{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T10:07:38Z","timestamp":1779185258007,"version":"3.51.4"},"reference-count":77,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100006359","name":"Blekinge Institute of Technology","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006359","id-type":"DOI","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>Parkinson\u2019s disease (PD) and chronic obstructive pulmonary disease (COPD) are prevalent conditions with substantial impact on quality of life and health care systems. Both disorders affect voice production through different physiological mechanisms, yet neither condition has a widely adopted objective biomarker for routine clinical use. Voice analysis has emerged as a non-invasive digital biomarker candidate, but existing studies have largely focused on binary classification within a single disorder or language. This study aimed to evaluate whether an unified multiclass machine learning (ML) framework applied to sustained vowel \u201ca\u201d phonation can discriminate between PD, COPD, and healthy controls (HC) across linguistically distinct cohorts. Sustained vowel recordings were analyzed from Swedish speaking individuals with COPD and HC, and English-speaking individuals with PD and HC, collected under comparable mobile recording conditions. Acoustic features included baseline voice measures and Mel Frequency Cepstral Coefficients. A soft voting ML framework integrating support vector machine, random forest, CatBoost, and light gradient boosting classifiers was trained using nested cross validation with hyperparameter optimization. Data were partitioned at the participant level into a development cohort and an independent test cohort. Model performance was evaluated using accuracy, macro averaged precision, recall, F1 score, receiver operating characteristic analysis, and confusion matrices. Model interpretability was assessed using Shapley additive explanations and vowel space analysis. The final soft voting classifier achieved robust multiclass discrimination on the participant disjoint independent test set, with an overall accuracy of 0.842 and a macro averaged F1 score of 0.839. Classification performance differed across groups, with the highest performance observed for PD, intermediate performance for HC, and lower performance for COPD. Misclassifications occurred primarily between HC and COPD, while confusion between PD and COPD was minimal. Feature attribution analysis revealed class dependent relevance patterns, and vowel space analysis demonstrated subtle but consistent group level differences. These findings demonstrate the feasibility of using an explainable soft voting machine learning framework applied to sustained vowel phonation to distinguish between neurologically and respiratory driven voice impairments across linguistic contexts. The study supports voice as a promising digital biomarker modality for multiclass clinical discrimination using mobile recordings.<\/jats:p>","DOI":"10.1038\/s41598-026-53409-3","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T09:05:03Z","timestamp":1779181503000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Use of machine learning and voice for multiclass classification of Parkinson\u2019s disease, chronic obstructive pulmonary disease, and healthy controls"],"prefix":"10.1038","volume":"16","author":[{"given":"Alper","family":"Idrisoglu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anders","family":"Behrens","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,19]]},"reference":[{"key":"53409_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rmed.2023.107452","volume":"220","author":"J Anandan","year":"2023","unstructured":"Anandan, J., Dwivedi, D. P. & Govindaraj, V. Clinical phenotypes of COPD and their impact on quality of life: A cross-sectional study. Respir. Med. 220, 107452. https:\/\/doi.org\/10.1016\/j.rmed.2023.107452 (2023).","journal-title":"Respir. Med."},{"key":"53409_CR2","doi-asserted-by":"publisher","DOI":"10.1186\/s12883-024-03769-y","volume":"24","author":"I Cassidy","year":"2024","unstructured":"Cassidy, I., Doody, O., Richardson, M. & Meskell, P. Quality of life and living with Parkinson\u2019s disease: A qualitative exploration within an Irish context. BMC Neurol. 24, 275. https:\/\/doi.org\/10.1186\/s12883-024-03769-y (2024).","journal-title":"BMC Neurol."},{"key":"53409_CR3","doi-asserted-by":"publisher","first-page":"2284","DOI":"10.1016\/S0140-6736(21)00218-X","volume":"397","author":"BR Bloem","year":"2021","unstructured":"Bloem, B. R., Okun, M. S. & Klein, C. Parkinson\u2019s disease. Lancet 397, 2284\u20132303. https:\/\/doi.org\/10.1016\/S0140-6736(21)00218-X (2021).","journal-title":"Lancet"},{"key":"53409_CR4","doi-asserted-by":"publisher","first-page":"216","DOI":"10.2471\/BLT.21.286870","volume":"100","author":"P Jarhyan","year":"2022","unstructured":"Jarhyan, P., Hutchinson, A., Khaw, D., Prabhakaran, D. & Mohan, S. Prevalence of chronic obstructive pulmonary disease and chronic bronchitis in eight countries: A systematic review and meta-analysis. Bull. World Health Organ. 100, 216\u2013230. https:\/\/doi.org\/10.2471\/BLT.21.286870 (2022).","journal-title":"Bull. World Health Organ."},{"key":"53409_CR5","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.41149","author":"J Mishra","year":"2023","unstructured":"Mishra, J. et al. Occupational risks and chronic obstructive pulmonary disease in the indian subcontinent: A critical review. Cureus https:\/\/doi.org\/10.7759\/cureus.41149 (2023).","journal-title":"Cureus"},{"key":"53409_CR6","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s12916-020-01873-7","volume":"19","author":"A-F-A Mentis","year":"2021","unstructured":"Mentis, A.-F.-A., Dardiotis, E., Efthymiou, V. & Chrousos, G. P. Non-genetic risk and protective factors and biomarkers for neurological disorders: A meta-umbrella systematic review of umbrella reviews. BMC Med. 19, 6. https:\/\/doi.org\/10.1186\/s12916-020-01873-7 (2021).","journal-title":"BMC Med."},{"key":"53409_CR7","doi-asserted-by":"publisher","DOI":"10.1038\/s41531-024-00817-9","volume":"10","author":"A Favaro","year":"2024","unstructured":"Favaro, A. et al. Unveiling early signs of Parkinson\u2019s disease via a longitudinal analysis of celebrity speech recordings. Npj Park. Dis. 10, 207. https:\/\/doi.org\/10.1038\/s41531-024-00817-9 (2024).","journal-title":"Npj Park. Dis."},{"key":"53409_CR8","doi-asserted-by":"publisher","unstructured":"Triantafyllopoulos, A. et al. Sustained Vowels for Pre- vs Post-Treatment COPD Classification, 1410\u20131414. https:\/\/doi.org\/10.21437\/Interspeech.2024-96 (2024).","DOI":"10.21437\/Interspeech.2024-96"},{"key":"53409_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jocn.2019.12.029","volume":"72","author":"A Ma","year":"2020","unstructured":"Ma, A., Lau, K. K. & Thyagarajan, D. Voice changes in Parkinson\u2019s disease: What are they telling us? J. Clin. Neurosci. 72, 1\u20137. https:\/\/doi.org\/10.1016\/j.jocn.2019.12.029 (2020).","journal-title":"J. Clin. Neurosci."},{"key":"53409_CR10","doi-asserted-by":"publisher","DOI":"10.1080\/136828200410654","author":"J Holmes","year":"2000","unstructured":"Holmes, J. Voice characteristics in the progression of Parkinson\u2019s disease. International Journal of Language & Communication Disorders https:\/\/doi.org\/10.1080\/136828200410654 (2000).","journal-title":"International Journal of Language & Communication Disorders"},{"key":"53409_CR11","doi-asserted-by":"publisher","first-page":"32","DOI":"10.5005\/jp-journals-10001-1521","volume":"13","author":"TV Wang","year":"2022","unstructured":"Wang, T. V. & Song, P. C. Neurological voice disorders: A review. Int. J. Head Neck Surg. 13, 32\u201340. https:\/\/doi.org\/10.5005\/jp-journals-10001-1521 (2022).","journal-title":"Int. J. Head Neck Surg."},{"key":"53409_CR12","doi-asserted-by":"publisher","first-page":"45","DOI":"10.5005\/jp-journals-10023-1081","volume":"4","author":"A Shastry","year":"2014","unstructured":"Shastry, A., Balasubramanium, R. K. & Acharya, P. R. Voice analysis in individuals with chronic obstructive pulmonary disease. Int. J. Phonosurg. Laryngol. 4, 45\u201349. https:\/\/doi.org\/10.5005\/jp-journals-10023-1081 (2014).","journal-title":"Int. J. Phonosurg. Laryngol."},{"key":"53409_CR13","doi-asserted-by":"publisher","first-page":"20","DOI":"10.4103\/ejb.ejb_34_17","volume":"12","author":"AM Saeed","year":"2018","unstructured":"Saeed, A. M., Riad, N. M., Osman, N. M., Khattab, A. N. & Mohammed, S. E. Study of voice disorders in patients with bronchial asthma and chronic obstructive pulmonary disease. Egypt. J. Bronchol. 12, 20\u201326. https:\/\/doi.org\/10.4103\/ejb.ejb_34_17 (2018).","journal-title":"Egypt. J. Bronchol."},{"key":"53409_CR14","doi-asserted-by":"publisher","first-page":"1070","DOI":"10.1016\/j.jvoice.2022.02.009","volume":"38","author":"CL Payten","year":"2024","unstructured":"Payten, C. L., Chiapello, G., Weir, K. A. & Madill, C. J. Frameworks, terminology and definitions used for the classification of voice disorders: A scoping review. J. Voice 38, 1070\u20131087. https:\/\/doi.org\/10.1016\/j.jvoice.2022.02.009 (2024).","journal-title":"J. Voice"},{"key":"53409_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-022-01123-y","volume":"3","author":"A Tsanas","year":"2022","unstructured":"Tsanas, A. & Arora, S. Data-driven subtyping of Parkinson\u2019s using acoustic analysis of sustained vowels and cluster analysis: Findings in the Parkinson\u2019s Voice Initiative Study. SN Comput. Sci. 3, 232. https:\/\/doi.org\/10.1007\/s42979-022-01123-y (2022).","journal-title":"SN Comput. Sci."},{"key":"53409_CR16","doi-asserted-by":"crossref","unstructured":"Tsanas, A. & Arora, S. Large-scale Clustering of People Diagnosed with Parkinson\u2019s Disease using Acoustic Analysis of Sustained Vowels: Findings in the Parkinson\u2019s Voice Initiative Study. BIOSIGNALS, 369\u2013376, Available: https:\/\/www.scitepress.org\/PublishedPapers\/2020\/93612\/93612.pdf (2020).","DOI":"10.5220\/0009361200002513"},{"key":"53409_CR17","first-page":"135","volume":"9","author":"C Ittichaichareon","year":"2012","unstructured":"Ittichaichareon, C., Suksri, S. & Yingthawornsuk, T. Speech recognition using MFCC. Simul. Model. 9, 135\u2013138 (2012).","journal-title":"Simul. Model."},{"key":"53409_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108917","volume":"179","author":"N Kalra","year":"2024","unstructured":"Kalra, N., Verma, P. & Verma, S. Advancements in AI based healthcare techniques with focus on diagnostic techniques. Comput. Biol. Med. 179, 108917. https:\/\/doi.org\/10.1016\/j.compbiomed.2024.108917 (2024).","journal-title":"Comput. Biol. Med."},{"key":"53409_CR19","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-023-05465-z","volume":"24","author":"K Abnoosian","year":"2023","unstructured":"Abnoosian, K., Farnoosh, R. & Behzadi, M. H. Prediction of diabetes disease using an ensemble of machine learning multi-classifier models. BMC Bioinformatics 24, 337. https:\/\/doi.org\/10.1186\/s12859-023-05465-z (2023).","journal-title":"BMC Bioinformatics"},{"key":"53409_CR20","doi-asserted-by":"publisher","first-page":"120","DOI":"10.56705\/ijodas.v4i2.78","volume":"4","author":"N Rismayanti","year":"2023","unstructured":"Rismayanti, N. & Utami, A. P. Improving multi-class classification on 5-celebrity-faces dataset using ensemble classification methods. Indones. J. Data Sci. 4, 120\u2013129. https:\/\/doi.org\/10.56705\/ijodas.v4i2.78 (2023).","journal-title":"Indones. J. Data Sci."},{"key":"53409_CR21","doi-asserted-by":"publisher","DOI":"10.2196\/46105","volume":"25","author":"A Idrisoglu","year":"2023","unstructured":"Idrisoglu, A., Dallora, A. L., Anderberg, P. & Berglund, J. S. Applied machine learning techniques to diagnose voice-affecting conditions and disorders: Systematic literature review. J. Med. Internet Res. 25, e46105. https:\/\/doi.org\/10.2196\/46105 (2023).","journal-title":"J. Med. Internet Res."},{"key":"53409_CR22","doi-asserted-by":"publisher","unstructured":"Abdullah, A. A., Norazman, N. N., Ahmad, W. K. W., Awang, S. A. & Jian, F. W. Detection of Parkinson\u2019s Disease (PD) Based on Speech Recordings using Machine Learning Techniques, https:\/\/doi.org\/10.1109\/3ICT51146.2020.9311991 (2020).","DOI":"10.1109\/3ICT51146.2020.9311991"},{"key":"53409_CR23","doi-asserted-by":"publisher","DOI":"10.2196\/38472","volume":"24","author":"G Al-Hussain","year":"2022","unstructured":"Al-Hussain, G., Shuweihdi, F., Alali, H., Househ, M. & Abd-Alrazaq, A. The effectiveness of supervised machine learning in screening and diagnosing voice disorders: Systematic review and meta-analysis. J. Med. Internet Res. 24, e38472. https:\/\/doi.org\/10.2196\/38472 (2022).","journal-title":"J. Med. Internet Res."},{"key":"53409_CR24","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1007\/s10772-023-10070-9","volume":"26","author":"C Bang","year":"2023","unstructured":"Bang, C., Bogdanovic, N., Deutsch, G. & Marques, O. Machine learning for the diagnosis of Parkinson\u2019s disease using speech analysis: A systematic review. Int. J. Speech Technol. 26, 991\u2013998. https:\/\/doi.org\/10.1007\/s10772-023-10070-9 (2023).","journal-title":"Int. J. Speech Technol."},{"key":"53409_CR25","doi-asserted-by":"publisher","first-page":"2871","DOI":"10.7150\/ijms.58191","volume":"18","author":"Y Feng","year":"2021","unstructured":"Feng, Y., Wang, Y., Zeng, C. & Mao, H. Artificial intelligence and machine learning in chronic airway diseases: Focus on asthma and chronic obstructive pulmonary disease. Int. J. Med. Sci. 18, 2871\u20132889. https:\/\/doi.org\/10.7150\/ijms.58191 (2021).","journal-title":"Int. J. Med. Sci."},{"key":"53409_CR26","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-95320-3","volume":"15","author":"A Idrisoglu","year":"2025","unstructured":"Idrisoglu, A. et al. Vowel segmentation impact on machine learning classification for chronic obstructive pulmonary disease. Sci. Rep. 15, 9930. https:\/\/doi.org\/10.1038\/s41598-025-95320-3 (2025).","journal-title":"Sci. Rep."},{"key":"53409_CR27","doi-asserted-by":"publisher","unstructured":"Verdolini, K., Rosen, C. A. & Branski, R. C. (eds) Classification Manual for Voice Disorders-I https:\/\/doi.org\/10.4324\/9781410617293 (Psychology, 2014).","DOI":"10.4324\/9781410617293"},{"key":"53409_CR28","doi-asserted-by":"publisher","DOI":"10.3390\/s24041173","volume":"24","author":"P Kapetanidis","year":"2024","unstructured":"Kapetanidis, P. et al. Respiratory diseases diagnosis using audio analysis and artificial intelligence: A systematic review. Sensors 24, 1173. https:\/\/doi.org\/10.3390\/s24041173 (2024).","journal-title":"Sensors"},{"key":"53409_CR29","doi-asserted-by":"publisher","first-page":"549","DOI":"10.3390\/biomedinformatics4010031","volume":"4","author":"MG Di Cesare","year":"2024","unstructured":"Di Cesare, M. G., Perpetuini, D., Cardone, D. & Merla, A. Assessment of voice disorders using machine learning and vocal analysis of voice samples recorded through smartphones. BioMedInformatics 4, 549\u2013565. https:\/\/doi.org\/10.3390\/biomedinformatics4010031 (2024).","journal-title":"BioMedInformatics"},{"key":"53409_CR30","doi-asserted-by":"publisher","first-page":"1820","DOI":"10.1109\/JBHI.2015.2467375","volume":"19","author":"JR Orozco-Arroyave","year":"2015","unstructured":"Orozco-Arroyave, J. R. et al. Characterization methods for the detection of multiple voice disorders: Neurological, functional, and laryngeal diseases. IEEE J. Biomed. Health Inform. 19, 1820\u20131828. https:\/\/doi.org\/10.1109\/JBHI.2015.2467375 (2015).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"53409_CR31","doi-asserted-by":"publisher","unstructured":"Mojaly, M. A., Muhammad, G. & Alsulaiman, M. Detection and classification of voice pathology using feature selection. 2014 IEEE\/ACS 11th International Conference on Computer Systems and Applications (AICCSA), 571\u2013577. https:\/\/doi.org\/10.1109\/AICCSA.2014.7073250 (2014).","DOI":"10.1109\/AICCSA.2014.7073250"},{"key":"53409_CR32","doi-asserted-by":"publisher","unstructured":"Hosseini, P. T., Almasganj, F. & Darabad, M. R. Pathological voice classifcation using local discriminant basis and genetic algorithm. 16th Mediterranean Conference on Control and Automation. 2008, 872\u2013876. https:\/\/doi.org\/10.1109\/MED.2008.4602260 (2008).","DOI":"10.1109\/MED.2008.4602260"},{"key":"53409_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2019.101615","volume":"55","author":"ES Fonseca","year":"2020","unstructured":"Fonseca, E. S. et al. Acoustic investigation of speech pathologies based on the discriminative paraconsistent machine (DPM). Biomed. Signal Process. Control 55, 101615. https:\/\/doi.org\/10.1016\/j.bspc.2019.101615 (2020).","journal-title":"Biomed. Signal Process. Control"},{"key":"53409_CR34","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2022.842301","author":"P Hecker","year":"2022","unstructured":"Hecker, P., Steckhan, N., Eyben, F., Schuller, B. W. & Arnrich, B. Voice analysis for neurological disorder recognition\u2013A systematic review and perspective on emerging trends. Front Digit Health https:\/\/doi.org\/10.3389\/fdgth.2022.842301 (2022).","journal-title":"Front Digit Health"},{"key":"53409_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2025.10.013","author":"A Idrisoglu","year":"2025","unstructured":"Idrisoglu, A. et al. Feature Analysis of the Vowel [a:] in Individuals With Chronic Obstructive Pulmonary Disease and Healthy Controls. J. Voice. https:\/\/doi.org\/10.1016\/j.jvoice.2025.10.013 (2025). cited 29 Oct 2025.","journal-title":"J. Voice"},{"key":"53409_CR36","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/S1353-8020(97)00007-2","volume":"3","author":"FJ Jim\u00e9nez-Jim\u00e9nez","year":"1997","unstructured":"Jim\u00e9nez-Jim\u00e9nez, F. J. et al. Acoustic voice analysis in untreated patients with Parkinson\u2019s disease. Parkinsonism Relat. Disord. 3, 111\u2013116. https:\/\/doi.org\/10.1016\/S1353-8020(97)00007-2 (1997).","journal-title":"Parkinsonism Relat. Disord."},{"key":"53409_CR37","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-64004-9","volume":"14","author":"S Srinivasan","year":"2024","unstructured":"Srinivasan, S. et al. Detection of Parkinson disease using multiclass machine learning approach. Sci. Rep. 14, 13813. https:\/\/doi.org\/10.1038\/s41598-024-64004-9 (2024).","journal-title":"Sci. Rep."},{"key":"53409_CR38","doi-asserted-by":"crossref","unstructured":"Kovac, D. et al. Exploring language-independent digital speech biomarkers of hypokinetic dysarthria. medRxiv ; 2022\u20132010. (2022).","DOI":"10.1101\/2022.10.24.22281459"},{"key":"53409_CR39","doi-asserted-by":"publisher","first-page":"1394","DOI":"10.1007\/s00415-019-09271-7","volume":"266","author":"J Rusz","year":"2019","unstructured":"Rusz, J. et al. Distinctive speech signature in cerebellar and parkinsonian subtypes of multiple system atrophy. J. Neurol. 266, 1394\u20131404. https:\/\/doi.org\/10.1007\/s00415-019-09271-7 (2019).","journal-title":"J. Neurol."},{"key":"53409_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102953","volume":"156","author":"A Idrisoglu","year":"2024","unstructured":"Idrisoglu, A. et al. COPDVD: Automated classification of chronic obstructive pulmonary disease on a new collected and evaluated voice dataset. Artif. Intell. Med. 156, 102953. https:\/\/doi.org\/10.1016\/j.artmed.2024.102953 (2024).","journal-title":"Artif. Intell. Med."},{"key":"53409_CR41","doi-asserted-by":"publisher","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":"53409_CR42","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2245","volume":"10","author":"M Sivakumar","year":"2024","unstructured":"Sivakumar, M., Parthasarathy, S. & Padmapriya, T. Trade-off between training and testing ratio in machine learning for medical image processing. PeerJ Comput. Sci. 10, e2245. https:\/\/doi.org\/10.7717\/peerj-cs.2245 (2024).","journal-title":"PeerJ Comput. Sci."},{"key":"53409_CR43","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1002\/sam.11583","volume":"15","author":"VR Joseph","year":"2022","unstructured":"Joseph, V. R. Optimal ratio for data splitting. Statistical Analysis and Data Mining: The ASA Data Science Journal 15, 531\u2013538. https:\/\/doi.org\/10.1002\/sam.11583 (2022).","journal-title":"Statistical Analysis and Data Mining: The ASA Data Science Journal"},{"key":"53409_CR44","unstructured":"Machine Learning-Based Classification of Parkinson\u2019s Disease Patients Using Speech Biomarkers - Mohammad Amran Hossain & Amenta, F., https:\/\/journals.sagepub.com\/doi\/10.3233\/JPD-230002 (2024).\u00a0"},{"key":"53409_CR45","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-7-91","volume":"7","author":"S Varma","year":"2006","unstructured":"Varma, S. & Simon, R. Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics 7, 91. https:\/\/doi.org\/10.1186\/1471-2105-7-91 (2006).","journal-title":"BMC Bioinformatics"},{"key":"53409_CR46","first-page":"2079","volume":"11","author":"GC Cawley","year":"2010","unstructured":"Cawley, G. C. & Talbot, N. L. On over-fitting in model selection and subsequent selection bias in performance evaluation. J. Mach. Learn. Res. 11, 2079\u20132107 (2010).","journal-title":"J. Mach. Learn. Res."},{"key":"53409_CR47","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C. & Vapnik, V. Support-vector networks. Mach. Learn. 20, 273\u2013297. https:\/\/doi.org\/10.1007\/BF00994018 (1995).","journal-title":"Mach. Learn."},{"key":"53409_CR48","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. https:\/\/doi.org\/10.1023\/A:1010933404324 (2001).","journal-title":"Mach. Learn."},{"key":"53409_CR49","unstructured":"Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V. & Gulin, A. CatBoost: unbiased boosting with categorical features. Adv Neural Inf Process Syst, Available: https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/14491b756b3a51daac41c24863285549-Abstract.html (2018)."},{"key":"53409_CR50","doi-asserted-by":"publisher","DOI":"10.2196\/75069","volume":"13","author":"A Idrisoglu","year":"2025","unstructured":"Idrisoglu, A. et al. Prediction of Mini-Mental State Examination scores for cognitive impairment and machine learning analysis of oral health and demographic data among individuals older than 60 years: Cross-sectional study. JMIR Med. Inform. 13, e75069. https:\/\/doi.org\/10.2196\/75069 (2025).","journal-title":"JMIR Med. Inform."},{"key":"53409_CR51","doi-asserted-by":"publisher","unstructured":"Flyborg, J., Idrisoglu, A., Anderberg, P., Renvert, S. & Berglund, J. S. Oral Health Parameter-Based Mini-Mental State Examination Indication Using Machine Learning. 12th International Conference on Bioinformatics and Computational Biology (ICBCB), 113\u2013118, https:\/\/doi.org\/10.1109\/ICBCB61507.2024.11011974 (2024).","DOI":"10.1109\/ICBCB61507.2024.11011974"},{"key":"53409_CR52","unstructured":"Ke, G. et al. Lightgbm: A highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst. ;30. (2017). Available: https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/6449f44a102fde848669bdd9eb6b76fa-Abstract.html"},{"key":"53409_CR53","doi-asserted-by":"crossref","unstructured":"Kuncheva LI. Combining pattern classifiers: methods and algorithms. John Wiley & Sons; Available: https:\/\/onlinelibrary.wiley.com\/doi\/book\/10.1002\/9781118914564 (2014).","DOI":"10.1002\/9781118914564"},{"key":"53409_CR54","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","volume":"45","author":"M Sokolova","year":"2009","unstructured":"Sokolova, M. & Lapalme, G. A systematic analysis of performance measures for classification tasks. Inf. Process. Manag. 45, 427\u2013437. https:\/\/doi.org\/10.1016\/j.ipm.2009.03.002 (2009).","journal-title":"Inf. Process. Manag."},{"key":"53409_CR55","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/S0034-4257(97)00083-7","volume":"62","author":"SV Stehman","year":"1997","unstructured":"Stehman, S. V. Selecting and interpreting measures of thematic classification accuracy. Remote Sens. Environ. 62, 77\u201389. https:\/\/doi.org\/10.1016\/S0034-4257(97)00083-7 (1997).","journal-title":"Remote Sens. Environ."},{"key":"53409_CR56","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1023\/A:1010920819831","volume":"45","author":"DJ Hand","year":"2001","unstructured":"Hand, D. J. & Till, R. J. A simple generalisation of the area under the ROC curve for multiple class classification problems. Mach. Learn. 45, 171\u2013186. https:\/\/doi.org\/10.1023\/A:1010920819831 (2001).","journal-title":"Mach. Learn."},{"key":"53409_CR57","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432","volume":"10","author":"T Saito","year":"2015","unstructured":"Saito, T. & Rehmsmeier, M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS One 10, e0118432. https:\/\/doi.org\/10.1371\/journal.pone.0118432 (2015).","journal-title":"PLoS One"},{"key":"53409_CR58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/3-540-45014-9_1","volume-title":"Ensemble Methods in Machine Learning. Multiple Classifier Systems","author":"TG Dietterich","year":"2000","unstructured":"Dietterich, T. G. Ensemble Methods in Machine Learning. Multiple Classifier Systems 1\u201315 (Springer, 2000). https:\/\/doi.org\/10.1007\/3-540-45014-9_1."},{"key":"53409_CR59","unstructured":"Lundberg, S. M., Lee, S-I-A. & Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems. Curran Associates, Available: https:\/\/papers.nips.cc\/paper\/2017\/hash\/8a20a8621978632d76c43dfd28b67767-Abstract.html (2017)."},{"key":"53409_CR60","unstructured":"Welcome to the SHAP documentation \u2014 SHAP latest documentation. [cited 7 Jan 2026]. Available: https:\/\/shap.readthedocs.io\/en\/latest\/ (2026)."},{"key":"53409_CR61","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1002\/9781444301007.ch22","volume-title":"The Handbook of Clinical Linguistics","author":"RD Kent","year":"2008","unstructured":"Kent, R. D. & Kim, Y. Acoustic Analysis of Speech. In The Handbook of Clinical Linguistics 360\u2013380 (2008). https:\/\/doi.org\/10.1002\/9781444301007.ch22."},{"key":"53409_CR62","doi-asserted-by":"publisher","DOI":"10.1038\/s41531-022-00389-6","volume":"8","author":"K Daoudi","year":"2022","unstructured":"Daoudi, K., Das, B., Tykalova, T., Klempir, J. & Rusz, J. Speech acoustic indices for differential diagnosis between Parkinson\u2019s disease, multiple system atrophy and progressive supranuclear palsy. Npj. Park. Dis. 8, 142. https:\/\/doi.org\/10.1038\/s41531-022-00389-6 (2022).","journal-title":"Npj. Park. Dis."},{"key":"53409_CR63","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00959-9","volume":"6","author":"M Bowden","year":"2023","unstructured":"Bowden, M. et al. A systematic review and narrative analysis of digital speech biomarkers in Motor Neuron Disease. Npj. Digit. Med. 6, 228. https:\/\/doi.org\/10.1038\/s41746-023-00959-9 (2023).","journal-title":"Npj. Digit. Med."},{"key":"53409_CR64","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1038\/s41531-025-00913-4","volume":"11","author":"F Cao","year":"2025","unstructured":"Cao, F., Vogel, A. P., Gharahkhani, P. & Renteria, M. E. Speech and language biomarkers for Parkinson\u2019s disease prediction, early diagnosis and progression. Npj. Park. Dis. 11, 57. https:\/\/doi.org\/10.1038\/s41531-025-00913-4 (2025).","journal-title":"Npj. Park. Dis."},{"key":"53409_CR65","doi-asserted-by":"publisher","unstructured":"Lee, S. M. et al. Voice as a Digital Biomarker: Foundation Model-Based COPD Assessment. Research Square;, https:\/\/doi.org\/10.21203\/rs.3.rs-8302274\/v1 (2025).","DOI":"10.21203\/rs.3.rs-8302274\/v1"},{"key":"53409_CR66","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-024-03605-7","volume":"22","author":"X Chen","year":"2024","unstructured":"Chen, X. et al. Efficacy of respiratory support therapies during pulmonary rehabilitation exercise training in chronic obstructive pulmonary disease patients: A systematic review and network meta-analysis. BMC. Med. 22, 389. https:\/\/doi.org\/10.1186\/s12916-024-03605-7 (2024).","journal-title":"BMC. Med."},{"key":"53409_CR67","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering12111279","author":"HS Malekroodi","year":"2025","unstructured":"Malekroodi, H. S. et al. Voice-based detection of Parkinson\u2019s disease using machine and deep learning approaches: A systematic review. Bioengineering https:\/\/doi.org\/10.3390\/bioengineering12111279 (2025).","journal-title":"Bioengineering"},{"key":"53409_CR68","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-49596-y","volume":"13","author":"P Sorokowski","year":"2023","unstructured":"Sorokowski, P. et al. Comparing accuracy in voice-based assessments of biological speaker traits across speech types. Sci. Rep. 13, 22989. https:\/\/doi.org\/10.1038\/s41598-023-49596-y (2023).","journal-title":"Sci. Rep."},{"key":"53409_CR69","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1016\/S0095-4470(95)80165-0","volume":"23","author":"DH Whalen","year":"1995","unstructured":"Whalen, D. H. & Levitt, A. G. The universality of intrinsic F0 of vowels. J. Phonetics. 23, 349\u2013366. https:\/\/doi.org\/10.1016\/S0095-4470(95)80165-0 (1995).","journal-title":"J. Phonetics."},{"key":"53409_CR70","doi-asserted-by":"publisher","unstructured":"Chun, K. S. et al. Towards Passive Assessment of Pulmonary Function from Natural Speech Recorded Using a Mobile Phone. 2020 IEEE International Conference on Pervasive Computing and Communications (PerCom),1\u201310. https:\/\/doi.org\/10.1109\/PerCom45495.2020.9127380 (2020).","DOI":"10.1109\/PerCom45495.2020.9127380"},{"key":"53409_CR71","doi-asserted-by":"publisher","first-page":"559e1","DOI":"10.1016\/j.jvoice.2022.10.006","volume":"39","author":"VS Fahed","year":"2025","unstructured":"Fahed, V. S., Doheny, E. P., Busse, M., Hoblyn, J. & Lowery, M. M. Comparison of acoustic voice features derived from mobile devices and studio microphone recordings. J. Voice. 39, 559e1-559e18. https:\/\/doi.org\/10.1016\/j.jvoice.2022.10.006 (2025).","journal-title":"J. Voice."},{"key":"53409_CR72","doi-asserted-by":"publisher","DOI":"10.1186\/s12938-021-00951-y","volume":"20","author":"J Carr\u00f3n","year":"2021","unstructured":"Carr\u00f3n, J., Campos-Roca, Y., Madruga, M. & P\u00e9rez, 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":"53409_CR73","unstructured":"Lundberg, S. M. & Lee, S-I. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. ;30. Available: https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/8a20a8621978632d76c43dfd28b67767-Abstract.html (2017)."},{"key":"53409_CR74","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2025.103109","volume":"163","author":"D Xavier","year":"2025","unstructured":"Xavier, D. et al. Voice analysis in Parkinson\u2019s disease - A systematic literature review. Artif. Intell. Med. 163, 103109. https:\/\/doi.org\/10.1016\/j.artmed.2025.103109 (2025).","journal-title":"Artif. Intell. Med."},{"key":"53409_CR75","doi-asserted-by":"publisher","first-page":"166370","DOI":"10.1109\/ACCESS.2021.3135626","volume":"9","author":"F Amato","year":"2021","unstructured":"Amato, F. et al. Speech impairment in Parkinson\u2019s disease: Acoustic analysis of unvoiced consonants in Italian native speakers. IEEE Access 9, 166370\u2013166381. https:\/\/doi.org\/10.1109\/ACCESS.2021.3135626 (2021).","journal-title":"IEEE Access"},{"key":"53409_CR76","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1212\/WNL.0000000000002350","volume":"86","author":"G Rizzo","year":"2016","unstructured":"Rizzo, G. et al. Accuracy of clinical diagnosis of Parkinson disease: A systematic review and meta-analysis. Neurology 86, 566\u2013576. https:\/\/doi.org\/10.1212\/WNL.0000000000002350 (2016).","journal-title":"Neurology"},{"key":"53409_CR77","doi-asserted-by":"publisher","first-page":"1971","DOI":"10.1038\/s41591-023-02450-0","volume":"29","author":"S Palmqvist","year":"2023","unstructured":"Palmqvist, S. et al. Cognitive effects of Lewy body pathology in clinically unimpaired individuals. Nat. Med. 29, 1971\u20131978. https:\/\/doi.org\/10.1038\/s41591-023-02450-0 (2023).","journal-title":"Nat. Med."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53409-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53409-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53409-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T09:29:09Z","timestamp":1779182949000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53409-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,19]]},"references-count":77,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["53409"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-53409-3","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,19]]},"assertion":[{"value":"13 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"The COPDVD dataset was collected at Blekinge Institute of Technology in accordance with applicable ethical regulations. The study was approved by the Swedish Ethical Review Authority in Ume\u00e5 (DNR: 2020 \u2212 01045) and was conducted in accordance with the principles of the Declaration of Helsinki\n                      40\n                      . All participants provided written informed consent prior to participation. The mPower dataset is a publicly available dataset collected by Sage Bionetworks. Ethical oversight for the original mPower study was obtained from the Western Institutional Review Board\n                      41\n                      . Participants were enrolled through a mobile application and completed an interactive electronic consent procedure, including an assessment of consent comprehension, before providing informed consent electronically. Participants actively selected their data sharing preferences as part of the consent process. The present study involved secondary analysis of fully de-identified data only and did not require additional ethical approval.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All authors have reviewed the manuscript and approved its submission for publication. The corresponding author confirms that consent for publication has been obtained from all co-authors.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"15485"}}