{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T15:14:33Z","timestamp":1790608473351,"version":"4.1.0"},"reference-count":28,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,11,30]],"date-time":"2025-11-30T00:00:00Z","timestamp":1764460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002701","name":"Ministry of Education of the Republic of Korea","doi-asserted-by":"crossref","award":["NRF-2022S1A5A2A03050428"],"award-info":[{"award-number":["NRF-2022S1A5A2A03050428"]}],"id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Behavioral Sciences"],"abstract":"<jats:p>This exploratory study investigated whether voice-derived acoustic features reflect depressive symptom severity and whether they carry preliminary predictive signal for distinguishing individuals with Major Depressive Disorder (MDD) from healthy controls (HC). Using the publicly available MODMA dataset (23 MDD; 29 HC), 6553 acoustic features were extracted with openSMILE. Spearman correlation and group-difference analyses identified several MFCC-derived spectral features as moderately and systematically associated with PHQ-9 scores, indicating their potential relevance as severity-linked acoustic markers. To complement these findings, a supplementary severity-based classification using a PHQ-9 \u2265 10 threshold showed that a logistic regression model trained on the top five correlated MFCC features achieved a cross-validated AUC of 0.78 (SD = 0.15), supporting their association with clinically defined symptom burden. Four machine learning pipelines were further evaluated for an exploratory MDD\u2013HC classification task. Among them, the PCA + XGBoost model demonstrated the most stable generalization (test AUC = 0.60), although predictive performance remained limited within the constraints of the small and high-dimensional dataset. SHAP analysis highlighted MFCC-derived features as key contributors to model decisions, providing transparent interpretability. Overall, the study presents preliminary evidence linking acoustic characteristics to depressive symptoms and outlines a reproducible analytical workflow, while underscoring the need for substantially larger and more diverse datasets to establish clinically meaningful predictive validity.<\/jats:p>","DOI":"10.3390\/bs15121648","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T13:03:02Z","timestamp":1764594182000},"page":"1648","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring Acoustic Correlates of Depression and Preliminary Screening Models Using XGBoost and SHAP"],"prefix":"10.3390","volume":"15","author":[{"given":"Kwang-Ho","family":"Seok","sequence":"first","affiliation":[{"name":"School of AI Convergence, Global Cyber University, Cheonan 31228, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaeeun","family":"Shin","sequence":"additional","affiliation":[{"name":"Department of Psychology, Chung-Ang University, Seoul 06974, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung-Man","family":"Bae","sequence":"additional","affiliation":[{"name":"Department of Psychology and Psychotherapy, College of Health Science, Dankook University, Cheonan 31116, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Al Hanai, T., Ghassemi, M., and Glass, J. (, January September). Detecting depression with audio\/text sequence modeling of interviews. Interspeech 2018, Hyderabad, India.","DOI":"10.21437\/Interspeech.2018-2522"},{"key":"ref_2","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":"Advances in Neural Information Processing Systems"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1037\/prj0000130","article-title":"Next-generation psychiatric assessment: Using smartphone sensors to monitor behavior and mental health","volume":"38","author":"Scherer","year":"2015","journal-title":"Psychiatric Rehabilitation Journal"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1038\/s41746-024-01199-1","article-title":"Responsible development of clinical speech AI: Bridging the gap between clinical research and technology","volume":"7","author":"Berisha","year":"2024","journal-title":"npj Digital Medicine"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Chen, I.-M., Chen, Y.-Y., Liao, S.-C., and Lin, Y.-H. (2022). Development of digital biomarkers of mental illness via mobile apps for personalized treatment and diagnosis. Journal of Personalized Medicine, 12.","DOI":"10.3390\/jpm12060936"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Chen, X., and Pan, Z. (2021). A convenient and low-cost model of depression screening and early warning based on voice data using for public mental health. International Journal of Environmental Research and Public Health, 18, (12).","DOI":"10.3390\/ijerph18126441"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.jad.2023.08.097","article-title":"Multilingual markers of depression in remotely collected speech samples: A preliminary analysis","volume":"341","author":"Cummins","year":"2023","journal-title":"Journal of Affective Disorders"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.specom.2015.03.004","article-title":"A review of depression and suicide risk assessment using speech analysis","volume":"71","author":"Cummins","year":"2015","journal-title":"Speech Communication"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.jad.2021.04.004","article-title":"Using i-vectors from voice features to identify major depressive disorder","volume":"288","author":"Di","year":"2021","journal-title":"Journal of Affective Disorders"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"100118","DOI":"10.1016\/j.smhl.2020.100118","article-title":"Moodable: On feasibility of instantaneous depression assessment using machine learning on voice samples with retrospectively harvested smartphone and social media data","volume":"17","author":"Dogrucu","year":"2020","journal-title":"Smart Health"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"11155","DOI":"10.1038\/s41598-023-35184-7","article-title":"Manifestation of depression in speech overlaps with characteristics used to represent and recognize speaker identity","volume":"13","author":"Dumpala","year":"2023","journal-title":"Scientific Reports"},{"key":"ref_12","unstructured":"Eyben, F., W\u00f6llmer, M., and Schuller, B. (, January October). openSMILE\u2014The Munich versatile and fast open-source audio feature extractor. 18th ACM International Conference on Multimedia, Florence, Italy."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Gheorghe, M., Mihalache, S., and Burileanu, D. (, January September). Using deep neural networks for detecting depression from speech. 2023 31st European Signal Processing Conference (EUSIPCO), Helsinki, Finland.","DOI":"10.23919\/EUSIPCO58844.2023.10289973"},{"key":"ref_14","unstructured":"Gonzalez-Machorro, M., Reichel, U., Hecker, P., Hammer, H., Sagha, H., Eyben, F., Hoepner, R., and Schuller, B. W. (2025). Speech-based depressive mood detection in the presence of multiple sclerosis: A cross-corpus and cross-lingual study. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"G\u00f3mez-Zaragoz\u00e1, L., Mar\u0131n-Morales, J., Alcaniz, M., and Soleymani, M. (, January August). Speech and text foundation models for depression detection: Cross-task and cross-language evaluation. Interspeech 2025, Rotterdam, The Netherlands.","DOI":"10.21437\/Interspeech.2025-1035"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"H\u00f6nig, F., Batliner, A., N\u00f6th, E., Schnieder, S., and Krajewski, J. (, January September). Automatic modeling of depressed speech: Relevant features and relevance of gender. Interspeech 2014, Singapore.","DOI":"10.21437\/Interspeech.2014-313"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"K\u00f6nig, A., Tr\u00f6ger, J., Mallick, E., Mina, M., Linz, N., Wagnon, C., Karbach, J., Kuhn, C., and Peter, J. (2022). Detecting subtle signs of depression with automated speech analysis in a non-clinical sample. BMC Psychiatry, 22.","DOI":"10.1186\/s12888-022-04475-0"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1046\/j.1525-1497.2001.016009606.x","article-title":"The PHQ-9: Validity of a brief depression severity measure","volume":"16","author":"Kroenke","year":"2001","journal-title":"Journal of General Internal Medicine"},{"key":"ref_19","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1038\/s44184-023-00040-z","article-title":"A systematic review on automated clinical depression diagnosis","volume":"2","author":"Mao","year":"2023","journal-title":"npj Mental Health Research"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Menne, F., D\u00f6rr, F., Schr\u00e4der, J., Tr\u00f6ger, J., Habel, U., K\u00f6nig, A., and Wagels, L. (2024). The voice of depression: Speech features as biomarkers for major depressive disorder. BMC Psychiatry, 24.","DOI":"10.1186\/s12888-024-06253-6"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e27589","DOI":"10.2196\/27589","article-title":"Toward a mobile platform for real-world digital measurement of depression: User-centered design, data quality, and behavioral and clinical modeling","volume":"8","author":"Nickels","year":"2021","journal-title":"JMIR Mental Health"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"119739","DOI":"10.1016\/j.jad.2025.119739","article-title":"A cross-linguistic depression detection method based on speech data","volume":"390","author":"Qin","year":"2025","journal-title":"Journal of Affective Disorders"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Schuller, B., Steidl, S., and Batliner, A. (, January September). The INTERSPEECH 2009 emotion challenge. Interspeech 2009, Brighton, UK.","DOI":"10.21437\/Interspeech.2009-103"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1016\/j.jad.2022.12.117","article-title":"Development and validation of a machine learning-based vocal predictive model for major depressive disorder","volume":"325","author":"Wasserzug","year":"2022","journal-title":"Journal of Affective Disorders"},{"key":"ref_26","unstructured":"World Health Organization (2025, April 13). COVID-19 pandemic triggers 25% increase in prevalence of anxiety and depression worldwide, Available online: https:\/\/www.who.int\/news\/item\/02-03-2022-covid-19-pandemic-triggers-25-increase-in-prevalence-of-anxiety-and-depression-worldwide."},{"key":"ref_27","unstructured":"World Health Organization (2025, April 13). Depression, Available online: https:\/\/www.who.int\/health-topics\/depression."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1038\/s41597-022-01211-x","article-title":"MODMA dataset: A multi-modal open dataset for mental-disorder analysis","volume":"9","author":"Zhu","year":"2022","journal-title":"Scientific Data"}],"container-title":["Behavioral Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-328X\/15\/12\/1648\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T05:10:54Z","timestamp":1764738654000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-328X\/15\/12\/1648"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,30]]},"references-count":28,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["bs15121648"],"URL":"https:\/\/doi.org\/10.3390\/bs15121648","relation":{},"ISSN":["2076-328X"],"issn-type":[{"value":"2076-328X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,30]]}}}