{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T17:14:37Z","timestamp":1794071677829,"version":"4.8.0"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T00:00:00Z","timestamp":1783123200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"vor","delay-in-days":93,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Parkinson\u2019s disease (PD) affects fine motor control and produces measurable abnormalities in handwriting and drawing. This study proposes a rigorously evaluated multimodal framework for PD detection that combines a Vision Transformer (ViT) for spiral and meander image analysis with an XGBoost classifier operating on 54 carefully engineered kinematic features extracted from multichannel handwriting signals. To assess how multimodal integration should be performed, both intermediate feature-level fusion and late decision-level fusion were evaluated under a strict 5-fold subject-wise cross-validation protocol, with supplementary sample-level analysis, on the NewHandPD dataset. The visual stream consistently outperformed the acquisition stream as a single modality, while both fusion strategies improved performance by exploiting complementary spatial (visual) and motor information. Intermediate fusion achieved the highest apparent discriminative performance, reaching 97.7% accuracy on spiral drawings and 98.5% accuracy on meander drawings, whereas late fusion provided more interpretable and modular behavior, with best subject-level results of 93.94% accuracy and AUC\u2009=\u20090.9687 for spiral, and 92.42% accuracy with AUC\u2009=\u20090.9770 for meander. These findings suggest that multimodal handwriting analysis can be an effective approach for Parkinson\u2019s disease detection on the NewHandPD dataset, although further validation on larger and independent cohorts is required.<\/jats:p>","DOI":"10.1038\/s41598-026-57147-4","type":"journal-article","created":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T09:46:24Z","timestamp":1783158384000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal fusion of handwriting images and kinematic features for Parkinson disease detection"],"prefix":"10.1038","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6137-4642","authenticated-orcid":false,"given":"Ameur","family":"Bensefia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8941-8440","authenticated-orcid":false,"given":"Nafeth","family":"Al Hashlamoun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Komal Kumar","family":"Napa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,4]]},"reference":[{"issue":"1","key":"57147_CR1","doi-asserted-by":"publisher","first-page":"17013","DOI":"10.1038\/nrdp.2017.13","volume":"3","author":"W Poewe","year":"2017","unstructured":"Poewe, W. et al. Parkinson disease. Nat. Rev. Dis. Primers. 3 (1), 17013. https:\/\/doi.org\/10.1038\/nrdp.2017.13 (2017).","journal-title":"Nat. Rev. Dis. Primers"},{"key":"57147_CR2","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1016\/j.neubiorev.2016.07.010","volume":"68","author":"AA Moustafa","year":"2016","unstructured":"Moustafa, A. A. et al. Motor symptoms in Parkinson\u2019s disease: A unified framework. Neurosci. Biobehav Rev. 68, 727\u2013740. https:\/\/doi.org\/10.1016\/j.neubiorev.2016.07.010 (2016).","journal-title":"Neurosci. Biobehav Rev."},{"key":"57147_CR3","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1007\/978-3-030-71804-6_14","volume-title":"Pattern Recognition and Artificial Intelligence","author":"F Abbas","year":"2021","unstructured":"Abbas, F. et al. Offline Writer Identification Based on CLBP and VLBP. In Pattern Recognition and Artificial Intelligence (eds Djeddi, C., Kessentini, Y., Siddiqi, I., Jmaiel, M. et al.) 188\u2013199 (Springer International Publishing, 2021)."},{"key":"57147_CR4","doi-asserted-by":"publisher","unstructured":"Arraziqi, D., Sardjono, T. A., Miawarni, H. & Purnomo, M. H. Detection of Parkinson\u2019s Disease at The Level of Motor Experiences of Daily Living Using Spiral Handwriting. In 2020\u00a0International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM), 39\u201346 (2020). https:\/\/doi.org\/10.1109\/CENIM51130.2020.9297932","DOI":"10.1109\/CENIM51130.2020.9297932"},{"issue":"2","key":"57147_CR5","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D. G. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110. https:\/\/doi.org\/10.1023\/B:VISI.0000029664.99615.94 (2004).","journal-title":"Int. J. Comput. Vis."},{"key":"57147_CR6","doi-asserted-by":"crossref","unstructured":"Mitra, S., Mohan Pandey, P., Pandey, V., Sharma, T. & Nair, R. A Fine-Tuned Transfer Learning Approach for Parkinson\u2019s Disease Detection on New Hand PD Dataset. In Botto-Tobar, M., Zambrano Vizuete, M., Montes Le\u00f3n, S., Torres-Carri\u00f3n, P., & Durakovic, B. (Eds.) International Conference on Applied Technologies, Springer Nature Switzerland, Cham, 86\u201398 (2024).","DOI":"10.1007\/978-3-031-58953-9_7"},{"issue":"2","key":"57147_CR7","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1007\/s41870-023-01601-3","volume":"16","author":"S Agrawal","year":"2024","unstructured":"Agrawal, S. & Sahu, S. P. Image-based Parkinson disease detection using deep transfer learning and optimization algorithm. Int. J. Inform. Technol. 16 (2), 871\u2013879. https:\/\/doi.org\/10.1007\/s41870-023-01601-3 (2024).","journal-title":"Int. J. Inform. Technol."},{"issue":"9","key":"57147_CR8","doi-asserted-by":"publisher","first-page":"2686","DOI":"10.1049\/ipr2.12820","volume":"17","author":"N Wang","year":"2023","unstructured":"Wang, N. et al. A coordinate attention enhanced swin transformer for handwriting recognition of Parkinson\u2019s disease. IET Image Process. 17 (9), 2686\u20132697. https:\/\/doi.org\/10.1049\/ipr2.12820 (2023).","journal-title":"IET Image Process."},{"key":"57147_CR9","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1016\/j.future.2020.11.020","volume":"117","author":"I Kamran","year":"2021","unstructured":"Kamran, I., Naz, S., Razzak, I. & Imran, M. Handwriting dynamics assessment using deep neural network for early identification of Parkinson\u2019s disease. Future Generation Comput. Syst. 117, 234\u2013244. https:\/\/doi.org\/10.1016\/j.future.2020.11.020 (2021).","journal-title":"Future Generation Comput. Syst."},{"key":"57147_CR10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3337804","author":"S Naz","year":"2023","unstructured":"Naz, S., Kamran, I., Gul, S., Hadi, F. & Khalifa, F. Multi-model fusion of CNNs for identification of Parkinson\u2019s disease using handwritten samples. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2023.3337804 (2023).","journal-title":"IEEE Access."},{"issue":"9","key":"57147_CR11","doi-asserted-by":"publisher","first-page":"2686","DOI":"10.1049\/ipr2.12820","volume":"17","author":"N Wang","year":"2023","unstructured":"Wang, N. et al. A coordinate attention enhanced swin transformer for handwriting recognition of Parkinson\u2019s disease. IET Image Process. 17(9), 2686\u20132697. https:\/\/doi.org\/10.1049\/ipr2.12820 (2023).","journal-title":"IET Image Process."},{"key":"57147_CR12","doi-asserted-by":"publisher","unstructured":"Bensefia, A., Zarrad, A. & Hashalamon, N. A. Vision Transformer-Based Classification of Parkinson\u2019s Disease Using Hand-Drawn Spiral Patterns. In 2025 10th International Conference on Information Technology Trends (ITT), 25\u201330 (2025). https:\/\/doi.org\/10.1109\/ITT69610.2025.11352923","DOI":"10.1109\/ITT69610.2025.11352923"},{"key":"57147_CR13","doi-asserted-by":"publisher","first-page":"103551","DOI":"10.1016\/j.bspc.2022.103551","volume":"75","author":"E Valla","year":"2022","unstructured":"Valla, E., N\u00f5mm, S., Medijainen, K., Taba, P. & Toomela, A. Tremor-related feature engineering for machine learning based Parkinson\u2019s disease diagnostics. Biomed. Signal. Process. Control. 75, 103551. https:\/\/doi.org\/10.1016\/j.bspc.2022.103551 (2022).","journal-title":"Biomed. Signal. Process. Control"},{"issue":"3","key":"57147_CR14","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/s40860-021-00130-9","volume":"7","author":"R Lamba","year":"2021","unstructured":"Lamba, R., Gulati, T., Al-Dhlan, K. A. & Jain, A. A systematic approach to diagnose Parkinson\u2019s disease through kinematic features extracted from handwritten drawings. J. Reliab. Intell. Environ. 7 (3), 253\u2013262. https:\/\/doi.org\/10.1007\/s40860-021-00130-9 (2021).","journal-title":"J. Reliab. Intell. Environ."},{"key":"57147_CR15","doi-asserted-by":"publisher","first-page":"104283","DOI":"10.1016\/j.ijmedinf.2020.104283","volume":"144","author":"S Xu","year":"2020","unstructured":"Xu, S. & Pan, Z. A novel ensemble of random forest for assisting diagnosis of Parkinson\u2019s disease on small handwritten dynamics dataset. Int. J. Med. Inf. 144, 104283. https:\/\/doi.org\/10.1016\/j.ijmedinf.2020.104283 (2020).","journal-title":"Int. J. Med. Inf."},{"issue":"3","key":"57147_CR16","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1109\/TNSRE.2014.2359997","volume":"23","author":"P Drot\u00e1r","year":"2015","unstructured":"Drot\u00e1r, P. et al. Decision Support Framework for Parkinson\u2019s Disease Based on Novel Handwriting Markers. IEEE Trans. Neural Syst. Rehabil. Eng. 23 (3), 508\u2013516. https:\/\/doi.org\/10.1109\/TNSRE.2014.2359997 (2015).","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"57147_CR17","doi-asserted-by":"publisher","first-page":"114405","DOI":"10.1016\/j.eswa.2020.114405","volume":"168","author":"M Diaz","year":"2021","unstructured":"Diaz, M., Moetesum, M., Siddiqi, I. & Vessio, G. Sequence-based dynamic handwriting analysis for Parkinson\u2019s disease detection with one-dimensional convolutions and BiGRUs. Expert Syst. Appl. 168, 114405. https:\/\/doi.org\/10.1016\/j.eswa.2020.114405 (2021).","journal-title":"Expert Syst. Appl."},{"key":"57147_CR18","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1016\/j.patrec.2019.08.018","volume":"128","author":"M Diaz","year":"2019","unstructured":"Diaz, M., Ferrer, M. A., Impedovo, D., Pirlo, G. & Vessio, G. Dynamically enhanced static handwriting representation for Parkinson\u2019s disease detection. Pattern Recognit. Lett. 128, 204\u2013210. https:\/\/doi.org\/10.1016\/j.patrec.2019.08.018 (2019).","journal-title":"Pattern Recognit. Lett."},{"issue":"5","key":"57147_CR19","doi-asserted-by":"publisher","first-page":"28157","DOI":"10.48084\/etasr.12833","volume":"15","author":"A Louja","year":"2025","unstructured":"Louja, A., Zaiouane, Y., Jamali, A. & Naja, N. DS-HViT: A dual-stream hierarchical vision transformer for multi-scale analysis of Parkinson\u2019s disease handwriting. Eng. Technol. Appl. Sci. Res. 15(5), 28157\u201328164. https:\/\/doi.org\/10.48084\/etasr.12833 (2025).","journal-title":"Eng. Technol. Appl. Sci. Res."},{"key":"57147_CR20","doi-asserted-by":"publisher","unstructured":"Chen, T. & Guestrin, C. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, in KDD \u201916. New York, NY, USA: Association for Computing Machinery, 785\u2013794 (2016). https:\/\/doi.org\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"57147_CR21","doi-asserted-by":"crossref","unstructured":"Kadem, M., Noseworthy, M. D. & Doyle, T. E. XGBoost for Interpretable Alzheimer\u2019s Decision Support. In\u00a0Proceedings of the AAAI Symposium Series. (2023).\u00a0https:\/\/api.semanticscholar.org\/CorpusID:265139573","DOI":"10.1609\/aaaiss.v1i1.27491"},{"issue":"13","key":"57147_CR22","doi-asserted-by":"publisher","first-page":"1268","DOI":"10.1007\/s11227-025-07744-3","volume":"81","author":"A Louja","year":"2025","unstructured":"Louja, A., Drira, I., Jamali, A., Naja, N. & Sliman, L. Wearable sensor-based eye-rubbing monitoring: a hybrid CNN-attentionrub architecture for keratoconus prevention. J. Supercomput. 81 (13), 1268. https:\/\/doi.org\/10.1007\/s11227-025-07744-3 (2025).","journal-title":"J. Supercomput"},{"key":"57147_CR23","doi-asserted-by":"publisher","unstructured":"Pereira, C. R., Weber, S. A. T., Hook, C., Rosa, G. H. & Papa, J. P. Deep Learning-Aided Parkinson\u2019s Disease Diagnosis from Handwritten Dynamics. In 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 340\u2013346 (2016). https:\/\/doi.org\/10.1109\/SIBGRAPI.2016.054","DOI":"10.1109\/SIBGRAPI.2016.054"},{"key":"57147_CR24","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.cmpb.2016.08.005","volume":"136","author":"CR Pereira","year":"2016","unstructured":"Pereira, C. R. et al. A new computer vision-based approach to aid the diagnosis of Parkinson\u2019s disease. Comput. Methods Programs Biomed. 136, 79\u201388. https:\/\/doi.org\/10.1016\/j.cmpb.2016.08.005 (2016).","journal-title":"Comput. Methods Programs Biomed."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-57147-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-57147-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-57147-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T23:11:31Z","timestamp":1791155491000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-57147-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,4]]},"references-count":24,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["57147"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-57147-4","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,4]]},"assertion":[{"value":"8 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"30752"}}