{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:14:03Z","timestamp":1781532843602,"version":"3.54.5"},"reference-count":56,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004515","name":"National University of Malaysia","doi-asserted-by":"crossref","award":["GGP-2020-014"],"award-info":[{"award-number":["GGP-2020-014"]}],"id":[{"id":"10.13039\/501100004515","id-type":"DOI","asserted-by":"crossref"}]},{"award":["GGP-2020-014"],"award-info":[{"award-number":["GGP-2020-014"]}],"id":[{"id":"https:\/\/ror.org\/00bw8d226","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Automated depression assessment is critical for scalable mental healthcare but faces dual challenges: the lack of clinical interpretability in \u201cblack-box\u201d deep learning models and the excessive computational cost of large-scale fusion architectures. To bridge this gap, we propose NS-Dep-KAN, a novel neuro-symbolic framework that harmonizes DSM-5-guided reasoning with Kolmogorov\u2013Arnold Networks (KANs). Our approach leverages a Large Language Model (LLM) to extract symbolic symptom evidence aligned with diagnostic criteria, which then guides the aggregation of multimodal features from frozen pretrained encoders (WavLM and Qwen). Unlike traditional Multi-Layer Perceptrons, the proposed KAN prediction head employs learnable B-spline activation functions to capture complex nonlinear symptom\u2013severity mappings with extreme parameter efficiency. Evaluations on the DAIC-WOZ benchmark demonstrate that NS-Dep-KAN achieves state-of-the-art performance among audio-text models (MAE 2.69, 13.5% improvement over the three-modality baseline MSGAF at MAE 3.11), with only \u223c4.9 K trainable parameters. Moreover, the framework offers inherent interpretability, revealing granular symptom contribution profiles that align with clinical intuition. This work establishes a path toward explainable trustworthy AI for mental health screening.<\/jats:p>","DOI":"10.3390\/info17060516","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T12:14:52Z","timestamp":1779452092000},"page":"516","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["NS-Dep-KAN: An Explainable Neuro-Symbolic Framework with Kolmogorov\u2013Arnold Networks for DSM-Guided Depression Assessment"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8380-9718","authenticated-orcid":false,"given":"Qiong","family":"Hong","sequence":"first","affiliation":[{"name":"Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM), Bangi 43600, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lailatul Qadri","family":"Zakaria","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM), Bangi 43600, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sabrina","family":"Tiun","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM), Bangi 43600, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,22]]},"reference":[{"key":"ref_1","unstructured":"World Health Organization (2025, October 16). Depression. Available online: https:\/\/www.who.int\/health-topics\/depression#tab=tab_1."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"American Psychiatric Association (2013). Diagnostic and Statistical Manual of Mental Disorders, American Psychiatric Publishing. [5th ed.].","DOI":"10.1176\/appi.books.9780890425596"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e419","DOI":"10.3399\/bjgp11X583209","article-title":"Measuring depression severity in general practice: Discriminatory performance of the PHQ-9, HADS-D, and BDI-II","volume":"61","author":"Cameron","year":"2011","journal-title":"Br. J. Gen. Pract."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"183952","DOI":"10.1109\/ACCESS.2020.3029154","article-title":"Application of machine learning methods in mental health detection: A systematic review","volume":"8","author":"Rahman","year":"2020","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1080\/24725579.2019.1567627","article-title":"Cost-effectiveness analysis of prognostic-based depression monitoring","volume":"9","author":"Lin","year":"2019","journal-title":"IISE Trans. Healthc. Syst. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Gong, Y., and Poellabauer, C. (2017, January 23). Topic modeling based multi-modal depression detection. Proceedings of the 7th Annual Workshop on Audio\/Visual Emotion Challenge (AVEC), Mountain View, CA, USA.","DOI":"10.1145\/3133944.3133945"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"He, L., Jiang, D., and Sahli, H. (2015, January 21\u201324). Multimodal depression recognition with dynamic visual and audio cues. Proceedings of the 2015 International Conference on Affective Computing and Intelligent Interaction (ACII), Xi\u2019an, China.","DOI":"10.1109\/ACII.2015.7344581"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1016\/j.jad.2021.08.090","article-title":"Multi-modal depression detection based on emotional audio and evaluation text","volume":"295","author":"Ye","year":"2021","journal-title":"J. Affect. Disord."},{"key":"ref_9","unstructured":"Makiuchi, M.R., Warnita, T., Uto, K., and Shinoda, K. (2019, January 21). Multimodal fusion of BERT-CNN and gated CNN representations for depression detection. Proceedings of the 9th International on Audio\/Visual Emotion Challenge and Workshop (AVEC), Nice, France."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Jia, X., Zhao, X., Tang, B., and Jiang, R. (2024, January 3\u20136). Bidirectional multimodal block-recurrent transformers for depression detection. Proceedings of the 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Lisbon, Portugal.","DOI":"10.1109\/BIBM62325.2024.10822661"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Huang, G., Shen, W., Lu, H., Hu, F., Li, J., and Liu, H. (2022, January 10\u201311). Multimodal depression detection based on factorized representation. Proceedings of the 2022 International Conference on High Performance Big Data and Intelligent Systems (HDIS), Tianjin, China.","DOI":"10.1109\/HDIS56859.2022.9991717"},{"key":"ref_12","first-page":"12449","article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"28400","DOI":"10.1038\/s41598-024-79981-0","article-title":"An adaptive multi-graph neural network with multimodal feature fusion learning for MDD detection","volume":"14","author":"Xing","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"652","DOI":"10.3934\/mbe.2025024","article-title":"Multimodal depression detection based on an attention graph convolution and transformer","volume":"22","author":"Jia","year":"2025","journal-title":"Math. Biosci. Eng."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Fan, Y., Zhou, Z., Zhao, J., Kong, J., Liu, Y., and Li, J. (2025, January 13\u201315). A multimodal deep learning framework for depression detection using vision transformers and large language models. Proceedings of the 2025 5th International Conference on Machine Learning and Intelligent Systems Engineering (MLISE), Shenzhen, China.","DOI":"10.1109\/MLISE66443.2025.11100256"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Teng, S., Liu, J., Sun, H., Chai, S., Tateyama, T., Lin, L., and Chen, Y.W. (2025, January 6\u201311). Enhanced multimodal depression detection with emotion prompts. Proceedings of the 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India.","DOI":"10.1109\/ICASSP49660.2025.10889035"},{"key":"ref_17","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_18","doi-asserted-by":"crossref","first-page":"108123","DOI":"10.1016\/j.bspc.2025.108123","article-title":"Multi-level spatiotemporal graph attention fusion for multimodal depression detection","volume":"110","author":"Yang","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Jung, J., Kang, C., Yoon, J., Kim, S., and Han, J. (2024, January 21\u201325). HiQuE: Hierarchical question embedding network for multimodal depression detection. Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (CIKM), Boise, ID, USA.","DOI":"10.1145\/3627673.3679797"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"115817","DOI":"10.1016\/j.psychres.2024.115817","article-title":"Explainable multimodal prediction of treatment-resistance in patients with depression leveraging brain morphometry and natural language processing","volume":"334","author":"Lee","year":"2024","journal-title":"Psychiatry Res."},{"key":"ref_21","unstructured":"Comanici, G., Bieber, E., Schaekermann, M., Pasupat, I., Sachdeva, N., Dhillon, I., Blistein, M., Ram, O., Zhang, D., and Rosen, E. (2025). Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","article-title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","volume":"16","author":"Chen","year":"2022","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_23","unstructured":"Yang, A., Li, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Gao, C., Huang, C., and Lv, C. (2025). Qwen3 technical report. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, Y., Vaidya, S., Ruehle, F., Halverson, J., Solja\u010di\u0107, M., Hou, T.Y., and Tegmark, M. (2024). KAN: Kolmogorov-Arnold networks. arXiv.","DOI":"10.1103\/4t7t-v19l"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"161203","DOI":"10.1109\/ACCESS.2024.3488081","article-title":"Integrating BERT with CNN and BiLSTM for explainable detection of depression in social media contents","volume":"12","author":"Xin","year":"2024","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"238","DOI":"10.11591\/ijai.v11.i1.pp238-253","article-title":"Comparison of classifiers using robust features for depression detection on Bahasa Malaysia speech","volume":"11","author":"Hashim","year":"2022","journal-title":"IAES Int. J. Artif. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Nasir, M., Jati, A., Shivakumar, P.G., Chakravarthula, S.N., and Georgiou, P. (2016, January 16). Multimodal and multiresolution depression detection from speech and facial landmark features. Proceedings of the 6th International Workshop on Audio\/Visual Emotion Challenge (AVEC), Amsterdam, The Netherlands.","DOI":"10.1145\/2988257.2988261"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e23042","DOI":"10.1016\/j.heliyon.2023.e23042","article-title":"Depressive symptoms among adults: Baseline findings of PURE Malaysia cohort study","volume":"10","author":"Tamil","year":"2024","journal-title":"Heliyon"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"63284","DOI":"10.1109\/ACCESS.2025.3559170","article-title":"Mental Health Safety and Depression Detection in Social Media Text Data: A Classification Approach Based on a Deep Learning Model","volume":"13","author":"Zhou","year":"2025","journal-title":"IEEE Access"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"6195","DOI":"10.1109\/TCSVT.2025.3533480","article-title":"Depression scale dictionary decomposition framework for multimodal automatic depression level prediction","volume":"35","author":"Niu","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"7749","DOI":"10.1109\/TCYB.2022.3197127","article-title":"MS2-GNN: Exploring GNN-based multimodal fusion network for depression detection","volume":"53","author":"Chen","year":"2023","journal-title":"IEEE Trans. Cybern."},{"key":"ref_32","unstructured":"Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., Laroussilhe, Q.D., Gesmundo, A., Attariyan, M., and Gelly, S. (2019, January 9\u201315). Parameter-efficient transfer learning for NLP. Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"61600","DOI":"10.1109\/ACCESS.2023.3285596","article-title":"Artificial intelligence and biosensors in healthcare and its clinical relevance: A review","volume":"11","author":"Qureshi","year":"2023","journal-title":"IEEE Access"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/64.491282","article-title":"Expert systems: A view of the field","volume":"11","author":"Durkin","year":"1996","journal-title":"IEEE Expert"},{"key":"ref_35","unstructured":"Ilkou, E., and Koutraki, M. (2020, January 19\u201320). Symbolic vs. sub-symbolic AI methods: Friends or enemies?. Proceedings of the CIKM 2020 Workshops, Galway, Ireland."},{"key":"ref_36","first-page":"71","article-title":"Knowledge graphs","volume":"54","author":"Hogan","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"109071","DOI":"10.1016\/j.compeleceng.2023.109071","article-title":"TAM-SenticNet: A neuro-symbolic AI approach for early depression detection via social media analysis","volume":"114","author":"Dou","year":"2024","journal-title":"Comput. Electr. Eng."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Dhanusha, C., Kumar, A.V.S., and Akula, V.S.G. (2022, January 1\u20132). Robust cuckoo search enabled fuzzy neuro symbolic reasoning-based Alzheimer\u2019s disease prediction at their earlier stages. Proceedings of the 5th International Conference on Computer Networks and Inventive Communication Technologies (ICCNCT), Coimbatore, India.","DOI":"10.1007\/978-981-19-3035-5_65"},{"key":"ref_39","unstructured":"Riegel, R., Gray, A., Luus, F., Khan, N., Makondo, N., Akhalwaya, I.Y., Qian, H., Fagin, R., Barahona, F., and Sharma, U. (2020). Logical neural networks. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1109\/MIC.2022.3179759","article-title":"Knowledge-infused learning: A sweet spot in neuro-symbolic AI","volume":"26","author":"Gaur","year":"2022","journal-title":"IEEE Internet Comput."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Agbavor, F., and Liang, H. (2022). Predicting dementia from spontaneous speech using large language models. PLoS Digit. Health, 1.","DOI":"10.1371\/journal.pdig.0000168"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1038\/s43856-025-01141-w","article-title":"Volumetric spline-based Kolmogorov-Arnold architectures surpass CNNs, vision transformers, and graph networks for Parkinson\u2019s disease detection","volume":"5","author":"Patel","year":"2025","journal-title":"Commun. Med."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Huang, Z., Cui, J., Yu, L., Contreras, L.F.H., and Kavehei, O. (2024). Abnormality detection in time-series bio-signals using Kolmogorov-Arnold networks for resource-constrained devices. medRxiv.","DOI":"10.1101\/2024.06.04.24308428"},{"key":"ref_44","unstructured":"Jampana, A.S., Velagapudi, M., Mohan, N., and S, S.K. (2024, January 19\u201322). Exploring Kolmogorov Arnold networks for interpretable mental health detection and classification from social media text. Proceedings of the 21st International Conference on Natural Language Processing (ICON), Chennai, India."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Pendyala, V.S., and Venkatachalam, N. (2025). The effectiveness of Kolmogorov\u2013Arnold networks in the healthcare domain. Appl. Sci., 15.","DOI":"10.3390\/app15169023"},{"key":"ref_46","unstructured":"Fang, L., Chai, B., Xu, Y., and Wang, S.J. (May, January 26). KANFeel: A novel Kolmogorov-Arnold network-based multimodal emotion recognition framework. Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA), Yokohama, Japan."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Ringeval, F., Schuller, B., Valstar, M., Gratch, J., Cowie, R., Scherer, S., Mozgai, S., Cummins, N., Schmitt, M., and Pantic, M. (2017, January 23). AVEC 2017: Real-life depression, and affect recognition workshop and challenge. Proceedings of the 7th Annual Workshop on Audio\/Visual Emotion Challenge (AVEC), Mountain View, CA, USA.","DOI":"10.1145\/3123266.3132049"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Zhao, Z., and Wang, K. (2022, January 11\u201315). Unaligned multimodal sequences for depression assessment from speech. Proceedings of the 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Glasgow, UK.","DOI":"10.1109\/EMBC48229.2022.9871556"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Sun, G., Zhao, S., Zou, B., and An, Y. (2022, January 30\u201331). Multimodal depression detection using a deep feature fusion network. Proceedings of the 3rd International Conference on Computer Science and Communication Technology (ICCSCT), Beijing, China.","DOI":"10.1117\/12.2662620"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"74324","DOI":"10.1109\/ACCESS.2023.3297091","article-title":"An investigation on the audio-video data based estimation of emotion regulation difficulties and their association with mental disorders","volume":"11","author":"Gupta","year":"2023","journal-title":"IEEE Access"},{"key":"ref_51","unstructured":"Pan, Y., Jiang, J., Jiang, K., and Liu, X. (November, January 28). Disentangled-multimodal privileged knowledge distillation for depression recognition with incomplete multimodal data. Proceedings of the 32nd ACM International Conference on Multimedia (MM), Melbourne, VIC, Australia."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"7536","DOI":"10.1109\/JBHI.2025.3574864","article-title":"TTFNet: Temporal-frequency features fusion network for speech based automatic depression recognition and assessment","volume":"29","author":"Chen","year":"2025","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1109\/TAFFC.2025.3606949","article-title":"Mitigating symptom heterogeneity in multimodal depression estimation via level separation and deviation regression","volume":"17","author":"Liu","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"3548","DOI":"10.1109\/TCSS.2025.3542986","article-title":"SIMMA: Multimodal automatic depression detection via spatiotemporal ensemble and cross-modal alignment","volume":"12","author":"Wang","year":"2025","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"ref_55","unstructured":"Google DeepMind (2026, March 10). Gemini 3 Pro Model Card. Available online: https:\/\/storage.googleapis.com\/deepmind-media\/Model-Cards\/Gemini-3-Pro-Model-Card.pdf."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"American Psychiatric Association (2022). Diagnostic and Statistical Manual of Mental Disorders: DSM-5-TR, American Psychiatric Association.","DOI":"10.1176\/appi.books.9780890425787"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/6\/516\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T04:10:53Z","timestamp":1780546253000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/6\/516"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,22]]},"references-count":56,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["info17060516"],"URL":"https:\/\/doi.org\/10.3390\/info17060516","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,22]]}}}