{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T18:12:12Z","timestamp":1791915132764,"version":"4.3.4"},"reference-count":39,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Neurotech"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Speech features are increasingly linked to neurodegenerative and mental health conditions, offering the potential for early detection and differentiation between disorders. As interest in speech analysis grows, distinguishing between conditions becomes critical for reliable diagnosis and assessment.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This pilot study explores speech biosignatures in two distinct neurodegenerative conditions: (1) mild traumatic brain injuries (eg, concussions) and (2) Parkinson disease (PD) as the neurodegenerative condition.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n The study included speech samples from 235 participants (97 concussed and 94 age-matched healthy controls, 29 PD and 15 healthy controls) for the PaTaKa test and 239 participants (91 concussed and 104 healthy controls, 29 PD and 15 healthy controls) for the Sustained Vowel (\/ah\/) test. Age-matched healthy controls were used. Young age-matched controls were used for concussion and respective age-matched controls for neurodegenerative participants (15 healthy samples for both tests). Data augmentation with noise was applied to balance small datasets for neurodegenerative and healthy controls. Machine learning models (support vector machine, decision tree, random forest, and Extreme Gradient Boosting) were employed using 37 temporal and spectral speech features. A 5-fold stratified cross-validation was used to evaluate classification performance.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n For the PaTaKa test, classifiers performed well, achieving\n F<\/jats:italic>\n 1<\/jats:sub>\n -scores above 0.9 for concussed versus healthy and concussed versus neurodegenerative classifications across all models. Initial tests using the original dataset for neurodegenerative versus healthy classification yielded very poor results, with\n F<\/jats:italic>\n 1<\/jats:sub>\n -scores below 0.2 and accuracy under 30% (eg, below 12 out of 44 correctly classified samples) across all models. This underscored the need for data augmentation, which significantly improved performance to 60%\u201070% (eg, 26\u201031 out of 44 samples) accuracy. In contrast, the Sustained Vowel test showed mixed results;\n F<\/jats:italic>\n 1<\/jats:sub>\n -scores remained high (more than 0.85 across all models) for concussed versus neurodegenerative classifications but were significantly lower for concussed versus healthy (0.59\u20100.62) and neurodegenerative versus healthy (0.33\u20100.77), depending on the model.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This study highlights the potential of speech features as biomarkers for neurodegenerative conditions. The PaTaKa test exhibited strong discriminative ability, especially for concussed versus neurodegenerative and concussed versus healthy tasks, whereas challenges remain for neurodegenerative versus healthy classification. These findings emphasize the need for further exploration of speech-based tools for differential diagnosis and early identification in neurodegenerative health.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/64624","type":"journal-article","created":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T03:57:08Z","timestamp":1736308628000},"page":"e64624-e64624","source":"Crossref","is-referenced-by-count":7,"title":["Exploring Speech Biosignatures for Traumatic Brain Injury and Neurodegeneration: Pilot Machine Learning Study"],"prefix":"10.2196","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3550-6624","authenticated-orcid":false,"given":"Rahmina","family":"Rubaiat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7229-9975","authenticated-orcid":false,"given":"John Michael","family":"Templeton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8766-7355","authenticated-orcid":false,"given":"Sandra L","family":"Schneider","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6913-3464","authenticated-orcid":false,"given":"Upeka","family":"De Silva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6430-9611","authenticated-orcid":false,"given":"Samaneh","family":"Madanian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0599-7941","authenticated-orcid":false,"given":"Christian","family":"Poellabauer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,2,12]]},"reference":[{"issue":"6","key":"R1","doi-asserted-by":"publisher","DOI":"10.2196\/15517","article-title":"Enhancement of neurocognitive assessments using smartphone capabilities: systematic review","volume":"8","author":"Templeton","journal-title":"JMIR Mhealth Uhealth"},{"issue":"1","key":"R2","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1044\/2021_PERSP-21-00174","article-title":"Speech as a biomarker: opportunities, interpretability, and challenges","volume":"7","author":"Ramanarayanan","journal-title":"Perspect ASHA SIGs"},{"issue":"3","key":"R3","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1159\/000510820","article-title":"Evaluation of speech-based digital biomarkers: review and recommendations","volume":"4","author":"Robin","journal-title":"Digit Biomark"},{"issue":"4","key":"R4","doi-asserted-by":"publisher","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","journal-title":"IEEE Trans Biomed Eng"},{"issue":"10","key":"R5","doi-asserted-by":"publisher","first-page":"1300","DOI":"10.1038\/s41593-018-0237-7","article-title":"Converging pathways in neurodegeneration, from genetics to mechanisms","volume":"21","author":"Gan","journal-title":"Nat Neurosci"},{"issue":"1","key":"R6","first-page":"3","volume":"4","author":"Kiaei","journal-title":"Basic Clin Neurosci"},{"key":"R7","unstructured":"Doherty C . ALS vs Parkinson\u2019s: what are the differences?Verywell Health. 2024. URL: https:\/\/www.verywellhealth.com\/als-vs-parkinsons-6826333 [Accessed 06-02-2025]"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1038\/scientificamerican0197-52","article-title":"Understanding Parkinson\u2019s disease","volume":"276","author":"Youdim","journal-title":"Sci Am"},{"issue":"10","key":"R9","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1001\/archneurol.2011.3747","article-title":"Dementia resulting from traumatic brain injury: what is the pathology?","volume":"69","author":"Shively","journal-title":"Arch Neurol"},{"issue":"2","key":"R10","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.jemermed.2005.01.020","article-title":"Recognition and characteristics of concussions in the emergency department population","volume":"29","author":"Delaney","journal-title":"J Emerg Med"},{"key":"R11","unstructured":"O\u2019Sullivan SB Schmitz TJ Fulk G . Physical Rehabilitation. FA Davis; 2019."},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfludis.2019.01.001","article-title":"Disfluency clusters in speakers with and without neurogenic stuttering following traumatic brain injury","volume":"59","author":"Penttil\u00e4","journal-title":"J Fluency Disord"},{"issue":"5-6","key":"R13","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1080\/21678421.2017.1303515","article-title":"The diagnostic utility of patient-report and speech-language pathologists\u2019 ratings for detecting the early onset of bulbar symptoms due to ALS","volume":"18","author":"Allison","journal-title":"Amyotroph Lateral Scler Frontotemporal Degener"},{"key":"R14","doi-asserted-by":"crossref","unstructured":"Aich S Kim HC younga K Hui KL Al-Absi AA Sain M . A supervised machine learning approach using different feature selection techniques on voice datasets for prediction of Parkinson\u2019s disease. Presented at: 2019 21st International Conference on Advanced Communication Technology (ICACT); Feb 17-20, 2019; PyeongChang, South Korea. [doi: 10.23919\/ICACT.2019.8701961]","DOI":"10.23919\/ICACT.2019.8701961"},{"key":"R15","doi-asserted-by":"crossref","unstructured":"Duffy JR . Motor Speech Disorders: Clues to Neurologic Diagnosis. Humana Press; 2000:35-53. [doi: 10.1007\/978-1-59259]","DOI":"10.1007\/978-1-59259-410-8_2"},{"key":"R16","doi-asserted-by":"crossref","unstructured":"Smith R Chepisheva M Cronin T Seemungal BM . Chapter 16 - diagnostic approaches techniques in concussion\/mild traumatic brain injury: where are we. In: Hoffer ME Balaban CD , editors. Neurosensory Disorders in Mild Traumatic Brain Injury. Academic Press; 2019:247-277. [doi: 10.1016\/B978-0-12-812344-7.00016-9]","DOI":"10.1016\/B978-0-12-812344-7.00016-9"},{"key":"R17","doi-asserted-by":"crossref","unstructured":"Patel S Grabowski C Dayalu V Cunningham M Testa AJ . Fluency changes due to sports-related concussion. medRxiv. Preprint posted online onSep23, 2021. [doi: 10.1101\/2021.09.19.21263791]","DOI":"10.1101\/2021.09.19.21263791"},{"issue":"2","key":"R18","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1109\/JBHI.2016.2633509","article-title":"Portable mTBI assessment using temporal and frequency analysis of speech","volume":"21","author":"Daudet","journal-title":"IEEE J Biomed Health Inform"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2019.8856559","article-title":"New insights into Parkinson\u2019s disease through statistical analysis of standard clinical scales quantifying symptom severity","volume":"2019","author":"Tsanas","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"issue":"5","key":"R20","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1038\/nn0507-535","article-title":"ALS: astrocytes move in as deadly neighbors","volume":"10","author":"Julien","journal-title":"Nat Neurosci"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/9832839","article-title":"Pathophysiology of motor dysfunction in Parkinson\u2019s disease as the rationale for drug treatment and rehabilitation","volume":"2016","author":"Magrinelli","journal-title":"Parkinsons Dis"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","first-page":"108","DOI":"10.15676\/ijeei.2016.8.1.8","article-title":"Voice analysis for detecting patients with Parkinson\u2019s disease using the hybridization of the best acoustic features","volume":"8","author":"Benba","journal-title":"Int J Electr Eng Inform"},{"key":"R23","doi-asserted-by":"crossref","unstructured":"Mallela J Illa A Suhas BN et al. Voice based classification of patients with amyotrophic lateral sclerosis, Parkinson\u2019s disease and healthy controls with CNN-LSTM using transfer learning. Presented at: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); May 4-8, 2020; Barcelona, Spain. [doi: 10.1109\/ICASSP40776.2020.9053682]","DOI":"10.1109\/ICASSP40776.2020.9053682"},{"issue":"2","key":"R24","doi-asserted-by":"publisher","first-page":"1840007","DOI":"10.1142\/S2424922X18400077","article-title":"Clustering Parkinson\u2019s and age-related voice impairment signal features for unsupervised learning","volume":"10","author":"Rueda","journal-title":"Adv Data Sci Adapt Data Anal"},{"key":"R25","unstructured":"Tsanas A Arora S . Biomedical speech signal insights from a large scale cohort across seven countries: the Parkinson\u2019s voice initiative study. Presented at: 11th International Workshop, Models and Analysis of Vocal Emissions for Biomedical Applications (MAVEBA); Dec 17-19, 2019; Firenze, Italy. 2019."},{"key":"R26","doi-asserted-by":"crossref","unstructured":"Vashkevich M Azarov E Petrovsky A Rushkevich Y . Features extraction for the automatic detection of ALS disease from acoustic speech signals. Presented at: 2018 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA); Sep 19-21, 2018; Poznan, Poland. [doi: 10.23919\/SPA.2018.8563414]","DOI":"10.23919\/SPA.2018.8563414"},{"issue":"5","key":"R27","doi-asserted-by":"publisher","first-page":"1264","DOI":"10.1109\/TBME.2012.2183367","article-title":"Novel speech signal processing algorithms for high-accuracy classification of Parkinson\u2019s disease","volume":"59","author":"Tsanas","journal-title":"IEEE Trans Biomed Eng"},{"key":"R28","doi-asserted-by":"crossref","unstructured":"Tsanas A Arora S . Assessing Parkinson\u2019s Disease Speech Signal Generalization of Clustering Results across Three Countries: Findings in the Parkinson\u2019s Voice Initiative Study. SCITEPRESS - Science and Technology Publications; 2021:124-131. [doi: 10.5220\/0010383001240131]","DOI":"10.5220\/0010383000002865"},{"issue":"2\/3","key":"R29","first-page":"147","volume":"18","author":"Bongioanni","journal-title":"Int J Med Biol Front"},{"issue":"9","key":"R30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0274395","article-title":"A deep learning-based approach to diagnose mild traumatic brain injury using audio classification","volume":"17","author":"Wall","journal-title":"PLoS One"},{"key":"R31","doi-asserted-by":"crossref","unstructured":"McFee B Raffel C Liang D et al. librosa: audio and music signal analysis in Python. Presented at: Python in Science Conference; Jul 6-12, 2015; Austin, Texas. [doi: 10.25080\/Majora-7b98e3ed-003]","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"R32","doi-asserted-by":"crossref","unstructured":"Boser BE Guyon IM Vapnik VN . A training algorithm for optimal margin classifiers. Presented at: COLT92; Jul 27-29, 1992; Pittsburgh, PA, United States. [doi: 10.1145\/130385.130401]","DOI":"10.1145\/130385.130401"},{"key":"R33","unstructured":"Vapnik V . The Nature of Statistical Learning Theory. Springer Science Business Media; 2013."},{"key":"R34","unstructured":"Rokach L Maimon O . Data Mining with Decision Trees: Theory and Applications. Vol81. 2nded. 2014. Series in Machine Perception and Artificial Intelligence. ISBN: 978-981-4590-07-5"},{"issue":"1","key":"R35","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","journal-title":"Mach Learn"},{"issue":"1","key":"R36","doi-asserted-by":"publisher","first-page":"012024","DOI":"10.1088\/1742-6596\/1538\/1\/012024","article-title":"Implementation of XGBoost for classification of Parkinson\u2019s disease","volume":"1538","author":"Abdurrahman","journal-title":"J Phys: Conf Ser"},{"key":"R37","doi-asserted-by":"crossref","unstructured":"Pishgar M Karim F Majumdar S Darabi H . Pathological voice classification using mel-cepstrum vectors and support vector machine. arXiv. Preprint posted online onDec19, 2018. [doi: 10.48550\/arXiv.1812.07729]","DOI":"10.1109\/BigData.2018.8622208"},{"key":"R38","unstructured":"Difference between Random Forest and XGBoost. Geeks for Geeks. 2024. URL: https:\/\/www.geeksforgeeks.org\/difference-between-random-forest-vs-xgboost\/ [Accessed 06-02-2025]"},{"key":"R39","unstructured":"Jain M Narayan S Balaji P P BK . Speech emotion recognition using support vector machine. arXiv. Preprint posted online onFeb3, 2020. [doi: 10.48550\/arXiv.2002.07590]"}],"container-title":["JMIR Neurotechnology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/neuro.jmir.org\/2025\/1\/e64624","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:30:19Z","timestamp":1785537019000},"score":1,"resource":{"primary":{"URL":"https:\/\/neuro.jmir.org\/2025\/1\/e64624"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,12]]},"references-count":39,"URL":"https:\/\/doi.org\/10.2196\/64624","relation":{},"ISSN":["2817-092X"],"issn-type":[{"value":"2817-092X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,12]]},"article-number":"v4i6e64624"}}