{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T20:52:14Z","timestamp":1781643134836,"version":"3.54.5"},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T00:00:00Z","timestamp":1773360000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T00:00:00Z","timestamp":1773360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"University of Kocaeli"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Med Biol Eng Comput"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:sec>\n                    <jats:title>Abstract<\/jats:title>\n                    <jats:p>\n                      Parkinson\u2019s disease (PD) is a progressive neurodegenerative disorder marked by motor symptoms, but early diagnosis is challenging due to symptom overlap with other conditions and a lack of definitive biomarkers (clinical assessments). In this study, we propose a novel multimodal artificial intelligence (AI)-based decision support system aimed at the early diagnosis of idiopathic PD. To the best of our knowledge, this is the first framework to enable the synchronous analysis of four distinct modalities: walking, facial expression, voice, and posture, whereas prior studies have typically focused on unimodal or partially multimodal approaches. We also constructed a new dataset by establishing a controlled clinical testing environment equipped with an L-shaped walking track and an integrated audiovisual recording system to capture natural walking, turning, facial, vocal, and postural characteristics. For each modality, specialized AI models were developed and evaluated. For the walking modality, the proposed Bidirectional GRU model achieved the best performance in terms of both\n                      <jats:inline-formula>\n                        <jats:tex-math>$$F_1$$<\/jats:tex-math>\n                      <\/jats:inline-formula>\n                      score (92.74%) and area under the curve (AUC) (97.86%), demonstrating superior gait-based classification performance. Similarly, in the face modality, the ensemble model integrating eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Categorical Boosting (CatBoost) yielded the highest\n                      <jats:inline-formula>\n                        <jats:tex-math>$$F_1$$<\/jats:tex-math>\n                      <\/jats:inline-formula>\n                      score (92.31%) while also achieving the best AUC (97.96%). For the voice and posture modalities, although the highest\n                      <jats:inline-formula>\n                        <jats:tex-math>$$F_1$$<\/jats:tex-math>\n                      <\/jats:inline-formula>\n                      scores were not obtained, the RF-based models achieved the highest AUC values (99.85% and 97.56%, respectively) within their respective modality comparisons in the literature, reflecting strong class separability and discriminative capability.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11517-026-03547-7","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T08:18:19Z","timestamp":1773389899000},"page":"1689-1711","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A novel multimodal AI framework for early diagnosis of idiopathic Parkinson\u2019s disease"],"prefix":"10.1007","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4049-9566","authenticated-orcid":false,"given":"Efe Y\u0131lmaz","family":"Ta\u015fy\u00fcrek","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1388-9191","authenticated-orcid":false,"given":"\u015eaban Murat","family":"Altun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8318-1686","authenticated-orcid":false,"given":"Ata Emir","family":"Uncu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1468-2252","authenticated-orcid":false,"given":"Sefa","family":"Tunca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1214-9235","authenticated-orcid":false,"given":"Sevin\u00e7 \u0130lhan","family":"Omurca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7581-9390","authenticated-orcid":false,"given":"Meltem Kurt","family":"Pehlivano\u011flu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4498-4817","authenticated-orcid":false,"given":"Aybala Neslihan","family":"Alag\u00f6z","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5102-7063","authenticated-orcid":false,"given":"O\u011fulcan","family":"Kalkan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,13]]},"reference":[{"issue":"2","key":"3547_CR1","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1007\/s11831-024-10148-w","volume":"32","author":"S Asif","year":"2025","unstructured":"Asif S, Wenhui Y, ur Rehman S, ul ain Q, Amjad K, Yueyang Y, Jinhai S, Awais M (2025) Advancements and prospects of machine learning in medical diagnostics: unveiling the future of diagnostic precision. Arch Comput Methods Eng 32(2):853\u2013883","journal-title":"Arch Comput Methods Eng"},{"issue":"22","key":"3547_CR2","doi-asserted-by":"publisher","first-page":"8773","DOI":"10.3390\/s22228773","volume":"22","author":"L di Biase","year":"2022","unstructured":"di Biase L, Raiano L, Caminiti ML, Pecoraro PM, Di Lazzaro V (2022) Parkinson\u2019s disease wearable gait analysis: kinematic and dynamic markers for diagnosis. Sensors 22(22):8773","journal-title":"Sensors"},{"issue":"24","key":"3547_CR3","doi-asserted-by":"publisher","first-page":"9903","DOI":"10.3390\/s22249903","volume":"22","author":"F Castelli Gattinara Di Zubiena","year":"2022","unstructured":"Castelli Gattinara Di Zubiena F, Menna G, Mileti I, Zampogna A, Asci F, Paoloni M, Suppa A, Del Prete Z, Palermo E (2022) Machine learning and wearable sensors for the early detection of balance disorders in Parkinson\u2019s disease. Sensors 22(24):9903","journal-title":"Sensors"},{"issue":"5","key":"3547_CR4","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.3390\/s24051499","volume":"24","author":"MG Di Cesare","year":"2024","unstructured":"Di Cesare MG, Perpetuini D, Cardone D, Merla A (2024) Machine learning-assisted speech analysis for early detection of parkinson\u2019s disease: a study on speaker diarization and classification techniques. Sensors 24(5):1499","journal-title":"Sensors"},{"key":"3547_CR5","doi-asserted-by":"crossref","unstructured":"He T, Chen J, Xu X, Wang W (2024) Exploiting smartphone voice recording as a digital biomarker for Parkinson\u2019s disease diagnosis. IEEE Trans Instrum Meas","DOI":"10.1109\/TIM.2024.3391339"},{"key":"3547_CR6","doi-asserted-by":"crossref","unstructured":"Huang B, Lv J, Qiang L (2025) Gait detection of lower limb exoskeleton robot integrating visual perception and geometric features. Intell Serv Robot, 1\u201323","DOI":"10.1007\/s11370-025-00598-x"},{"key":"3547_CR7","doi-asserted-by":"crossref","unstructured":"Huang W, Xu W, Wan R, Zhang P, Zha Y, Pang M (2023) Auto diagnosis of Parkinson\u2019s disease via a deep learning model based on mixed emotional facial expressions. IEEE J Biomed Health Inf","DOI":"10.1109\/JBHI.2023.3239780"},{"issue":"1","key":"3547_CR8","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1038\/s41531-022-00414-8","volume":"8","author":"WS Lim","year":"2022","unstructured":"Lim WS, Chiu SI, Wu MC, Tsai SF, Wang PH, Lin KP, Chen YM, Peng PL, Chen YY, Jang JSR et al (2022) An integrated biometric voice and facial features for early detection of parkinson\u2019s disease. npj Parkinson\u2019s Disease 8(1):145","journal-title":"npj Parkinson\u2019s Disease"},{"key":"3547_CR9","doi-asserted-by":"crossref","unstructured":"Mehta D, Asif U, Hao T, Bilal E, Von Cavallar S, Harrer S, Rogers J (2021) Towards automated and marker-less parkinson disease assessment: predicting updrs scores using sit-stand videos. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3841\u20133849","DOI":"10.1109\/CVPRW53098.2021.00425"},{"issue":"2","key":"3547_CR10","doi-asserted-by":"publisher","first-page":"140","DOI":"10.14802\/jmd.21129","volume":"15","author":"JH Shin","year":"2022","unstructured":"Shin JH, Woo KA, Lee CY, Jeon SH, Kim HJ, Jeon B (2022) Automatic measurement of postural abnormalities with a pose estimation algorithm in Parkinson\u2019s disease. J Mov Disord 15(2):140","journal-title":"J Mov Disord"},{"key":"3547_CR11","doi-asserted-by":"publisher","first-page":"831428","DOI":"10.3389\/fneur.2022.831428","volume":"13","author":"A Suppa","year":"2022","unstructured":"Suppa A, Costantini G, Asci F, Di Leo P, Al-Wardat MS, Di Lazzaro G, Scalise S, Pisani A, Saggio G (2022) Voice in Parkinson\u2019s disease: a machine learning study. Front Neurol 13:831428","journal-title":"Front Neurol"},{"key":"3547_CR12","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1109\/TNSRE.2024.3352004","volume":"32","author":"H Tian","year":"2024","unstructured":"Tian H, Li H, Jiang W, Ma X, Li X, Wu H, Li Y (2024) Cross-spatiotemporal graph convolution networks for skeleton-based parkinsonian gait mds-updrs score estimation. IEEE Trans Neural Syst Rehabil Eng 32:412\u2013421","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"3547_CR13","doi-asserted-by":"publisher","first-page":"1638340","DOI":"10.3389\/fnagi.2025.1638340","volume":"17","author":"B Twala","year":"2025","unstructured":"Twala B (2025) Ai-driven precision diagnosis and treatment in Parkinson\u2019s disease: a comprehensive review and experimental analysis. Front Aging Neurosci 17:1638340","journal-title":"Front Aging Neurosci"},{"key":"3547_CR14","doi-asserted-by":"crossref","unstructured":"Xu Z, Lv D, Li H, Li H, Gao H (2023) Application of reslstm in hypomimia video detection for parkinson\u2019s disease. In: 2023 International Conference on New Trends in Computational Intelligence (NTCI), vol 1. IEEE, pp 243\u2013247","DOI":"10.1109\/NTCI60157.2023.10403741"},{"key":"3547_CR15","doi-asserted-by":"publisher","first-page":"2912","DOI":"10.1109\/TNSRE.2023.3291359","volume":"31","author":"Q Zeng","year":"2023","unstructured":"Zeng Q, Liu P, Yu N, Wu J, Huo W, Han J (2023) Video-based quantification of gait impairments in Parkinson\u2019s disease using skeleton-silhouette fusion convolution network. IEEE Trans Neural Syst Rehabil Eng 31:2912\u20132922","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"3547_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12984-021-00959-4","volume":"18","author":"Z Zhang","year":"2021","unstructured":"Zhang Z, Hong R, Lin A, Su X, Jin Y, Gao Y, Peng K, Li Y, Zhang T, Zhi H et al (2021) Automated and accurate assessment for postural abnormalities in patients with Parkinson\u2019s disease based on kinect and machine learning. J Neuroeng Rehabil 18:1\u201310","journal-title":"J Neuroeng Rehabil"},{"key":"3547_CR17","doi-asserted-by":"publisher","first-page":"122837","DOI":"10.1016\/j.eswa.2023.122837","volume":"243","author":"Y Zhao","year":"2024","unstructured":"Zhao Y, Liu Y, Li J, Wang X, Yang R, Lian C, Shan P, Wang Y, Zhan Z, Fu C (2024) Global joint information extraction convolution neural network for Parkinson\u2019s disease diagnosis. Expert Syst Appl 243:122837","journal-title":"Expert Syst Appl"}],"container-title":["Medical &amp; Biological Engineering &amp; Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11517-026-03547-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11517-026-03547-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11517-026-03547-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T20:00:00Z","timestamp":1781640000000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11517-026-03547-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,13]]},"references-count":17,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["3547"],"URL":"https:\/\/doi.org\/10.1007\/s11517-026-03547-7","relation":{},"ISSN":["0140-0118","1741-0444"],"issn-type":[{"value":"0140-0118","type":"print"},{"value":"1741-0444","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,13]]},"assertion":[{"value":"8 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2026","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 study protocol was approved by the Ethical Committee for Non-Invasive Clinical Research at Kocaeli University (Decision No: K\u00dc GOKAEK-2024\/13.09). The study was carried out according to the principles outlined in the Declaration of Helsinki. Informed consent was obtained from all participants, and no procedures involving intervention or invasion of patient privacy were performed.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"The authors declare no conflict of interest. All authors have reviewed and approved the submitted version of the manuscript.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}]}}