{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T03:01:49Z","timestamp":1793156509314,"version":"4.5.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T00:00:00Z","timestamp":1754611200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T00:00:00Z","timestamp":1754611200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100008783","name":"National Research Council of Science and Technology","doi-asserted-by":"publisher","award":["No.CAP21054-300"],"award-info":[{"award-number":["No.CAP21054-300"]}],"id":[{"id":"10.13039\/501100008783","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008783","name":"National Research Council of Science and Technology","doi-asserted-by":"publisher","award":["No.CAP21054-300"],"award-info":[{"award-number":["No.CAP21054-300"]}],"id":[{"id":"10.13039\/501100008783","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008783","name":"National Research Council of Science and Technology","doi-asserted-by":"publisher","award":["No.CAP21054-300"],"award-info":[{"award-number":["No.CAP21054-300"]}],"id":[{"id":"10.13039\/501100008783","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008783","name":"National Research Council of Science and Technology","doi-asserted-by":"publisher","award":["No.CAP21054-300"],"award-info":[{"award-number":["No.CAP21054-300"]}],"id":[{"id":"10.13039\/501100008783","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-14998-7","type":"journal-article","created":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T10:35:35Z","timestamp":1754649335000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Multimodal Alzheimer\u2019s disease recognition from image, text and audio"],"prefix":"10.1038","volume":"15","author":[{"given":"Byounghwa","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hwa Jeon","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young-Jin","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byung Ok","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,8]]},"reference":[{"key":"14998_CR1","volume-title":"BDAE: The Boston diagnostic aphasia examination","author":"H Goodglass","year":"2001","unstructured":"Goodglass, H., Kaplan, E. & Weintraub, S. BDAE: The Boston diagnostic aphasia examination (Lippincott Williams & Wilkins Philadelphia, 2001)."},{"key":"14998_CR2","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1001\/archneur.1994.00540180063015","volume":"51","author":"JT Becker","year":"1994","unstructured":"Becker, J. T., Boiler, F., Lopez, O. L., Saxton, J. & McGonigle, K. L. The natural history of alzheimer\u2019s disease: description of study cohort and accuracy of diagnosis. Arch. neurology 51, 585\u2013594 (1994).","journal-title":"Arch. neurology"},{"key":"14998_CR3","doi-asserted-by":"crossref","unstructured":"Luz, S., Haider, F., de la Fuente, S., Fromm, D. & MacWhinney, B. Detecting cognitive decline using speech only: The adresso challenge. arXiv preprint arXiv:2104.09356 (2021).","DOI":"10.1101\/2021.03.24.21254263"},{"key":"14998_CR4","doi-asserted-by":"crossref","unstructured":"Balagopalan, A. & Novikova, J. Comparing acoustic-based approaches for alzheimer\u2019s disease detection. arXiv preprint arXiv:2106.01555 (2021).","DOI":"10.21437\/Interspeech.2021-759"},{"key":"14998_CR5","doi-asserted-by":"crossref","unstructured":"Gauder, M.\u00a0L., Pepino, L.\u00a0D., Ferrer, L. & Riera, P. Alzheimer Disease Recognition Using Speech-Based Embeddings From Pre-Trained Models. In Proc. Interspeech 2021, 3795\u20133799, :10.21437\/Interspeech.2021-753 (2021).","DOI":"10.21437\/Interspeech.2021-753"},{"key":"14998_CR6","doi-asserted-by":"crossref","unstructured":"Pan, Y. et al. Using the outputs of different automatic speech recognition paradigms for acoustic-and bert-based alzheimer\u2019s dementia detection through spontaneous speech. In Interspeech, 3810\u20133814 (2021).","DOI":"10.21437\/Interspeech.2021-1519"},{"key":"14998_CR7","doi-asserted-by":"crossref","unstructured":"Syed, Z.\u00a0S., Syed, M. S.\u00a0S., Lech, M. & Pirogova, E. Tackling the adresso challenge 2021: The muet-rmit system for alzheimer\u2019s dementia recognition from spontaneous speech. In Interspeech, 3815\u20133819 (2021).","DOI":"10.21437\/Interspeech.2021-1572"},{"key":"14998_CR8","doi-asserted-by":"crossref","unstructured":"Touvron, H. et al. Training data-efficient image transformers & distillation through attention. In International conference on machine learning, 10347\u201310357 (PMLR, 2021).","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"14998_CR9","doi-asserted-by":"crossref","unstructured":"Ilias, L. & Askounis, D. Context-aware attention layers coupled with optimal transport domain adaptation and multimodal fusion methods for recognizing dementia from spontaneous speech. Knowledge-Based Syst. 277, (2023).","DOI":"10.1016\/j.knosys.2023.110834"},{"key":"14998_CR10","doi-asserted-by":"crossref","unstructured":"Bang, J.-U., Han, S.-H. & Kang, B.-O. Alzheimer\u2019s disease recognition from spontaneous speech using large language models. ETRI Journal (2024).","DOI":"10.4218\/etrij.2023-0356"},{"key":"14998_CR11","doi-asserted-by":"crossref","unstructured":"Botelho, C. et al. Macro-descriptors for alzheimer\u2019s disease detection using large language models. In Interspeech 2024, 1975\u20131979, :10.21437\/Interspeech.2024-1255 (2024).","DOI":"10.21437\/Interspeech.2024-1255"},{"key":"14998_CR12","doi-asserted-by":"crossref","unstructured":"Casu, F., Lagorio, A., Ruiu, P., Trunfio, G.\u00a0A. & Grosso, E. Integrating fine-tuned llm with acoustic features for enhanced detection of alzheimer\u2019s disease. IEEE J. Biomed. Heal. Informatics\u00a0(2025).","DOI":"10.1109\/JBHI.2025.3566615"},{"key":"14998_CR13","doi-asserted-by":"crossref","unstructured":"Wang, N., Cao, Y., Hao, S., Shao, Z. & Subbalakshmi, K. Modular multi-modal attention network for alzheimer\u2019s disease detection using patient audio and language data. In Interspeech, 3835\u20133839 (2021).","DOI":"10.21437\/Interspeech.2021-2024"},{"key":"14998_CR14","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Obyat, A., Liang, X., Batsis, J.\u00a0A. & Roth, R.\u00a0M. Wavbert: Exploiting semantic and non-semantic speech using wav2vec and bert for dementia detection. In Interspeech, vol. 2021, 3790 (NIH Public Access, 2021).","DOI":"10.21437\/Interspeech.2021-332"},{"key":"14998_CR15","first-page":"3825","volume":"2021","author":"R Pappagari","year":"2021","unstructured":"Pappagari, R. et al. Automatic detection and assessment of alzheimer disease using speech and language technologies in low-resource scenarios. In Interspeech 2021, 3825\u20133829 (2021).","journal-title":"In Interspeech"},{"key":"14998_CR16","doi-asserted-by":"crossref","unstructured":"Li, J. & Zhang, W.-Q. Whisper-based transfer learning for alzheimer disease classification: Leveraging speech segments with full transcripts as prompts. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 11211\u201311215 (IEEE, 2024).","DOI":"10.1109\/ICASSP48485.2024.10448004"},{"key":"14998_CR17","unstructured":"Zhu, Y. et al. Evaluating picture description speech for dementia detection using image-text alignment. arXiv preprint arXiv:2308.07933 (2023)."},{"key":"14998_CR18","unstructured":"Radford, A. et al. Learning transferable visual models from natural language supervision. In International conference on machine learning, 8748\u20138763 (PMLR, 2021)."},{"key":"14998_CR19","first-page":"997","volume":"15","author":"B Lee","year":"2025","unstructured":"Lee, B., Bang, J.-U., Song, H. J. & Kang, B. O. Alzheimer\u2019s disease recognition using graph neural network by leveraging image-text similarity from vision language model. Sci. Reports 15, 997 (2025).","journal-title":"Sci. Reports"},{"key":"14998_CR20","unstructured":"Li, J., Li, D., Xiong, C. & Hoi, S. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning, 12888\u201312900 (PMLR, 2022)."},{"key":"14998_CR21","doi-asserted-by":"crossref","unstructured":"Casu, F., Grosso, E., Lagorio, A., Ruiu, P. & Trunfio, G.\u00a0A. Leveraging multimodal vision language models for early detection of alzheimer\u2019s disease. In 2025 33rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP), 291\u2013298 (IEEE, 2025).","DOI":"10.1109\/PDP66500.2025.00047"},{"key":"14998_CR22","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/MSP.2017.2738401","volume":"34","author":"D Ramachandram","year":"2017","unstructured":"Ramachandram, D. & Taylor, G. W. Deep multimodal learning: A survey on recent advances and trends. IEEE signal processing magazine 34, 96\u2013108 (2017).","journal-title":"IEEE signal processing magazine"},{"key":"14998_CR23","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2018","unstructured":"Baltru\u0161aitis, T., Ahuja, C. & Morency, L.-P. Multimodal machine learning: A survey and taxonomy. IEEE transactions on pattern analysis and machine intelligence 41, 423\u2013443 (2018).","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"14998_CR24","unstructured":"Yin, S. et al. A survey on multimodal large language models. arXiv preprint arXiv:2306.13549 (2023)."},{"key":"14998_CR25","doi-asserted-by":"crossref","unstructured":"Shapley, L.\u00a0S. A value for n-person games. Contribution to the Theory of Games 2 (1953).","DOI":"10.1515\/9781400881970-018"},{"key":"14998_CR26","doi-asserted-by":"crossref","unstructured":"Hu, P., Li, X. & Zhou, Y. Shape: An unified approach to evaluate the contribution and cooperation of individual modalities. arXiv preprint arXiv:2205.00302 (2022).","DOI":"10.24963\/ijcai.2022\/425"},{"key":"14998_CR27","doi-asserted-by":"crossref","unstructured":"Jeon, J., Kim, J., Park, J. & Kim, J. Msv: Contribution of modalities based on the shapley value. In 2024 IEEE International Conference on Consumer Electronics (ICCE), 1\u20136 (IEEE, 2024).","DOI":"10.1109\/ICCE59016.2024.10444313"},{"key":"14998_CR28","unstructured":"Li, J., Li, D., Savarese, S. & Hoi, S. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning, 19730\u201319742 (PMLR, 2023)."},{"key":"14998_CR29","unstructured":"Baevski, A., Zhou, Y., Mohamed, A. & Auli, M. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems 33, 12449\u201312460 (2020)."},{"key":"14998_CR30","doi-asserted-by":"crossref","unstructured":"Wu, S.-L., Kingsbury, E., Morgan, N. & Greenberg, S. Incorporating information from syllable-length time scales into automatic speech recognition. In Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP\u201998 (Cat. No. 98CH36181), vol.\u00a02, 721\u2013724 (IEEE, 1998).","DOI":"10.1109\/ICASSP.1998.675366"},{"key":"14998_CR31","first-page":"160","volume":"1","author":"S-L Wu","year":"1998","unstructured":"Wu, S.-L., Kingsbury, B., Morgan, N. & Greenberg, S. Performance improvements through combining phone-and syllable-scale information in automatic speech recognition. In ICSLP 1, 160\u2013163 (1998).","journal-title":"In ICSLP"},{"key":"14998_CR32","unstructured":"Radford, A. et al. Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning, 28492\u201328518 (PMLR, 2023)."},{"key":"14998_CR33","unstructured":"Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"14998_CR34","unstructured":"Kipf, T.\u00a0N. & Welling, M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"14998_CR35","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.\u00a0R. et al. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision, 618\u2013626 (2017).","DOI":"10.1109\/ICCV.2017.74"},{"key":"14998_CR36","doi-asserted-by":"crossref","unstructured":"Li, D. et al. Lavis: A one-stop library for language-vision intelligence. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), 31\u201341 (2023).","DOI":"10.18653\/v1\/2023.acl-demo.3"},{"key":"14998_CR37","unstructured":"Fey, M. & Lenssen, J.\u00a0E. Fast graph representation learning with pytorch geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds (2019)."},{"key":"14998_CR38","doi-asserted-by":"publisher","first-page":"4602","DOI":"10.1609\/aaai.v33i01.33014602","volume":"33","author":"C Morris","year":"2019","unstructured":"Morris, C. et al. Weisfeiler and leman go neural: Higher-order graph neural networks. In Proceedings of the AAAI conference on artificial intelligence 33, 4602\u20134609 (2019).","journal-title":"In Proceedings of the AAAI conference on artificial intelligence"},{"key":"14998_CR39","unstructured":"Paszke, A. et al. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"14998_CR40","doi-asserted-by":"crossref","unstructured":"Henderson, S.\u00a0K. et al. Lexical markers of disordered speech in primary progressive aphasia and \u2018parkinson-plus\u2019 disorders. Brain Commun.\u00a06, fcae433 (2024).","DOI":"10.1093\/braincomms\/fcae433"},{"key":"14998_CR41","doi-asserted-by":"publisher","first-page":"496","DOI":"10.26599\/BDMA.2024.9020090","volume":"8","author":"P Wang","year":"2025","unstructured":"Wang, P. et al. Large language model for medical images: A survey of taxonomy, systematic review, and future trends. Big Data Min. Anal. 8, 496\u2013517 (2025).","journal-title":"Big Data Min. Anal."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-14998-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-14998-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-14998-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T19:40:26Z","timestamp":1757360426000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-14998-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,8]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["14998"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-14998-7","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,8]]},"assertion":[{"value":"14 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2025","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 authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"29038"}}