{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T07:16:22Z","timestamp":1788419782253,"version":"build-2803163510"},"reference-count":19,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T00:00:00Z","timestamp":1788393600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med. Technol."],"abstract":"<jats:sec>\n                    <jats:title>Problem<\/jats:title>\n                    <jats:p>While voice-based analysis has emerged as a potential non-invasive approach for exploring acoustic alterations associated with Type 2 Diabetes Mellitus (T2DM), current approaches often fail to fully capture disease-relevant vocal patterns due to simplified recording protocols and insufficient feature modeling.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Aim<\/jats:title>\n                    <jats:p>This study aims to investigate the feasibility of voice-based classification of T2DM using a multi-feature fusion framework, leveraging sustained vowel phonations and integrating multiple acoustic feature types to enhance diagnostic performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Voice recordings were collected from 378 participants, including T2DM patients and healthy controls. Each participant pronounced six Mandarin vowels, from which acoustic features\u2014including Mel-frequency cepstral coefficients (MFCCs), glottal parameters, and eGeMAPS descriptors\u2014were extracted. Neural networks, including convolutional and deep architectures, were applied to capture pathology-relevant segments. Vowel-level fusion modules aggregated features across vowels, and an attention-based hierarchical fusion mechanism combined the three feature types, adaptively emphasizing features most relevant to T2DM.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed dual-branch hierarchical fusion model achieved 80.48% detection accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>These results suggest that sustained vowel phonations contain potentially informative acoustic patterns associated with T2DM status. However, further validation using independent cohorts is required before clinical application.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmedt.2026.1908856","type":"journal-article","created":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T06:41:50Z","timestamp":1788417710000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-branch hierarchical fusion network for voice-based classification of type 2 diabetes mellitus using multi-vowel acoustic features"],"prefix":"10.3389","volume":"8","author":[{"given":"Pengxu","family":"Jiang","sequence":"first","affiliation":[{"name":"Central Hospital of Kaifeng","place":["Kaifeng, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenke","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Institute of Complexity Science, Henan University of Technology","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aiqin","family":"Li","sequence":"additional","affiliation":[{"name":"Central Hospital of Kaifeng","place":["Kaifeng, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[{"name":"The Institute of Complexity Science, Henan University of Technology","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1068","DOI":"10.1016\/S0140-6736(13)62154-6","article-title":"Pathophysiology and treatment of type 2 diabetes: perspectives on the past, present, and future","volume":"383","author":"Kahn","year":"2014","journal-title":"Lancet"},{"key":"B2","doi-asserted-by":"publisher","first-page":"10","DOI":"10.2337\/cd22-as01","article-title":"Standards of medical care in diabetes\u20142022 abridged for primary care providers","volume":"40","year":"2022","journal-title":"Clin Diabetes"},{"key":"B3","doi-asserted-by":"publisher","first-page":"101706","DOI":"10.1016\/j.artmed.2019.101706","article-title":"The virtual doctor: an interactive clinical-decision-support system based on deep learning for non-invasive prediction of diabetes","volume":"100","author":"Sp\u00e4nig","year":"2019","journal-title":"Artif Intell Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1016\/j.mcpdig.2023.08.005","article-title":"Acoustic analysis and prediction of type 2 diabetes mellitus using smartphone-recorded voice segments","volume":"1","author":"Kaufman","year":"2023","journal-title":"Mayo Clin Proc: Digit Health"},{"key":"B5","doi-asserted-by":"publisher","first-page":"2707","DOI":"10.1007\/s00405-024-08485-4","article-title":"Exploring the impact of type II diabetes mellitus on voice quality","volume":"281","author":"Saghiri","year":"2024","journal-title":"Eur Arch Otorhinolaryngol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1080\/14015439.2021.1917653","article-title":"Disease related changes in vocal parameters of patients with type 2 diabetes mellitus","volume":"47","author":"G\u00f6la\u00e7","year":"2022","journal-title":"Logoped Phoniatr Vocol"},{"key":"B7","author":"Chitkara","year":""},{"key":"B8","doi-asserted-by":"publisher","first-page":"e13327","DOI":"10.1111\/exsy.13327","article-title":"Voice pathology identification system using a deep learning approach based on unique feature selection sets","volume":"42","author":"Abdulmajeed","year":"2025","journal-title":"Expert Syst"},{"key":"B9","doi-asserted-by":"publisher","first-page":"64","DOI":"10.65511\/jaima.v1i1.733","article-title":"Automated multi-class diabetic retinopathy classification using EfficientNet-B2 based on color fundus images","volume":"1","author":"Mukhlif","year":"2025","journal-title":"J Artif Intell Med Appl"},{"key":"B10","first-page":"19","article-title":"Mfcc and its applications in speaker recognition","volume":"1","author":"Tiwari","year":"2010","journal-title":"Int J Emerg Technol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/TBME.2007.900562","article-title":"Critical analysis of the impact of glottal features in the classification of clinical depression in speech","volume":"55","author":"Moore II","year":"2008","journal-title":"IEEE Trans Biomed Eng"},{"key":"B12","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","article-title":"The geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing","volume":"7","author":"Eyben","year":"2016","journal-title":"IEEE Trans Affect Comput"},{"key":"B13","author":"Eyben","year":""},{"key":"B14","doi-asserted-by":"publisher","first-page":"218","DOI":"10.21037\/atm.2016.03.37","article-title":"Introduction to machine learning: k-nearest neighbors","volume":"4","author":"Zhang","year":"2016","journal-title":"Ann Transl Med"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41870-017-0080-1","article-title":"Survey on SVM and their application in image classification","volume":"13","author":"Chandra","year":"2021","journal-title":"Int J Inf Technol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1162\/neco_a_01199","article-title":"A review of recurrent neural networks: LSTM cells and network architectures","volume":"31","author":"Yu","year":"2019","journal-title":"Neural Comput"},{"key":"B17","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1007\/s42979-020-0114-9","article-title":"Detecting affect states using VGG16, ResNet50 and SE-ResNet50 networks","volume":"1","author":"Theckedath","year":"2020","journal-title":"SN Comput Sci"},{"key":"B18","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.jvoice.2019.07.003","article-title":"Instrumental acoustic voice characteristics in adults with type 2 diabetes","volume":"35","author":"Pinyopodjanard","year":"2021","journal-title":"J Voice"},{"key":"B19","doi-asserted-by":"publisher","first-page":"e0000679","DOI":"10.1371\/journal.pdig.0000679","article-title":"A voice-based algorithm can predict type 2 diabetes status in USA adults: findings from the colive voice study","volume":"3","author":"Elb\u00e9ji","year":"2024","journal-title":"PLoS Digit Health"}],"container-title":["Frontiers in Medical Technology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmedt.2026.1908856\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T06:41:51Z","timestamp":1788417711000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmedt.2026.1908856\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,3]]},"references-count":19,"alternative-id":["10.3389\/fmedt.2026.1908856"],"URL":"https:\/\/doi.org\/10.3389\/fmedt.2026.1908856","relation":{},"ISSN":["2673-3129"],"issn-type":[{"value":"2673-3129","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,3]]},"article-number":"1908856"}}