{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:44:45Z","timestamp":1792788285676,"version":"4.5.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T00:00:00Z","timestamp":1721779200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T00:00:00Z","timestamp":1721779200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100014717","name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82004260"],"award-info":[{"award-number":["82004260"]}],"id":[{"id":"10.13039\/100014717","id-type":"DOI","asserted-by":"publisher"}]},{"name":"High Level Key Discipline of National Administration of Traditional Chinese Medicine - Traditional Chinese constitutional medicine","award":["ZYYZDXK-2023251"],"award-info":[{"award-number":["ZYYZDXK-2023251"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Chin Med"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Human health is a complex, dynamic concept encompassing a spectrum of states influenced by genetic, environmental, physiological, and psychological factors. Traditional Chinese Medicine categorizes health into nine body constitutional types, each reflecting unique balances or imbalances in vital energies, influencing physical, mental, and emotional states. Advances in machine learning models offer promising avenues for diagnosing conditions like Alzheimer's, dementia, and respiratory diseases by analyzing speech patterns, enabling complementary non-invasive disease diagnosis. The study aims to use speech audio to identify subhealth populations characterized by unbalanced constitution types.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Participants, aged 18\u201345, were selected from the Acoustic Study of Health. Audio recordings were collected using ATR2500X-USB microphones and Praat software. Exclusion criteria included recent illness, dental issues, and specific medical histories. The audio data were preprocessed to Mel-frequency cepstral coefficients (MFCCs) for model training. Three deep learning models\u20141-Dimensional Convolution Network (Conv1D), 2-Dimensional Convolution Network (Conv2D), and Long Short-Term Memory (LSTM)\u2014were implemented using Python to classify health status. Saliency maps were generated to provide model explainability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The study used 1,378 recordings from balanced (healthy) and 1,413 from unbalanced (subhealth) types. The Conv1D model achieved a training accuracy of 91.91% and validation accuracy of 84.19%. The Conv2D model had 96.19% training accuracy and 84.93% validation accuracy. The LSTM model showed 92.79% training accuracy and 87.13% validation accuracy, with early signs of overfitting. AUC scores were 0.92 and 0.94 (Conv1D), 0.99 (Conv2D), and 0.97 (LSTM). All models demonstrated robust performance, with Conv2D excelling in discrimination accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The deep learning classification of human speech audio for health status using body constitution types showed promising results with Conv1D, Conv2D, and LSTM models. Analysis of ROC curves, training accuracy, and validation accuracy showed all models robustly distinguished between balanced and unbalanced constitution types. Conv2D excelled with good accuracy, while Conv1D and LSTM also performed well, affirming their reliability. The study integrates constitution theory and deep learning technologies to classify subhealth populations using noninvasive approach, thereby promoting personalized medicine and early intervention strategies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13020-024-00973-3","type":"journal-article","created":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T02:06:55Z","timestamp":1721786815000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Sound as a bell: a deep learning approach for health status classification through speech acoustic biomarkers"],"prefix":"10.1186","volume":"19","author":[{"given":"Yanbing","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuoxuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liwen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiarui","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixiang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shujuan","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,24]]},"reference":[{"issue":"1","key":"973_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41435-022-00192-6","volume":"24","author":"SJ Virolainen","year":"2023","unstructured":"Virolainen SJ, et al. Gene-environment interactions and their impact on human health. Genes Immun. 2023;24(1):1\u201311.","journal-title":"Genes Immun"},{"issue":"4","key":"973_CR2","doi-asserted-by":"publisher","first-page":"e1463","DOI":"10.1002\/wcs.1463","volume":"9","author":"B Chambliss","year":"2018","unstructured":"Chambliss B. The mind-body problem. Wiley Interdiscip Rev Cogn Sci. 2018;9(4):e1463.","journal-title":"Wiley Interdiscip Rev Cogn Sci"},{"issue":"2","key":"973_CR3","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1097\/MOP.0000000000000876","volume":"32","author":"T Poulain","year":"2020","unstructured":"Poulain T, Vogel M, Kiess W. Review on the role of socioeconomic status in child health and development. Curr Opin Pediatr. 2020;32(2):308\u201314.","journal-title":"Curr Opin Pediatr"},{"issue":"2","key":"973_CR4","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1177\/0022146510395592","volume":"52","author":"PA Thoits","year":"2011","unstructured":"Thoits PA. Mechanisms linking social ties and support to physical and mental health. J Health Soc Behav. 2011;52(2):145\u201361.","journal-title":"J Health Soc Behav"},{"issue":"1","key":"973_CR5","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1037\/0003-066X.55.1.68","volume":"55","author":"RM Ryan","year":"2000","unstructured":"Ryan RM, Deci EL. Self-determination theory and the facilitation of intrinsic motivation, social development, and well-being. Am Psychol. 2000;55(1):68\u201378.","journal-title":"Am Psychol"},{"issue":"1","key":"973_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11684-012-0173-y","volume":"6","author":"Q Wang","year":"2012","unstructured":"Wang Q. Individualized medicine, health medicine, and constitutional theory in Chinese medicine. Front Med. 2012;6(1):1\u20137.","journal-title":"Front Med"},{"issue":"5","key":"973_CR7","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1007\/s11655-014-2019-8","volume":"21","author":"J Wang","year":"2015","unstructured":"Wang J, et al. Research on constitution of Chinese medicine and implementation of translational medicine. Chin J Integr Med. 2015;21(5):389\u201393.","journal-title":"Chin J Integr Med"},{"issue":"2","key":"973_CR8","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1142\/S0192415X13500183","volume":"41","author":"J Wang","year":"2013","unstructured":"Wang J, et al. Phlegm-dampness constitution: genomics, susceptibility, adjustment and treatment with traditional Chinese medicine. Am J Chin Med. 2013;41(2):253\u201362.","journal-title":"Am J Chin Med"},{"issue":"2","key":"973_CR9","doi-asserted-by":"publisher","first-page":"e12424","DOI":"10.1016\/j.heliyon.2022.e12424","volume":"9","author":"H Zhao","year":"2023","unstructured":"Zhao H, et al. Damp-heat constitution influences gut microbiota and urine metabolism of Chinese infants. Heliyon. 2023;9(2):e12424.","journal-title":"Heliyon"},{"issue":"12","key":"973_CR10","first-page":"7333","volume":"37","author":"X-L Wang","year":"2022","unstructured":"Wang X-L, Wan J-Y, Yao H-Q. Discussion on the effects of irregular daily living on the formation of phlegm-dampness constitution from the perspective of circadian dysrhythmia modulating intestinal flora. China J Tradit Chin Med Pharm (Zhong Hua Zhong Yi Yao Za Zhi). 2022;37(12):7333\u20136.","journal-title":"China J Tradit Chin Med Pharm (Zhong Hua Zhong Yi Yao Za Zhi)"},{"issue":"1","key":"973_CR11","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1186\/s13020-023-00844-3","volume":"18","author":"M-H Bai","year":"2023","unstructured":"Bai M-H, et al. Development and evaluation of short-form version of the Constitution in Chinese Medicine Questionnaire: study a new and best brief instrument of Chinese medicine for health management. Chin Med. 2023;18(1):140.","journal-title":"Chin Med"},{"issue":"5","key":"973_CR12","doi-asserted-by":"publisher","first-page":"e0217388","DOI":"10.1371\/journal.pone.0217388","volume":"14","author":"S Al-Hameed","year":"2019","unstructured":"Al-Hameed S, et al. A new diagnostic approach for the identification of patients with neurodegenerative cognitive complaints. PLoS ONE. 2019;14(5):e0217388.","journal-title":"PLoS ONE"},{"key":"973_CR13","doi-asserted-by":"publisher","DOI":"10.1136\/jnnp-2019-322517","author":"RPD O'Malley","year":"2020","unstructured":"O\u2019Malley RPD, et al. Fully automated cognitive screening tool based on assessment of speech and language. J Neurol Neurosurg Psychiatry. 2020. https:\/\/doi.org\/10.1136\/jnnp-2019-322517.","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"973_CR14","doi-asserted-by":"publisher","first-page":"624137","DOI":"10.3389\/fpsyg.2020.624137","volume":"11","author":"RM Haulcy","year":"2020","unstructured":"Haulcy RM, Glass J. Classifying Alzheimer\u2019s disease using audio and text-based representations of speech. Front Psychol. 2020;11:624137.","journal-title":"Front Psychol"},{"issue":"1","key":"973_CR15","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1186\/s13195-021-00888-3","volume":"13","author":"C Xue","year":"2021","unstructured":"Xue C, et al. Detection of dementia on voice recordings using deep learning: a Framingham heart study. Alzheimer\u2019s Res Ther. 2021;13(1):146.","journal-title":"Alzheimer's Res Ther"},{"issue":"12","key":"973_CR16","doi-asserted-by":"publisher","first-page":"3599","DOI":"10.3390\/s20123599","volume":"20","author":"B Sumali","year":"2020","unstructured":"Sumali B, et al. Speech quality feature analysis for classification of depression and dementia patients. Sensors. 2020;20(12):3599.","journal-title":"Sensors"},{"issue":"23","key":"973_CR17","doi-asserted-by":"publisher","first-page":"9311","DOI":"10.3390\/s22239311","volume":"22","author":"MR Kumar","year":"2022","unstructured":"Kumar MR, et al. Dementia detection from speech using machine learning and deep learning architectures. Sensors. 2022;22(23):9311.","journal-title":"Sensors"},{"key":"973_CR18","doi-asserted-by":"publisher","first-page":"109539","DOI":"10.1016\/j.knosys.2022.109539","volume":"253","author":"G Costantini","year":"2022","unstructured":"Costantini G, et al. Deep learning and machine learning-based voice analysis for the detection of COVID-19: a proposal and comparison of architectures. Knowl-Based Syst. 2022;253:109539.","journal-title":"Knowl-Based Syst"},{"issue":"6","key":"973_CR19","doi-asserted-by":"publisher","first-page":"e37004","DOI":"10.2196\/37004","volume":"24","author":"T Dang","year":"2022","unstructured":"Dang T, et al. Exploring longitudinal cough, breath, and voice data for COVID-19 progression prediction via sequential deep learning: model development and validation. J Med Internet Res. 2022;24(6):e37004.","journal-title":"J Med Internet Res"},{"issue":"1","key":"973_CR20","doi-asserted-by":"publisher","first-page":"19149","DOI":"10.1038\/s41598-021-98742-x","volume":"11","author":"P Suppakitjanusant","year":"2021","unstructured":"Suppakitjanusant P, et al. Identifying individuals with recent COVID-19 through voice classification using deep learning. Sci Rep. 2021;11(1):19149.","journal-title":"Sci Rep"},{"key":"973_CR21","unstructured":"Boersma, P. and D. Weenink, Praat: doing phonetics by computer [Computer program]. 2022. https:\/\/www.praat.org. Accessed 1 Mar 2022."},{"issue":"4","key":"973_CR22","first-page":"1","volume":"28","author":"W Qi","year":"2005","unstructured":"Qi W. Classification and diagnosis basis of nine basic constitutions in Chinese medicine. J Beijing Univ Tradit Chin Med. 2005;28(4):1.","journal-title":"J Beijing Univ Tradit Chin Med"},{"key":"973_CR23","unstructured":"Team RC. R: A Language and Environment for Statistical Computing. 2022."},{"key":"973_CR24","unstructured":"Choi K, Joo D, Kim J. Kapre: On-GPU Audio Preprocessing Layers for a Quick Implementation of Deep Neural Network Models with Keras, in Machine Learning for Music Discovery Workshop at 34th International Conference on Machine Learning. 2017."},{"key":"973_CR25","doi-asserted-by":"crossref","unstructured":"McFee B, Raffel C, Liang D, Ellis DP, McVicar M, Battenberg E, et al. librosa: Audio and music signal analysis inpython. In: Proceedings of the 14th python in science conference. 2015.","DOI":"10.25080\/Majora-7b98e3ed-003"},{"issue":"1","key":"973_CR26","doi-asserted-by":"publisher","first-page":"22787","DOI":"10.1038\/s41598-023-49352-2","volume":"13","author":"B Tracey","year":"2023","unstructured":"Tracey B, et al. Towards interpretable speech biomarkers: exploring MFCCs. Sci Rep. 2023;13(1):22787.","journal-title":"Sci Rep"},{"key":"973_CR27","doi-asserted-by":"publisher","first-page":"4364186","DOI":"10.1155\/2022\/4364186","volume":"2022","author":"NS Alghamdi","year":"2022","unstructured":"Alghamdi NS, et al. Neurogenerative disease diagnosis in cepstral domain using MFCC with deep learning. Comput Math Methods Med. 2022;2022:4364186.","journal-title":"Comput Math Methods Med"},{"issue":"4","key":"973_CR28","doi-asserted-by":"publisher","first-page":"363","DOI":"10.3233\/THC-181306","volume":"27","author":"H Kuresan","year":"2019","unstructured":"Kuresan H, Samiappan D, Masunda S. Fusion of WPT and MFCC feature extraction in Parkinson\u2019s disease diagnosis. Technol Health Care. 2019;27(4):363\u201372.","journal-title":"Technol Health Care"},{"issue":"10","key":"973_CR29","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.1109\/TNSRE.2016.2533582","volume":"24","author":"A Benba","year":"2016","unstructured":"Benba A, Jilbab A, Hammouch A. Discriminating between patients with Parkinson\u2019s and neurological diseases using cepstral analysis. IEEE Trans Neural Syst Rehabil Eng. 2016;24(10):1100\u20138.","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"issue":"3","key":"973_CR30","doi-asserted-by":"publisher","first-page":"e0213659","DOI":"10.1371\/journal.pone.0213659","volume":"14","author":"RXA Pramono","year":"2019","unstructured":"Pramono RXA, Imtiaz SA, Rodriguez-Villegas E. Evaluation of features for classification of wheezes and normal respiratory sounds. PLoS ONE. 2019;14(3):e0213659.","journal-title":"PLoS ONE"},{"issue":"16","key":"973_CR31","doi-asserted-by":"publisher","first-page":"5555","DOI":"10.3390\/s21165555","volume":"21","author":"BT Balamurali","year":"2021","unstructured":"Balamurali BT, et al. Deep neural network-based respiratory pathology classification using cough sounds. Sensors. 2021;21(16):5555.","journal-title":"Sensors"},{"issue":"9","key":"973_CR32","doi-asserted-by":"publisher","first-page":"3172","DOI":"10.3390\/s21093172","volume":"21","author":"AT Purnomo","year":"2021","unstructured":"Purnomo AT, et al. Non-contact monitoring and classification of breathing pattern for the supervision of people infected by COVID-19. Sensors. 2021;21(9):3172.","journal-title":"Sensors"},{"key":"973_CR33","first-page":"197","volume":"8","author":"R Ranjan","year":"2019","unstructured":"Ranjan R, Thakur A. Analysis of feature extraction techniques for speech recognition system. Int J Innov Technol Explor Eng. 2019;8:197\u2013200.","journal-title":"Int J Innov Technol Explor Eng"},{"key":"973_CR34","unstructured":"Ittichaichareon C, Suksri S, Yingthawornsuk T. Speech recognition using MFCC. in International conference on computer graphics, simulation and modeling. 2012."},{"key":"973_CR35","doi-asserted-by":"crossref","unstructured":"Allamy S, Koerich AL. 1D CNN architectures for music genre classification. in 2021 IEEE symposium series on computational intelligence (SSCI). 2021. IEEE.","DOI":"10.1109\/SSCI50451.2021.9659979"}],"container-title":["Chinese Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13020-024-00973-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13020-024-00973-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13020-024-00973-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T02:11:27Z","timestamp":1721787087000},"score":1,"resource":{"primary":{"URL":"https:\/\/cmjournal.biomedcentral.com\/articles\/10.1186\/s13020-024-00973-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,24]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["973"],"URL":"https:\/\/doi.org\/10.1186\/s13020-024-00973-3","relation":{},"ISSN":["1749-8546"],"issn-type":[{"value":"1749-8546","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,24]]},"assertion":[{"value":"7 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2024","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 study was approved by Ethics Committee of Beijing University of Chinese Medicine (2023BZYLL1008). All participants signed the consent form before participating the study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All authors consent to publication of this study in <i>Chinese Medicine<\/i>.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"101"}}