{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T04:13:45Z","timestamp":1788149625149,"version":"build-2803163510"},"reference-count":35,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T00:00:00Z","timestamp":1788048000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Multimodal behavioral sensing may support depression screening, but evaluation on small clinical-interview datasets is particularly vulnerable to data leakage and model-selection bias. We present a leakage-audited trimodal framework evaluated on DAIC-WOZ (n=180, PHQ-8 \u226510), combining SBERT text embeddings, OpenFace facial-behavior descriptors, and COVAREP prosodic features. Participant-level partitioning is performed before augmentation, while decision thresholds and neural-model checkpoints are selected exclusively from internal validation data. A controlled five-seed experiment showed that a deliberately leaky full-pool MixUp construction, in which a retained development sample could include a held-out participant as its second parent, was associated with a 27\u201333 percentage-point increase in Macro-F1 across four fusion configurations. Under the participant-level leakage-free 5-fold protocol, trimodal late fusion achieved a Macro-F1 of 0.532\u00b10.041, compared with 0.446\u00b10.021 for Text+Imaging late fusion. Paired participant-level correctness outcomes also favored trimodal fusion (McNemar \u03c72=6.618, p=0.010), consistent with improved paired classification when the audio modality was included under the leakage-free protocol. On 86 participant-disjoint E-DAIC sessions, using a consistent PHQ-8-based outcome definition (PHQ-8 \u226510), trimodal late fusion achieved Macro-F1 = 0.621 and AUC = 0.676; this experiment is interpreted as within-family generalization rather than independent cross-corpus validation. Overall, the results show that leakage control can substantially alter both absolute performance and comparative conclusions, and that multimodal gains should be established through participant-level evaluation, modality-specific analysis, and reproducible model-selection procedures.<\/jats:p>","DOI":"10.3390\/bioengineering13091009","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T02:08:58Z","timestamp":1788142138000},"page":"1009","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Leakage-Free Multimodal Depression Screening: Controlled Evaluation of Text, Facial Behavior, and Prosodic Fusion"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4733-197X","authenticated-orcid":false,"given":"Souaad","family":"Hamza-Cherif","sequence":"first","affiliation":[{"name":"Biomedical Engineering Laboratory, University of Tlemcen, Tlemcen 13000, Algeria"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0460-9713","authenticated-orcid":false,"given":"Nesma","family":"Settouti","sequence":"additional","affiliation":[{"name":"LabISEN, LSL, ISEN Ouest, 14000 Caen, France"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,30]]},"reference":[{"key":"ref_1","unstructured":"World Health Organization (2026, May 01). Depressive Disorder (Depression). Fact Sheet, 29 August 2025. Available online: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/depression."},{"key":"ref_2","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."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Gratch, J., Artstein, R., Lucas, G., Stratou, G., Scherer, S., Nazarian, A., Wood, R., Boberg, J., DeVault, D., and Marsella, S. (2014). The Distress Analysis Interview Corpus of Human and Computer Interviews. Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914), Reykjavik, Iceland, 26\u201331 May 2014, European Language Resources Association (ELRA).","DOI":"10.63317\/3o7bccg9xequ"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Danylenko, I., and Unold, O. (2026). Common Pitfalls and Recommendations for Use of Machine Learning in Depression Severity Estimation: DAIC-WOZ Study. Appl. Sci., 16.","DOI":"10.31234\/osf.io\/enrbq_v1"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1007\/978-3-319-44564-9_3","article-title":"A Test Collection for Research on Depression and Language Use","volume":"Volume 9822","author":"Losada","year":"2016","journal-title":"Experimental IR Meets Multilinguality, Multimodality, and Interaction"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1017\/S1351324916000383","article-title":"Natural Language Processing in Mental Health Applications Using Non-Clinical Texts","volume":"23","author":"Calvo","year":"2017","journal-title":"Nat. Lang. Eng."},{"key":"ref_7","unstructured":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), Volume 1, Minneapolis, MN, USA, 2\u20137 June 2019, Association for Computational Linguistics."},{"key":"ref_8","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv."},{"key":"ref_9","unstructured":"Huang, K., Altosaar, J., and Ranganath, R. (2019). ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ji, S., Zhang, T., Ansari, L., Fu, J., Tiwari, P., and Cambria, E. (2022). MentalBERT: Publicly Available Pretrained Language Models for Mental Healthcare. Proceedings of the Thirteenth Language Resources and Evaluation Conference (LREC 2022), Marseille, France, 20\u201325 June 2022, European Language Resources Association (ELRA).","DOI":"10.63317\/2d7umxifj8wz"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Teferra, B.G., Perivolaris, A., Hsiang, W.-N., Sidharta, C.K., Rueda, A., Parkington, K., Wu, Y., Soni, A., Samavi, R., and Jetly, R. (2025). Leveraging Large Language Models for Automated Depression Screening. PLoS Digit. Health, 4.","DOI":"10.1371\/journal.pdig.0000943"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Lee, J.-J., Han, J., and Woo, C.-W. (2026). Interpretable Depression Assessment Using a Large Language Model. PLoS Digit. Health, 5.","DOI":"10.1371\/journal.pdig.0001205"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1476","DOI":"10.1109\/TMM.2018.2877129","article-title":"Automatic Depression Analysis Using Dynamic Facial Appearance Descriptor and Dirichlet Process Fisher Encoding","volume":"21","author":"He","year":"2019","journal-title":"IEEE Trans. Multimed."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Baltru\u0161aitis, T., Zadeh, A., Lim, Y.C., and Morency, L.-P. (2018). OpenFace 2.0: Facial Behavior Analysis Toolkit. Proceedings of the 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), Xi\u2019an, China, 15\u201319 May 2018, IEEE.","DOI":"10.1109\/FG.2018.00019"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Flores, R., Tlachac, M.L., Shrestha, A., and Rundensteiner, E.A. (2022). Temporal Facial Features for Depression Screening. Adjunct Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2022 ACM International Symposium on Wearable Computers (UbiComp\/ISWC \u201922 Adjunct), Association for Computing Machinery.","DOI":"10.1145\/3544793.3563424"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Degottex, G., Kane, J., Drugman, T., Raitio, T., and Scherer, S. (2014). COVAREP\u2014A Collaborative Voice Analysis Repository for Speech Technologies. Proceedings of the 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, 4\u20139 May 2014, IEEE.","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Williamson, J.R., Quatieri, T.F., Helfer, B.S., Ciccarelli, G.A., and Mehta, D.D. (2014). Vocal and Facial Biomarkers of Depression Based on Motor Incoordination and Timing. Proceedings of the 4th International Workshop on Audio\/Visual Emotion Challenge (AVEC \u201914), Orlando, FL, USA, 7 November 2014, Association for Computing Machinery.","DOI":"10.1145\/2661806.2661809"},{"key":"ref_18","unstructured":"Ioannides, G., Kieback, A., Chadha, A., and Elkins, A. (2024). Density Adaptive Attention-Based Speech Network: Enhancing Feature Understanding for Mental Health Disorders. arXiv."},{"key":"ref_19","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":"Sci. Rep."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal Machine Learning: A Survey and Taxonomy","volume":"41","author":"Ahuja","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Al Hanai, T., Ghassemi, M.M., and Glass, J.R. (2018, January 2\u20136). Detecting Depression with Audio\/Text Sequence Modeling of Interviews. Proceedings of the Interspeech 2018, Hyderabad, India.","DOI":"10.21437\/Interspeech.2018-2522"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, S., Ni, D., Wei, Z., Yang, K., Jin, S., Huang, G., Liang, Z., Zhang, L., and Li, L. (2024). Multimodal Sensing for Depression Risk Detection: Integrating Audio, Video, and Text Data. Sensors, 24.","DOI":"10.3390\/s24123714"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Nykoniuk, M., Basystiuk, O., Shakhovska, N., and Melnykova, N. (2025). Multimodal Data Fusion for Depression Detection Approach. Computation, 13.","DOI":"10.3390\/computation13010009"},{"key":"ref_24","unstructured":"Ishikawa, T., and Duke, J. (2026). A Multi-Probe Audit of Clinical-Interview Depression Detection Benchmarks. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Burdisso, S.G., Reyes-Ram\u00edrez, E., Villatoro-Tello, E., S\u00e1nchez-Vega, F., Lopez Monroy, A., and Motlicek, P. (2024). DAIC-WOZ: On the Validity of Using the Therapist\u2019s Prompts in Automatic Depression Detection from Clinical Interviews. Proceedings of the 6th Clinical Natural Language Processing Workshop, Mexico City, Mexico, 21 June 2024, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.clinicalnlp-1.8"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Trelles, A., Fontaines Ruiz, T., and Ponce Rojo, A. (2025). Systematic Review and Meta-Analysis of Explainable Machine Learning Models for Clinical Depression Detection. Behav. Sci., 15.","DOI":"10.3390\/bs15111476"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1007\/978-3-032-07956-5_12","article-title":"Investigation of Explainable Multimodal Methods for Detecting Mental Disorders","volume":"Volume 16187","author":"Dolgushin","year":"2026","journal-title":"Speech and Computer: 27th International Conference, SPECOM 2025"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1038\/s44184-024-00112-8","article-title":"Harnessing Multimodal Approaches for Depression Detection Using Large Language Models and Facial Expressions","volume":"3","author":"Sadeghi","year":"2024","journal-title":"npj Ment. Health Res."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Ringeval, F., Schuller, B., Valstar, M., Cummins, N., Cowie, R., Tavabi, L., Schmitt, M., Alisamir, S., Amiriparian, S., and Messner, E.-M. (2019). AVEC 2019 Workshop and Challenge: State-of-Mind, Detecting Depression with AI, and Cross-Cultural Affect Recognition. Proceedings of the 9th International Audio\/Visual Emotion Challenge and Workshop (AVEC \u201919), Nice, France, 21 October 2019, Association for Computing Machinery.","DOI":"10.1145\/3347320.3357688"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Reimers, N., and Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings Using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, 3\u20137 November 2019, Association for Computational Linguistics.","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref_31","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., and Lopez-Paz, D. (May, January 30). mixup: Beyond Empirical Risk Minimization. Proceedings of the 6th International Conference on Learning Representations (ICLR 2018), Vancouver, BC, Canada. Available online: https:\/\/openreview.net\/forum?id=r1Ddp1-Rb."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD \u201916), San Francisco, CA, USA, 13\u201317 August 2016, Association for Computing Machinery.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_33","first-page":"3146","article-title":"LightGBM: A Highly Efficient Gradient Boosting Decision Tree","volume":"30","author":"Ke","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_34","first-page":"4765","article-title":"A Unified Approach to Interpreting Model Predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD \u201916), San Francisco, CA, USA, 13\u201317 August 2016, Association for Computing Machinery.","DOI":"10.1145\/2939672.2939778"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/9\/1009\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T03:20:35Z","timestamp":1788146435000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/9\/1009"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,30]]},"references-count":35,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["bioengineering13091009"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering13091009","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,30]]}}}