/\/doi.org\/10.1016\/j.csda.2009.04.009 (2009).","journal-title":"Comput. Stat. Data Anal."},{"key":"92105_CR79","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1186\/s13550-022-00931-w","volume":"12","author":"JJ Eertink","year":"2022","unstructured":"Eertink, J. J. et al. External validation: a simulation study to compare cross-validation versus holdout or external testing to assess the performance of clinical prediction models using PET data from DLBCL patients. EJNMMI Res. 12, 58. https:\/\/doi.org\/10.1186\/s13550-022-00931-w (2022).","journal-title":"EJNMMI Res."}],"updated-by":[{"DOI":"10.1038\/s41598-026-75398-z","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T00:00:00Z","timestamp":1793923200000}}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-92105-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-92105-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-92105-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T12:16:28Z","timestamp":1793967388000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-92105-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,1]]},"references-count":80,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["92105"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-92105-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-5348708\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,1]]},"assertion":[{"value":"28 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2026","order":5,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":6,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1038\/s41598-026-75398-z","URL":"https:\/\/doi.org\/10.1038\/s41598-026-75398-z","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"7337"}}