{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T15:50:33Z","timestamp":1791474633768,"version":"4.3.4"},"reference-count":33,"publisher":"Walter de Gruyter GmbH","issue":"4-5","license":[{"start":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:00:00Z","timestamp":1772496000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,26]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec id=\"j_bmt-2026-0004_abs_001\">\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Accurate identification of Parkinson\u2019s disease (PD), particularly during its prodromal stage, remains a major clinical challenge due to heterogeneous symptom presentation and overlapping neurological patterns. This study proposes an LLM-Guided Multimodal Attention Network (LLM-MAN) to improve PD staging by jointly modeling structural MRI and clinical\/cognitive metadata.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"j_bmt-2026-0004_abs_002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We develop a unified multimodal framework that\u00a0encodes structural MRI using a ResNet-18 backbone enhanced with Convolutional Block Attention Modules (CBAM) for discriminative neuroimaging feature extraction, and represents clinical\/cognitive metadata using an LLM-based text encoder (pre-trained BERT) for contextualized semantic modeling. A Meta-Guided Cross-Attention (MGCA) module is introduced to align clinical semantic knowledge with imaging features, enabling robust cross-modal fusion for multiclass classification (Normal Control, prodromal PD, and diagnosed PD). The model is evaluated on the Parkinson\u2019s Progression Markers Initiative (PPMI) dataset and further validated on an independent external cohort.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"j_bmt-2026-0004_abs_003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On the PPMI dataset, LLM-MAN achieved an accuracy of 95.68\u202f% for distinguishing Normal Control, prodromal PD, and diagnosed PD. External validation on an independent cohort yielded 94.10\u202f% accuracy, indicating strong generalization performance across datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"j_bmt-2026-0004_abs_004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>LLM-guided multimodal fusion via MGCA provides reliable and interpretable approach for PD staging, substantially improving prodromal PD identification by integrating semantic clinical knowledge with neuroimaging representations.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1515\/bmt-2026-0004","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T14:26:49Z","timestamp":1772461609000},"page":"349-361","source":"Crossref","is-referenced-by-count":1,"title":["LLM-guided multimodal attention network for robust multiclass Parkinson\u2019s disease diagnosis"],"prefix":"10.1515","volume":"71","author":[{"given":"Taisheng","family":"Zeng","sequence":"first","affiliation":[{"name":"Faculty of Mathematics and Computer Science , Quanzhou Normal University , Quanzhou , China"},{"name":"Fujian Provincial Key Laboratory of Data Intensive Computing , Quanzhou , China"},{"name":"Key Laboratory of Intelligent Computing and Information Processing, Fujian Province University , Quanzhou , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuguang","family":"Ye","sequence":"additional","affiliation":[{"name":"Faculty of Mathematics and Computer Science , Quanzhou Normal University , Quanzhou , China"},{"name":"Fujian Provincial Key Laboratory of Data Intensive Computing , Quanzhou , China"},{"name":"Key Laboratory of Intelligent Computing and Information Processing, Fujian Province University , Quanzhou , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bijiao","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology , Huaqiao University Affiliated Strait Hospital , Quanzhou , Fujian , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology , Huaqiao University Affiliated Strait Hospital , Quanzhou , Fujian , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5401-5650","authenticated-orcid":false,"given":"Muhammad Ibrahim","family":"Umar","sequence":"additional","affiliation":[{"name":"12443 School of Artificial Intelligence and Automation, Huazhong University of Science and Technology , Wuhan , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kavimbi","family":"Chipusu","sequence":"additional","affiliation":[{"name":"Faculty of Mathematics and Computer Science , Quanzhou Normal University , Quanzhou , China"},{"name":"Fujian Provincial Key Laboratory of Data Intensive Computing , Quanzhou , China"},{"name":"Key Laboratory of Intelligent Computing and Information Processing, Fujian Province University , Quanzhou , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianlong","family":"Huang","sequence":"additional","affiliation":[{"name":"Faculty of Mathematics and Computer Science , Quanzhou Normal University , Quanzhou , China"},{"name":"Fujian Provincial Key Laboratory of Data Intensive Computing , Quanzhou , China"},{"name":"Key Laboratory of Intelligent Computing and Information Processing, Fujian Province University , Quanzhou , China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"374","published-online":{"date-parts":[[2026,3,3]]},"reference":[{"key":"2026100814512984724_j_bmt-2026-0004_ref_001","doi-asserted-by":"crossref","unstructured":"Riley, JC. Estimates of regional and global life expectancy, 1800\u20132001. Popul Dev Rev 2005;31. https:\/\/doi.org\/10.1111\/j.1728-4457.2005.00083.x.","DOI":"10.1111\/j.1728-4457.2005.00083.x"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_002","unstructured":"World Health Organization Global Health Observatory. Life expectancy and healthy life expectancy. WHO Press, World Health Organization; 2023."},{"key":"2026100814512984724_j_bmt-2026-0004_ref_003","doi-asserted-by":"crossref","unstructured":"Heuveline, P. Global and national declines in life expectancy: an end-of-2021 assessment. Popul Dev Rev 2022;48. https:\/\/doi.org\/10.1111\/padr.12477.","DOI":"10.1101\/2022.01.14.22269109"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_004","doi-asserted-by":"crossref","unstructured":"Wong, KKL. Cybernetical intelligence: engineering cybernetics with machine intelligence. Hoboken, New Jersey: John Wiley & Sons, Inc.; 2023.","DOI":"10.1002\/9781394217519"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_005","doi-asserted-by":"crossref","unstructured":"Marek, K, Chowdhury, S, Siderowf, A, Lasch, S, Coffey, CS, Caspell, GC, et al.. The Parkinson\u2019s progression markers initiative (PPMI)\u00a0\u2013\u00a0establishing a PD biomarker cohort. Ann Clin Transl Neurol 2018;5. https:\/\/doi.org\/10.1002\/acn3.644.","DOI":"10.1002\/acn3.644"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_006","doi-asserted-by":"crossref","unstructured":"Xue, W, Bowman, FDB, Kang, J. A Bayesian spatial model to predict disease status using imaging data from various modalities. Front Neurosci 2018;12. https:\/\/doi.org\/10.3389\/fnins.2018.00184.","DOI":"10.3389\/fnins.2018.00184"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_007","doi-asserted-by":"crossref","unstructured":"Bhagwat, N, Pipitone, J, Park, MTM, Voineskos, AN, Chakravarty, M. P4\u2010210: neural-net model for predicting clinical symptom scores in Alzheimer\u2019s disease. Alzheimer\u2019s Dementia 2016;12. https:\/\/doi.org\/10.1016\/j.jalz.2016.06.2302.","DOI":"10.1016\/j.jalz.2016.06.2302"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_008","doi-asserted-by":"crossref","unstructured":"Qin, Y, Li, Y, Zhuo, Z, Liu, Z, Liu, Y, Ye, C. Multimodal super-resolved q-space deep learning. Med Image Anal 2021;71. https:\/\/doi.org\/10.1016\/j.media.2021.102085.","DOI":"10.1016\/j.media.2021.102085"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_009","doi-asserted-by":"crossref","unstructured":"Abdolrahimzadeh, S, Pugi, DM, Manni, P, Iodice, CM, Tizio, FD, Persechino, F, et al.. An update on ophthalmological perspectives in oculodermal melanocytosis (Nevus of Ota). Graefe\u2019s Arch Clin Exp\u00a0Ophthalmol 2023;261. https:\/\/doi.org\/10.1007\/s00417-022-05743-1.","DOI":"10.1007\/s00417-022-05743-1"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_010","doi-asserted-by":"crossref","unstructured":"Peng, Z, Ma, R, Zhang, Y, Yan, M, Lu, J, Cheng, Q, et al.. Development and evaluation of multimodal AI for diagnosis and triage of ophthalmic diseases using ChatGPT and anterior segment images: protocol for a two-stage cross-sectional study. Front Artif Intell 2023;6. https:\/\/doi.org\/10.3389\/frai.2023.1323924.","DOI":"10.3389\/frai.2023.1323924"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_011","doi-asserted-by":"crossref","unstructured":"Wang, H, Huang, R, Zhang, J. Research progress on vision\u2013language multimodal pretraining model technology. Electronics 2022;11. https:\/\/doi.org\/10.3390\/electronics11213556.","DOI":"10.3390\/electronics11213556"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_012","doi-asserted-by":"crossref","unstructured":"Wang, W, Bao, H, Dong, L, Bjorck, J, Peng, Z, Liu, Q, et al.. Image as a foreign language: BEIT pretraining for vision and vision-language tasks. In Proceedings of the proceedings of the IEEE computer society conference on computer vision and pattern recognition; 2023.","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_013","doi-asserted-by":"crossref","unstructured":"Wang, W, Tan, X, Zhang, P, Wang, X. A CBAM based multiscale transformer fusion approach for remote sensing image change detection. IEEE J Sel Top Appl Earth Obs Rem Sens 2022;15. https:\/\/doi.org\/10.1109\/JSTARS.2022.3198517.","DOI":"10.1109\/JSTARS.2022.3198517"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_014","doi-asserted-by":"crossref","unstructured":"Woo, S, Park, J, Lee, JY, Kweon, IS. CBAM: convolutional block attention module. Proc Lect Notes Comput Sci 2018;11211.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_015","unstructured":"Hashimoto, R, Mori, E. Mini-mental state examination (MMSE). Nihon Rinsho 2011, 69."},{"key":"2026100814512984724_j_bmt-2026-0004_ref_016","doi-asserted-by":"crossref","unstructured":"Dahbour, S, Hashim, M, Alhyasat, A, Salameh, A, Qtaishat, A, Braik, R, et al.. Mini-mental state examination (MMSE) scores in elderly Jordanian population. Cereb Circ Cogn Behav 2021;2. https:\/\/doi.org\/10.1016\/j.cccb.2021.100016.","DOI":"10.1016\/j.cccb.2021.100016"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_017","doi-asserted-by":"crossref","unstructured":"Hwang, IC, Kang, HS. Anomaly detection based on a 3D convolutional neural network combining convolutional block attention module using merged frames. Sensors 2023;23. https:\/\/doi.org\/10.3390\/s23239616.","DOI":"10.3390\/s23239616"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_018","doi-asserted-by":"crossref","unstructured":"Xin, H, Li, L. Arbitrary style transfer with fused convolutional block attention modules. IEEE Access 2023;11. https:\/\/doi.org\/10.1109\/ACCESS.2023.3273949.","DOI":"10.1109\/ACCESS.2023.3273949"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_019","doi-asserted-by":"crossref","unstructured":"Chen, B, Zhang, Z, Liu, N, Tan, Y, Liu, X, Chen, T. Spatiotemporal convolutional neural network with convolutional block attention module for micro-expression recognition. Information 2020;11. https:\/\/doi.org\/10.3390\/INFO11080380.","DOI":"10.3390\/info11080380"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_020","doi-asserted-by":"crossref","unstructured":"Tang, T, Cui, Y, Feng, R, Xiang, D. Vehicle target recognition in SAR images with complex scenes based on mixed attention mechanism. Information 2024;15. https:\/\/doi.org\/10.3390\/info15030159.","DOI":"10.3390\/info15030159"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_021","doi-asserted-by":"crossref","unstructured":"Cao, Y, Zhao, Z, Huang, Y, Lin, X, Luo, S, Xiang, B, et al.. Case instance segmentation of small farmland based on mask R-CNN of feature pyramid network with double attention mechanism in high resolution satellite images. Comput Electron Agric 2023;212. https:\/\/doi.org\/10.1016\/j.compag.2023.108073.","DOI":"10.1016\/j.compag.2023.108073"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_022","doi-asserted-by":"crossref","unstructured":"Rahman, S, Rahman, MM, Bhatt, S, Sundararajan, R, Faezipour, M. NeuroNet-AD: a multimodal deep learning framework for multiclass Alzheimer\u2019s disease diagnosis. Bioengineering 2025;12:1107. https:\/\/doi.org\/10.3390\/bioengineering12101107.","DOI":"10.3390\/bioengineering12101107"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_023","doi-asserted-by":"crossref","unstructured":"Argade, D, Khairnar, V, Vora, D, Patil, S, Kotecha, K, Alfarhood, S. Multimodal abstractive summarization using bidirectional encoder representations from transformers with attention mechanism. Heliyon 2024;10. https:\/\/doi.org\/10.1016\/j.heliyon.2024.e26162.","DOI":"10.1016\/j.heliyon.2024.e26162"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_024","doi-asserted-by":"crossref","unstructured":"Ben\u00edtez-Andrades, JA, Alija-Perez, JM, Vidal, ME, Pastor-Vargas, R, Garc\u00eda-Ordas, MT. Traditional machine learning models and bidirectional encoder representations from transformer (BERT)-based automatic classification of tweets about eating disorders: algorithm development and validation study. JMIR Med Inform 2022;10. https:\/\/doi.org\/10.2196\/34492.","DOI":"10.2196\/34492"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_025","doi-asserted-by":"crossref","unstructured":"Sadot, AAIM, Maliha Mehjabin, M, Mahafuz, A. A novel approach to efficient multilabel text classification: BERT-federated learning fusion. In Proceedings of the 2023\u00a026th international conference on computer and information technology. ICCIT; 2023.","DOI":"10.1109\/ICCIT60459.2023.10441264"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_026","doi-asserted-by":"crossref","unstructured":"Chahine, LM, Siderowf, A, Barnes, J, Seedorff, N, Caspell-Garcia, C, Simuni, T, Parkinson\u2019s Progression Markers Initiative\u2020, et al.. Predicting progression in Parkinson\u2019s disease using baseline and 1-year change measures. J\u00a0Parkinsons Dis 2019;9:665\u201379. https:\/\/doi.org\/10.3233\/jpd-181518.","DOI":"10.3233\/JPD-181518"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_027","doi-asserted-by":"crossref","unstructured":"Zeng, T, Chipusu, K, Zhu, Y, Li, M, Muhammad Ibrahim, U, Huang, J. Differential evolutionary optimization fuzzy entropy for gland segmentation based on breast mammography imaging. J\u00a0Radiat Res Appl Sci 2024;17:100966. https:\/\/doi.org\/10.1016\/j.jrras.2024.100966.","DOI":"10.1016\/j.jrras.2024.100966"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_032","doi-asserted-by":"crossref","unstructured":"Shen, D, Du, S, Wang, S, Yan, L, Li, S, Chen, X. An improved variational autoencoder and graph attention network method for wear prediction of aerospace self-lubricating bearing using acoustic emission signal. IEEE Sens J 2026. https:\/\/doi.org\/10.1109\/JSEN.2025.3650493.","DOI":"10.1109\/JSEN.2025.3650493"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_033","doi-asserted-by":"crossref","unstructured":"Wang, S, Du, S, Yan, L, Li, S, Chen, X. A hybrid physical damage neural network for wear prediction of self-lubricating bearings. J Comput Inf Sci Eng 2026. https:\/\/doi.org\/10.1115\/1.4071182.","DOI":"10.1115\/1.4071182"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_031","doi-asserted-by":"crossref","unstructured":"Zhou, Y, Lv, J, Du, S, Shen, X, Liu, M. Multi-resource constrained flexible job shop scheduling with fixture-pallets and setup stations under pallet automation systems. IEEE Trans Syst Man Cybern: Systems 2026. https:\/\/doi.org\/10.1109\/TSMC.2026.3655483.","DOI":"10.36227\/techrxiv.174439259.90707217\/v1"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_028","doi-asserted-by":"crossref","unstructured":"Wong, KKL, Xu, W, Ayoub, M, Fu, YL, Xu, H, Shi, RZ, et al.. Brain image segmentation of the corpus callosum by combining bi-directional convolutional LSTM and U-net using multi-slice CT and MRI. Comput Methods Progr Biomed 2023:107602. https:\/\/doi.org\/10.1016\/j.cmpb.2023.107602.","DOI":"10.1016\/j.cmpb.2023.107602"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_029","doi-asserted-by":"crossref","unstructured":"KKL Wong, J Xu, C Chen, D Ghista and H Zhao, Functional magnetic resonance imaging providing the brain effect mechanism of acupuncture and moxibustion treatment for depression, Front Neurol, dio: https:\/\/doi.org\/10.3389\/fneur.2023.1151421, 2023.","DOI":"10.3389\/fneur.2023.1151421"},{"key":"2026100814512984724_j_bmt-2026-0004_ref_030","doi-asserted-by":"crossref","unstructured":"Wong, KKL, Ayoub, M, Cao, Z, Chen, C, Chen, W, Ghista, D, et al.. The synergy of cybernetical intelligence with medical image analysis for deep medicine: a methodological perspective. Comput Methods Progr Biomed 2023:107677. https:\/\/doi.org\/10.1016\/j.cmpb.2023.107677.","DOI":"10.1016\/j.cmpb.2023.107677"}],"container-title":["Biomedical Engineering \/ Biomedizinische Technik"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/bmt-2026-0004\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/bmt-2026-0004\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T14:53:35Z","timestamp":1791471215000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/bmt-2026-0004\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,3]]},"references-count":33,"journal-issue":{"issue":"4-5","published-online":{"date-parts":[[2026,6,8]]},"published-print":{"date-parts":[[2026,10,26]]}},"alternative-id":["10.1515\/bmt-2026-0004"],"URL":"https:\/\/doi.org\/10.1515\/bmt-2026-0004","relation":{},"ISSN":["0013-5585","1862-278X"],"issn-type":[{"value":"0013-5585","type":"print"},{"value":"1862-278X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,3]]}}}