{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T05:26:56Z","timestamp":1774934816237,"version":"3.50.1"},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T00:00:00Z","timestamp":1758931200000},"content-version":"am","delay-in-days":300,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100018833","name":"French Government Defense Innovation Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018833","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.fr","clinicalkey.jp","clinicalkey.es","clinicalkey.com.au","clinicalkey.com","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Methods and Programs in Biomedicine"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1016\/j.cmpb.2024.108439","type":"journal-article","created":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T16:28:43Z","timestamp":1727368123000},"page":"108439","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":7,"special_numbering":"C","title":["Paying attention to uncertainty: A stochastic multimodal transformers for post-traumatic stress disorder detection using video"],"prefix":"10.1016","volume":"257","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6332-7854","authenticated-orcid":false,"given":"Mamadou","family":"Dia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8078-8461","authenticated-orcid":false,"given":"Ghazaleh","family":"Khodabandelou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3442-0578","authenticated-orcid":false,"given":"Alice","family":"Othmani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.cmpb.2024.108439_b1","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.neuron.2007.09.006","article-title":"Response variation following trauma: A translational neuroscience approach to understanding PTSD","volume":"56","author":"Yehuda","year":"2007","journal-title":"Neuron"},{"key":"10.1016\/j.cmpb.2024.108439_b2","series-title":"What is Posttraumatic Stress Disorder (PTSD)?","author":"Taylor-Desir","year":"2022"},{"issue":"2","key":"10.1016\/j.cmpb.2024.108439_b3","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s10772-012-9175-z","article-title":"Characterization and recognition of emotions from speech using excitation source information","volume":"16","author":"Krothapalli","year":"2013","journal-title":"Int. J. Speech Technol."},{"issue":"1","key":"10.1016\/j.cmpb.2024.108439_b4","doi-asserted-by":"crossref","first-page":"195","DOI":"10.2466\/pr0.1990.66.1.195","article-title":"Why summaries of research on psychological theories are often uninterpretable","volume":"66","author":"Meehl","year":"1990","journal-title":"Psychol. Rep."},{"issue":"7553","key":"10.1016\/j.cmpb.2024.108439_b5","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"issue":"6","key":"10.1016\/j.cmpb.2024.108439_b6","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1111\/j.1469-8986.1979.tb01511.x","article-title":"A bio-informational theory of emotional imagery","volume":"16","author":"Lang","year":"1979","journal-title":"Psychophysiology"},{"issue":"11","key":"10.1016\/j.cmpb.2024.108439_b7","doi-asserted-by":"crossref","first-page":"1134","DOI":"10.1145\/1968.1972","article-title":"A theory of the learnable","volume":"27","author":"Valiant","year":"1984","journal-title":"Commun. ACM"},{"key":"10.1016\/j.cmpb.2024.108439_b8","series-title":"Review of pathological anxiety: Emotional processing in etiology and treatment","author":"Westra","year":"2007"},{"issue":"3","key":"10.1016\/j.cmpb.2024.108439_b9","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1214\/10-STS330","article-title":"To explain or to predict?","volume":"25","author":"Shmueli","year":"2010","journal-title":"Stat. Sci."},{"key":"10.1016\/j.cmpb.2024.108439_b10","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cmpb.2024.108439_b11","series-title":"Effective approaches to attention-based neural machine translation","author":"Luong","year":"2015"},{"key":"10.1016\/j.cmpb.2024.108439_b12","series-title":"Transformers with learnable activation functions","author":"Fang","year":"2022"},{"issue":"3","key":"10.1016\/j.cmpb.2024.108439_b13","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1177\/1524838009334448","article-title":"The epidemiology of trauma, PTSD, and other posttrauma disorders","volume":"10","author":"B.","year":"2009","journal-title":"Trauma Violence Abuse"},{"issue":"8","key":"10.1016\/j.cmpb.2024.108439_b14","doi-asserted-by":"crossref","first-page":"1041","DOI":"10.1016\/S0272-7358(99)00030-6","article-title":"Information processing and ptsd: A review of the empirical literature","volume":"20","author":"Buckley","year":"2000","journal-title":"Clin. Psychol. Rev."},{"issue":"2","key":"10.1016\/j.cmpb.2024.108439_b15","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1109\/TITB.2011.2107561","article-title":"Addressing mental health epidemic among university students via web-based, self-screening, and referral system: a preliminary study","volume":"15","author":"Kim","year":"2011","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"issue":"3","key":"10.1016\/j.cmpb.2024.108439_b16","doi-asserted-by":"crossref","first-page":"1693","DOI":"10.1007\/s10115-019-01337-2","article-title":"A deep transfer learning approach for improved post-traumatic stress disorder diagnosis","volume":"60","author":"Banerjee","year":"2019","journal-title":"Knowl. Inf. Syst."},{"key":"10.1016\/j.cmpb.2024.108439_b17","series-title":"PTSD in the wild: A video database for studying post-traumatic stress disorder recognition in unconstrained environments","author":"Sawadogo","year":"2022"},{"key":"10.1016\/j.cmpb.2024.108439_b18","series-title":"Machine Learning-based Approaches for Post-Traumatic Stress Disorder Diagnosis using Video and EEG Sensors: A Review","author":"Othmani","year":"2023"},{"key":"10.1016\/j.cmpb.2024.108439_b19","series-title":"Proceedings of Trends in Electronics and Health Informatics","first-page":"291","article-title":"An atypical approach toward PTSD diagnosis through speech-based emotion modeling using CNN-LSTM","author":"Josephine M. J.","year":"2022"},{"key":"10.1016\/j.cmpb.2024.108439_b20","series-title":"DEPA: Self-supervised audio embedding for depression detection","first-page":"135","author":"Zhang","year":"2021"},{"key":"10.1016\/j.cmpb.2024.108439_b21","series-title":"Autoencoder Based on Cepstrum Separation to Detect Depression from Speech","first-page":"508","author":"Zhang","year":"2021"},{"issue":"5","key":"10.1016\/j.cmpb.2024.108439_b22","doi-asserted-by":"crossref","first-page":"957","DOI":"10.1017\/S0033291720002718","article-title":"Deep learning-based classification of posttraumatic stress disorder and depression following trauma utilizing visual and auditory markers of arousal and mood","volume":"52","author":"Schultebraucks","year":"2022","journal-title":"Psychol. Med."},{"key":"10.1016\/j.cmpb.2024.108439_b23","doi-asserted-by":"crossref","DOI":"10.3389\/fpsyt.2021.811392","article-title":"Detecting presence of PTSD using sentiment analysis from text data","volume":"12","author":"Sawalha","year":"2022","journal-title":"Front. Psychiatry"},{"key":"10.1016\/j.cmpb.2024.108439_b24","series-title":"The Distress Analysis Interview Corpus of Human and Computer Interviews","author":"Gratch","year":"2014"},{"key":"10.1016\/j.cmpb.2024.108439_b25","doi-asserted-by":"crossref","unstructured":"H. Kaya, D. Fedotov, et al., Predicting depression and emotions in the cross-roads of cultures, para-linguistics, and non-linguistics, in: Proceedings of the 9th International on Audio\/Visual Emotion Challenge and Workshop, 2019, pp. 27\u201335.","DOI":"10.1145\/3347320.3357691"},{"issue":"3","key":"10.1016\/j.cmpb.2024.108439_b26","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1080\/24725579.2019.1583703","article-title":"Continuous monitoring and detection of post-traumatic stress disorder (PTSD) triggers among veterans: a supervised machine learning approach","volume":"9","author":"McDonald","year":"2019","journal-title":"IISE Trans. Healthc. Syst. Eng."},{"key":"10.1016\/j.cmpb.2024.108439_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.neuroimage.2021.118242","article-title":"Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors","volume":"238","author":"Sheynin","year":"2021","journal-title":"Neuroimage"},{"key":"10.1016\/j.cmpb.2024.108439_b28","doi-asserted-by":"crossref","unstructured":"M. Rodrigues Makiuchi, T. Warnita, K. Uto, K. Shinoda, Multimodal fusion of bert-cnn and gated cnn representations for depression detection, in: Proceedings of the 9th International on Audio\/Visual Emotion Challenge and Workshop, 2019, pp. 55\u201363.","DOI":"10.1145\/3347320.3357694"},{"issue":"2","key":"10.1016\/j.cmpb.2024.108439_b29","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1177\/1073191115602551","article-title":"Automated assessment of patients\u2019 self-narratives for posttraumatic stress disorder screening using natural language processing and text mining","volume":"24","author":"He","year":"2017","journal-title":"Assessment"},{"key":"10.1016\/j.cmpb.2024.108439_b30","series-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"10.1016\/j.cmpb.2024.108439_b31","article-title":"Compete to compute","author":"Srivastava","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cmpb.2024.108439_b32","article-title":"Winner-take-all autoencoders","volume":"28","author":"Makhzani","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cmpb.2024.108439_b33","doi-asserted-by":"crossref","first-page":"24","DOI":"10.3389\/fncom.2018.00024","article-title":"Unsupervised feature learning with winner-takes-all based stdp","volume":"12","author":"Ferr\u00e9","year":"2018","journal-title":"Front. Comput. Neurosci."},{"key":"10.1016\/j.cmpb.2024.108439_b34","series-title":"European Conference on Computer Vision","first-page":"646","article-title":"Deep networks with stochastic depth","author":"Huang","year":"2016"},{"key":"10.1016\/j.cmpb.2024.108439_b35","series-title":"Wide residual networks","author":"Zagoruyko","year":"2016"},{"key":"10.1016\/j.cmpb.2024.108439_b36","first-page":"15475","article-title":"ResT: An efficient transformer for visual recognition","volume":"34","author":"Zhang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cmpb.2024.108439_b37","series-title":"Locally-connected and convolutional neural networks for small footprint speaker recognition","author":"Chen","year":"2015"},{"key":"10.1016\/j.cmpb.2024.108439_b38","article-title":"Understanding dropout","volume":"26","author":"Baldi","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cmpb.2024.108439_b39","series-title":"Bam: Bottleneck attention module","author":"Park","year":"2018"},{"key":"10.1016\/j.cmpb.2024.108439_b40","series-title":"Sixteenth Annual Conference of the International Speech Communication Association","article-title":"Speech-based assessment of PTSD in a military population using diverse feature classes","author":"Vergyri","year":"2015"},{"key":"10.1016\/j.cmpb.2024.108439_b41","doi-asserted-by":"crossref","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":"10.1016\/j.cmpb.2024.108439_b42","series-title":"2013 3rd IEEE International Advance Computing Conference","first-page":"842","article-title":"Emotion recognition in speech using MFCC and wavelet features","author":"Kishore","year":"2013"},{"issue":"11","key":"10.1016\/j.cmpb.2024.108439_b43","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevD.103.116023","article-title":"Deep learning stochastic processes with QCD phase transition","volume":"103","author":"Jiang","year":"2021","journal-title":"Phys. Rev. D"},{"key":"10.1016\/j.cmpb.2024.108439_b44","doi-asserted-by":"crossref","first-page":"1067","DOI":"10.1007\/s00371-019-01707-5","article-title":"A comprehensive survey on automatic facial action unit analysis","volume":"36","author":"Zhi","year":"2020","journal-title":"Vis. Comput."},{"key":"10.1016\/j.cmpb.2024.108439_b45","series-title":"Encyclopedia of Operations Research and Management Science","article-title":"Wardrop equilibria","author":"Correa","year":"2011"},{"key":"10.1016\/j.cmpb.2024.108439_b46","series-title":"Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VI 13","first-page":"253","article-title":"Efficient image and video co-localization with frank-wolfe algorithm","author":"Joulin","year":"2014"},{"key":"10.1016\/j.cmpb.2024.108439_b47","series-title":"Frame-level prediction of facial expressions, valence, arousal and action units for mobile devices","author":"Savchenko","year":"2022"},{"key":"10.1016\/j.cmpb.2024.108439_b48","doi-asserted-by":"crossref","unstructured":"F. Ringeval, B. Schuller, M. Valstar, N. Cummins, R. Cowie, L. Tavabi, M. Schmitt, S. Alisamir, S. Amiriparian, E.-M. Messner, et al., AVEC 2019 workshop and challenge: state-of-mind, detecting depression with AI, and cross-cultural affect recognition, in: Proceedings of the 9th International on Audio\/Visual Emotion Challenge and Workshop, 2019, pp. 3\u201312.","DOI":"10.1145\/3347320.3357688"},{"key":"10.1016\/j.cmpb.2024.108439_b49","series-title":"Release strategies and the social impacts of language models","author":"Solaiman","year":"2019"},{"key":"10.1016\/j.cmpb.2024.108439_b50","series-title":"Temporal attention model for neural machine translation","author":"Sankaran","year":"2016"},{"key":"10.1016\/j.cmpb.2024.108439_b51","series-title":"Dual-signal transformation lstm network for real-time noise suppression","author":"Westhausen","year":"2020"},{"issue":"1\u20136","key":"10.1016\/j.cmpb.2024.108439_b52","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1007\/BF01759054","article-title":"Stochastic neural networks","volume":"6","author":"Wong","year":"1991","journal-title":"Algorithmica"},{"key":"10.1016\/j.cmpb.2024.108439_b53","series-title":"2023 IEEE 36th International Symposium on Computer-Based Medical Systems","first-page":"700","article-title":"A novel stochastic transformer-based approach for post-traumatic stress disorder detection using audio recording of clinical interviews","author":"Dia","year":"2023"},{"key":"10.1016\/j.cmpb.2024.108439_b54","doi-asserted-by":"crossref","unstructured":"S. Chen, D. Wang, Y. Huang, Exploring the complementary features of audio and text notes for video-based learning in mobile settings, in: Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, 2021, pp. 1\u20137.","DOI":"10.1145\/3411763.3451801"},{"key":"10.1016\/j.cmpb.2024.108439_b55","series-title":"Model compression via distillation and quantization","author":"Polino","year":"2018"},{"issue":"1","key":"10.1016\/j.cmpb.2024.108439_b56","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41746-020-00323-1","article-title":"The future of digital health with federated learning","volume":"3","author":"Rieke","year":"2020","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.cmpb.2024.108439_b57","series-title":"2021 IEEE International Conference on Image Processing","first-page":"2339","article-title":"Towards a general deep feature extractor for facial expression recognition","author":"Schoneveld","year":"2021"}],"container-title":["Computer Methods and Programs in Biomedicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0169260724004322?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0169260724004322?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T02:28:44Z","timestamp":1740796124000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0169260724004322"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":57,"alternative-id":["S0169260724004322"],"URL":"https:\/\/doi.org\/10.1016\/j.cmpb.2024.108439","relation":{},"ISSN":["0169-2607"],"issn-type":[{"value":"0169-2607","type":"print"}],"subject":[],"published":{"date-parts":[[2024,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Paying attention to uncertainty: A stochastic multimodal transformers for post-traumatic stress disorder detection using video","name":"articletitle","label":"Article Title"},{"value":"Computer Methods and Programs in Biomedicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cmpb.2024.108439","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108439"}}