{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T01:36:02Z","timestamp":1777512962080,"version":"3.51.4"},"reference-count":62,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T00:00:00Z","timestamp":1721088000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"King\u2019s College London\u2014China Scholarship Council","award":["202208310042"],"award-info":[{"award-number":["202208310042"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>This study aims to conduct a systematic review and meta-analysis of the diagnostic accuracy of deep learning (DL) using speech samples in depression.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>This review included studies reporting diagnostic results of DL algorithms in depression using speech data, published from inception to January 31, 2024, on PubMed, Medline, Embase, PsycINFO, Scopus, IEEE, and Web of Science databases. Pooled accuracy, sensitivity, and specificity were obtained by random-effect models. The diagnostic Precision Study Quality Assessment Tool (QUADAS-2) was used to assess the risk of bias.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>A total of 25 studies met the inclusion criteria and 8 of them were used in the meta-analysis. The pooled estimates of accuracy, specificity, and sensitivity for depression detection models were 0.87 (95% CI, 0.81-0.93), 0.85 (95% CI, 0.78-0.91), and 0.82 (95% CI, 0.71-0.94), respectively. When stratified by model structure, the highest pooled diagnostic accuracy was 0.89 (95% CI, 0.81-0.97) in the handcrafted group.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>To our knowledge, our study is the first meta-analysis on the diagnostic performance of DL for depression detection from speech samples. All studies included in the meta-analysis used convolutional neural network (CNN) models, posing problems in deciphering the performance of other DL algorithms. The handcrafted model performed better than the end-to-end model in speech depression detection.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>The application of DL in speech provided a useful tool for depression detection. CNN models with handcrafted acoustic features could help to improve the diagnostic performance.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Protocol registration<\/jats:title>\n                  <jats:p>The study protocol was registered on PROSPERO (CRD42023423603).<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocae189","type":"journal-article","created":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T22:04:20Z","timestamp":1721167460000},"page":"2394-2404","source":"Crossref","is-referenced-by-count":27,"title":["Diagnostic accuracy of deep learning using speech samples in depression: a systematic review and meta-analysis"],"prefix":"10.1093","volume":"31","author":[{"given":"Lidan","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Population Health Sciences, School of Life Course and Population Sciences, Faculty of Life Sciences & Medicine, King's College London , London, SE1 1UL, United Kingdom"}]},{"given":"Lu","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences, School of Life Course and Population Sciences, Faculty of Life Sciences & Medicine, King's College London , London, SE1 1UL, United Kingdom"}]},{"given":"Hatem A","family":"Wafa","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences, School of Life Course and Population Sciences, Faculty of Life Sciences & Medicine, King's College London , London, SE1 1UL, United Kingdom"}]},{"given":"Florence","family":"Tydeman","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences, School of Life Course and Population Sciences, Faculty of Life Sciences & Medicine, King's College London , London, SE1 1UL, United Kingdom"}]},{"given":"Wanqing","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Intelligent Medical Engineering, School of Biomedical Engineering, Anhui Medical University , Hefei, 230032, China"},{"name":"Department of Psychology, School of Mental Health and Psychological Sciences, Anhui Medical University , Hefei, 230032, China"},{"name":"Beth Israel Deaconess Medical Center, Harvard Medical School, Harvard University , Boston, MA, 02115, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0768-1676","authenticated-orcid":false,"given":"Yanzhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences, School of Life Course and Population Sciences, Faculty of Life Sciences & Medicine, King's College London , London, SE1 1UL, United Kingdom"}]}],"member":"286","published-online":{"date-parts":[[2024,7,16]]},"reference":[{"issue":"Suppl 13","key":"2024092007531987400_ocae189-B1","first-page":"4","article-title":"Epidemiology, burden, and disability in depression and anxiety","volume":"62","author":"Lepine","year":"2001","journal-title":"J Clin Psychiatry"},{"key":"2024092007531987400_ocae189-B2","author":"World Health Organization","year":"2023"},{"issue":"Suppl 8","key":"2024092007531987400_ocae189-B3","first-page":"4","article-title":"The burden of depression and anxiety in general medicine","volume":"62","author":"Lecrubier","year":"2021","journal-title":"J Clin Psychiatry"},{"issue":"3","key":"2024092007531987400_ocae189-B4","first-page":"36","article-title":"Diagnostic and statistical manual of mental disorders: DSM-5","volume":"28","author":"Guha","year":"2014","journal-title":"Ref Rev"},{"issue":"1","key":"2024092007531987400_ocae189-B5","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1002\/lio2.354","article-title":"Automated assessment of psychiatric disorders using speech: a systematic review","volume":"5","author":"Low","year":"2020","journal-title":"Laryngoscope Investig Otolaryngol"},{"issue":"4","key":"2024092007531987400_ocae189-B6","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1007\/s00138-020-01080-7","article-title":"Automated facial video-based recognition of depression and anxiety symptom severity: cross-corpus validation","volume":"31","author":"Pampouchidou","year":"2020","journal-title":"Mach Vis Appl"},{"issue":"1","key":"2024092007531987400_ocae189-B7","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.bbe.2021.12.005","article-title":"Automated diagnosis of depression from EEG signals using traditional and deep learning approaches: a comparative analysis","volume":"42","author":"Khosla","year":"2022","journal-title":"Biocybern Biomed Eng"},{"issue":"4","key":"2024092007531987400_ocae189-B8","first-page":"227","article-title":"Comorbidity of depressive and anxiety disorders: challenges in diagnosis and assessment","volume":"26","author":"Wu","year":"2014","journal-title":"Shanghai Arch Psychiatry"},{"issue":"2","key":"2024092007531987400_ocae189-B9","doi-asserted-by":"crossref","first-page":"152","DOI":"10.2174\/1871527320666211213125847","article-title":"Speech as a biomarker for depression","volume":"22","author":"Koops","year":"2023","journal-title":"CNS Neurol Disord Drug Targets"},{"issue":"11","key":"2024092007531987400_ocae189-B10","doi-asserted-by":"crossref","first-page":"e00938","DOI":"10.1016\/j.heliyon.2018.e00938","article-title":"State-of-the-art in artificial neural network applications: a survey","volume":"4","author":"Abiodun","year":"2018","journal-title":"Heliyon"},{"key":"2024092007531987400_ocae189-B11","doi-asserted-by":"crossref","first-page":"101869","DOI":"10.1016\/j.inffus.2023.101869","article-title":"A review of deep learning techniques for speech processing","volume":"99","author":"Mehrish","year":"2023","journal-title":"Inf Fusion"},{"key":"2024092007531987400_ocae189-B12","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.ymeth.2018.07.007","article-title":"Speech analysis for health: Current state-of-the-art and the increasing impact of deep learning","volume":"151","author":"Cummins","year":"2018","journal-title":"Methods"},{"issue":"3","key":"2024092007531987400_ocae189-B13","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1049\/cit2.12113","article-title":"Automatic depression recognition by intelligent speech signal processing: a systematic survey","volume":"8","author":"Wu","year":"2022","journal-title":"CAAI Trans Intel Tech"},{"key":"2024092007531987400_ocae189-B14","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 Commun"},{"issue":"8284","key":"2024092007531987400_ocae189-B15","doi-asserted-by":"crossref","first-page":"n71","DOI":"10.1136\/bmj.n71","article-title":"The PRISMA 2020 statement: an updated guideline for reporting systematic reviews","volume":"372","author":"Page","year":"2021","journal-title":"BMJ"},{"issue":"4","key":"2024092007531987400_ocae189-B16","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1001\/jama.2017.19163","article-title":"Preferred reporting items for a systematic review and meta-analysis of diagnostic test accuracy studies: the PRISMA-DTA statement","volume":"319","author":"McInnes","year":"2018","journal-title":"JAMA"},{"key":"2024092007531987400_ocae189-B17","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1002\/9780470712184.ch4","article-title":"Guide to the contents of a cochrane protocol and review","author":"Higgins","year":"2008","journal-title":"Cochrane Handbook for Systematic Reviews of Interventions"},{"issue":"3","key":"2024092007531987400_ocae189-B18","first-page":"40","article-title":"meta: an R package for meta-analysis","volume":"7","author":"Schwarzer","year":"2007","journal-title":"R News"},{"issue":"14","key":"2024092007531987400_ocae189-B19","doi-asserted-by":"crossref","first-page":"1293","DOI":"10.1002\/sim.4780121403","article-title":"Combining independent studies of a diagnostic test into a summary ROC curve: data-analytic approaches and some additional considerations","volume":"12","author":"Moses","year":"1993","journal-title":"Stat Med"},{"issue":"8","key":"2024092007531987400_ocae189-B20","doi-asserted-by":"crossref","first-page":"529","DOI":"10.7326\/0003-4819-155-8-201110180-00009","article-title":"QUADAS-2: A revised tool for the quality assessment of diagnostic accuracy studies","volume":"155","author":"Whiting","year":"2011","journal-title":"Ann Intern Med"},{"key":"2024092007531987400_ocae189-B21","first-page":"3123","author":"Gratch","year":"; 2014"},{"key":"2024092007531987400_ocae189-B22","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1016\/j.procs.2019.12.228","article-title":"Automated speech-based screening of depression using deep convolutional neural networks","volume":"164","author":"Chlasta","year":"2019","journal-title":"Procedia Comput Sci"},{"key":"2024092007531987400_ocae189-B23","first-page":"229","author":"Saidi","year":"2020"},{"key":"2024092007531987400_ocae189-B24","first-page":"5","author":"Othmani","year":"2021"},{"key":"2024092007531987400_ocae189-B25","doi-asserted-by":"crossref","first-page":"103107","DOI":"10.1016\/j.bspc.2021.103107","article-title":"MFCC-based recurrent neural network for automatic clinical depression recognition and assessment from speech","volume":"71","author":"Rejaibi","year":"2022","journal-title":"Biomed Signal Process Control"},{"key":"2024092007531987400_ocae189-B26","first-page":"1","author":"Homsiang","year":"2022"},{"key":"2024092007531987400_ocae189-B27","doi-asserted-by":"crossref","first-page":"116076","DOI":"10.1016\/j.eswa.2021.116076","article-title":"Audio based depression detection using convolutional autoencoder","volume":"189","author":"Sardari","year":"2022","journal-title":"Expert Syst Appl"},{"key":"2024092007531987400_ocae189-B28","doi-asserted-by":"crossref","first-page":"3338","DOI":"10.21437\/Interspeech.2022-10798","article-title":"A step towards preserving speakers\u2019 identity while detecting depression via speaker disentanglement","volume":"2022","author":"Ravi","year":"2022","journal-title":"Interspeech"},{"key":"2024092007531987400_ocae189-B29","first-page":"1371","author":"Cui","year":"2022"},{"issue":"5","key":"2024092007531987400_ocae189-B30","doi-asserted-by":"crossref","first-page":"2797","DOI":"10.1109\/TCSS.2022.3202294","article-title":"Hierarchical multifeature fusion via audio-response-level modeling for depression detection","volume":"10","author":"Zhou","year":"2023","journal-title":"IEEE Trans Comput Soc Syst"},{"issue":"2","key":"2024092007531987400_ocae189-B31","doi-asserted-by":"crossref","first-page":"328","DOI":"10.3390\/electronics12020328","article-title":"Depression detection in speech using transformer and parallel convolutional neural networks","volume":"12","author":"Yin","year":"2023","journal-title":"Electronics"},{"key":"2024092007531987400_ocae189-B32","first-page":"1","article-title":"Deep learning for depression recognition from speech","volume":"28","author":"Tian","year":"2023","journal-title":"Mobile Netw Appl"},{"key":"2024092007531987400_ocae189-B33","first-page":"1","author":"Feng","year":"2023"},{"issue":"2","key":"2024092007531987400_ocae189-B34","doi-asserted-by":"crossref","first-page":"1588","DOI":"10.3390\/ijerph20021588","article-title":"Classification of depression and its severity based on multiple audio features using a graphical convolutional neural network","volume":"20","author":"Ishimaru","year":"2023","journal-title":"Int J Environ Res Public Health"},{"key":"2024092007531987400_ocae189-B35","first-page":"100587","article-title":"A hybrid model for depression detection using deep learning","volume":"25","author":"Vandana","year":"2023","journal-title":"Meas: Sensors"},{"key":"2024092007531987400_ocae189-B36","first-page":"1","author":"B","year":"2023"},{"key":"2024092007531987400_ocae189-B37","doi-asserted-by":"crossref","first-page":"101605","DOI":"10.1016\/j.csl.2023.101605","article-title":"Enhancing accuracy and privacy in speech-based depression detection through speaker disentanglement","volume":"86","author":"Ravi","year":"2024","journal-title":"Comput Speech Lang"},{"key":"2024092007531987400_ocae189-B38","doi-asserted-by":"crossref","first-page":"66135","DOI":"10.1007\/s11042-023-18076-w","article-title":"Depression detection using cascaded attention based deep learning framework using speech data","author":"Gupta","year":"2024","journal-title":"Multimedia Tools Appl"},{"issue":"2","key":"2024092007531987400_ocae189-B39","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1007\/s10015-023-00852-4","article-title":"Smart voice recognition based on deep learning for depression diagnosis","volume":"28","author":"Suparatpinyo","year":"2023","journal-title":"Artif Life Robot"},{"key":"2024092007531987400_ocae189-B40","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.neunet.2023.05.041","article-title":"Attention guided learnable time-domain filterbanks for speech depression detection","volume":"165","author":"Yang","year":"2023","journal-title":"Neural Netw"},{"key":"2024092007531987400_ocae189-B41","first-page":"101","author":"Jenei","year":"2020"},{"issue":"3","key":"2024092007531987400_ocae189-B42","doi-asserted-by":"crossref","first-page":"227","DOI":"10.3311\/PPee.15958","article-title":"Severity estimation of depression using convolutional neural network","volume":"65","author":"Jenei","year":"2021","journal-title":"Periodica Polytechnica Electr Eng Comput Sci"},{"key":"2024092007531987400_ocae189-B43","first-page":"3896","author":"Wang","year":"2022"},{"key":"2024092007531987400_ocae189-B44","first-page":"162","author":"Wang","year":"2022"},{"key":"2024092007531987400_ocae189-B45","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/j.jad.2022.11.060","article-title":"Depression recognition using a proposed speech chain model fusing speech production and perception features","volume":"323","author":"Du","year":"2023","journal-title":"J Affect Disord"},{"key":"2024092007531987400_ocae189-B46","doi-asserted-by":"crossref","first-page":"105898","DOI":"10.1016\/j.bspc.2023.105898","article-title":"A deep learning model for depression detection based on MFCC and CNN generated spectrogram features","volume":"90","author":"Das","year":"2024","journal-title":"Biomed Signal Process Control"},{"key":"2024092007531987400_ocae189-B47","first-page":"3","author":"Valstar","year":"2016"},{"issue":"1","key":"2024092007531987400_ocae189-B48","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1038\/s41597-022-01211-x","article-title":"A multi-modal open dataset for mental-disorder analysis","volume":"9","author":"Cai","year":"2022","journal-title":"Sci Data"},{"key":"2024092007531987400_ocae189-B49","first-page":"6549","author":"Huang","year":"2020"},{"issue":"1-3","key":"2024092007531987400_ocae189-B50","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/j.jad.2008.06.026","article-title":"The PHQ-8 as a measure of current depression in the general population","volume":"114","author":"Kroenke","year":"2009","journal-title":"J Affect Disord"},{"issue":"1","key":"2024092007531987400_ocae189-B51","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1136\/jnnp.23.1.56","article-title":"A rating scale for depression","volume":"23","author":"Hamilton","year":"1960","journal-title":"J Neurol Neurosurg Psychiatry"},{"issue":"3","key":"2024092007531987400_ocae189-B52","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1207\/s15327752jpa6703_13","article-title":"Comparison of beck depression inventories-IA and-II in psychiatric outpatients","volume":"67","author":"Beck","year":"1996","journal-title":"J Pers Assess"},{"issue":"9","key":"2024092007531987400_ocae189-B53","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1046\/j.1525-1497.2001.016009606.x","article-title":"The PHQ-9","volume":"16","author":"Kroenke","year":"2001","journal-title":"J Gen Intern Med"},{"issue":"1","key":"2024092007531987400_ocae189-B54","first-page":"186","article-title":"Preprocessing technique in automatic speech recognition for human computer interaction: an overview","volume":"15","author":"Ibrahim","year":"2017","journal-title":"Ann Comput Sci Ser"},{"key":"2024092007531987400_ocae189-B55","first-page":"743","author":"Liu","year":"2015"},{"key":"2024092007531987400_ocae189-B56","doi-asserted-by":"crossref","first-page":"105020","DOI":"10.1016\/j.bspc.2023.105020","article-title":"Bio-acoustic features of depression: a review","volume":"85","author":"Almaghrabi","year":"2023","journal-title":"Biomed Signal Process Control"},{"key":"2024092007531987400_ocae189-B57","doi-asserted-by":"publisher","first-page":"815678","DOI":"10.3389\/fpsyt.2022.815678","article-title":"Vocal acoustic features as potential biomarkers for identifying\/diagnosing depression: a cross-sectional study","volume":"13","author":"Zhao","year":"2022","journal-title":"Front Psychiatry"},{"issue":"5","key":"2024092007531987400_ocae189-B58","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1080\/03007995.2022.2038487","article-title":"An insight into diagnosis of depression using machine learning techniques: a systematic review","volume":"38","author":"Bhadra","year":"2022","journal-title":"Curr Med Res Opin"},{"issue":"3","key":"2024092007531987400_ocae189-B59","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1037\/a0036048","article-title":"Evidence for cultural dialects in vocal emotion expression: acoustic classification within and across five nations","volume":"14","author":"Laukka","year":"2014","journal-title":"Emotion"},{"key":"2024092007531987400_ocae189-B60","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1007\/978-3-319-28109-4_11","article-title":"Language independent detection possibilities of depression by speech","volume":"48","author":"Kiss","year":"2016","journal-title":"Recent Adv Nonlinear Speech Process"},{"key":"2024092007531987400_ocae189-B61","volume-title":"Nat Commun","author":"Albouy"},{"issue":"2","key":"2024092007531987400_ocae189-B62","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1007\/s00406-018-0974-3","article-title":"Smartphone applications for depression: a systematic literature review and a survey of health care professionals\u2019 attitudes towards their use in clinical practice","volume":"270","author":"Kerst","year":"2020","journal-title":"European Arch Psychiatry Clin Neurosci"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/10\/2394\/59206370\/ocae189.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/10\/2394\/59206370\/ocae189.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T07:54:09Z","timestamp":1726818849000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/31\/10\/2394\/7715014"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,16]]},"references-count":62,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,7,16]]},"published-print":{"date-parts":[[2024,10,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocae189","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,10]]},"published":{"date-parts":[[2024,7,16]]}}}