{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T05:46:28Z","timestamp":1782452788815,"version":"3.54.5"},"reference-count":30,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Extrapyramidal symptoms (EPS) are motor side effects commonly induced by antipsychotic medications and can lead to measurable changes in handwriting patterns. These symptoms affect both the spatial and temporal characteristics of writing, including stroke thickness, direction and the rate of directional change. To model these complex variations, we propose a novel Liquid Generative Adversarial Network (LiquidGAN), which combines the adaptive dynamics of liquid neural networks with the data generation capability of GANs. Handwriting data were collected from 94 patients with confirmed EPS and 30 healthy controls using Archimedean spiral patterns drawn with both hands. A total of 211 images were processed for both binary and multiclass classification using a pretrained ResNet50 model. The pretrained ResNet50 achieved 92% accuracy and 97% precision in the binary classification task; however, its performance dropped significantly to 57% accuracy in multiclass classification, indicating limited capability in capturing fine-grained EPS severity variations. In contrast, the proposed LiquidGAN demonstrated excellent performance in the binary classification task, achieving 97% accuracy and 98% precision. More importantly, LiquidGAN substantially outperformed the baseline in the more challenging multiclass setting, achieving 70% accuracy and precision across four classes (mild, moderate, severe, and control). This shows that the diverse dataset from the liquidGAN significantly improves the HOG-ANN classification and effectively captures complex and subtle handwriting variations associated with different EPS severity levels that conventional models such as ResNet50 fail to distinguish. In addition, LiquidGAN generated diverse and realistic synthetic handwriting samples, yielding improved Fr\u00e9chet Inception Distance (FID), precision, and recall compared with style GAN. These findings demonstrate that handwriting biomarkers, when analyzed through dynamic generative learning, offer an effective and non-invasive approach for monitoring extrapyramidal side effects in clinical settings.<\/jats:p>","DOI":"10.3390\/s26123890","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T13:04:04Z","timestamp":1781874244000},"page":"3890","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LiquidGAN for Handwriting-Based Detection and Severity Classification of Extrapyramidal Symptoms"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0639-2490","authenticated-orcid":false,"given":"Erandhi M.","family":"Liyanage","sequence":"first","affiliation":[{"name":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW 2007, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8125-4306","authenticated-orcid":false,"given":"Chun-Hung","family":"Lee","sequence":"additional","affiliation":[{"name":"Jianan Psychiatric Center Ministry of Health and Welfare, Tainan City 701, Taiwan"},{"name":"Taoyuan Psychiatric Center, Ministry of Health and Welfare, Taoyuan City 330, Taiwan"},{"name":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan City 701, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8744-3004","authenticated-orcid":false,"given":"Wen-Yen","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan City 701, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew An-Zhe","family":"Lee","sequence":"additional","affiliation":[{"name":"Taoyuan Psychiatric Center, Ministry of Health and Welfare, Taoyuan City 330, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guan-Hsiung","family":"Liaw","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, I-Shou University, Kaohsiung City 800, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wu-Chuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, I-Shou University, Kaohsiung City 800, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Hsin","family":"Liu","sequence":"additional","affiliation":[{"name":"Florence Nightingale School of Nursing & Midwifery, King\u2019s College London, London WC2R 2LS, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun-Chan","family":"Lan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan City 701, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0849-5098","authenticated-orcid":false,"given":"Sai Ho","family":"Ling","sequence":"additional","affiliation":[{"name":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW 2007, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1016\/j.biopsych.2023.04.004","article-title":"Data-Driven Taxonomy for Antipsychotic Medication: A New Classification System","volume":"94","author":"McCutcheon","year":"2023","journal-title":"Biol. Psychiatry"},{"key":"ref_2","unstructured":"D\u2019Souza, R.S., Aslam, S.P., and Hooten, H.W. (2024). Extrapyramidal Side Effects. StatPearls, StatPearls Publishing."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1038\/s41531-025-00907-2","article-title":"Systematic review and consensus conceptual model of meaningful symptoms and functional impacts in early Parkinson\u2019s Disease","volume":"11","author":"Mammen","year":"2025","journal-title":"npj Park. Dis."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"384","DOI":"10.5694\/mja17.01085","article-title":"James Parkinson\u2019s Essay on the shaking palsy, 1817\u20132017","volume":"208","author":"Toodayan","year":"2018","journal-title":"Med. J. Aust."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1177\/0269881107087976","article-title":"A new self-rating scale for detecting atypical or second-generation antipsychotic side effects","volume":"22","author":"Waddell","year":"2008","journal-title":"J. Psychopharmacol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1354","DOI":"10.1002\/mds.10255","article-title":"Metric characteristics of the drug-induced extrapyramidal symptoms scale (DIEPSS): A practical combined rating scale for drug-induced movement disorders","volume":"17","author":"Kim","year":"2002","journal-title":"Mov. Disord."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Crespo, Y., Iba\u00f1ez, A., Soriano, M.F., Iglesias, S., and Aznarte, J.I. (2019). Handwriting movements for assessment of motor symptoms in schizophrenia spectrum disorders and bipolar disorder. PLoS ONE, 14.","DOI":"10.1371\/journal.pone.0213657"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1136\/practneurol-2017-001719","article-title":"How to use pen and paper tasks to aid tremor diagnosis in the clinic","volume":"17","author":"Alty","year":"2017","journal-title":"Pract. Neurol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/S0379-0738(97)00105-9","article-title":"Handwriting changes due to aging and Parkinson\u2019s syndrome","volume":"88","author":"Walton","year":"1997","journal-title":"Forensic Sci. Int."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Saetee, P., Rueangrong, T., Chanwimalueang, T., Jampa-ngern, S., Methawasin, K., and Tantisatirapong, S. (2024). Enhanced Diagnosis of Parkinson\u2019s Disease Using Digitized Archimedean Spiral Handwriting Analysis. Proceedings of the Biomedical Engineering International Conference, IEEE.","DOI":"10.1109\/BMEiCON64021.2024.10896271"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1742","DOI":"10.1002\/mdc3.70278","article-title":"Clinical Applications and Measurement Properties of the Digitized Archimedes Spiral Drawing Test: A Scoping Review","volume":"12","author":"Wang","year":"2025","journal-title":"Mov. Disord. Clin. Pract."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Huang, Y., Chaturvedi, K., Nayan, A.A., Hesamian, M.H., Braytee, A., and Prasad, M. (2024). Early Parkinson\u2019s Disease Diagnosis through Hand-Drawn Spiral and Wave Analysis Using Deep Learning Techniques. Information, 15.","DOI":"10.3390\/info15040220"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Wu, E., Leng, P., Sun, J., Ma, M., and Pan, Z. (2025). Finger drawing on smartphone screens enables early Parkinson\u2019s disease detection through hybrid 1D-CNN and BiGRU deep learning architecture. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0327733"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1002\/mds.870131308","article-title":"Overview of Human Tremor Physiology","volume":"13","author":"Hallett","year":"2008","journal-title":"Mov. Disord."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1007\/s42979-026-04929-2","article-title":"Cure-Net: A Deep Learning Framework for the Proactive Detection of Parkinson\u2019s Disease via Automated Handwriting Analysis","volume":"7","author":"Kumar","year":"2026","journal-title":"SN Comput. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wysoki\u0144ski, A., and Zwierzchowska-Kieszek, A. (2024). EDEPS (Early Detection of ExtraPyramidal Symptoms): Supervised machine learning models to detect antipsychotics-induced extrapyramidal hand tremor from a mobile device built-in sensors. medRxiv, 2024-12.","DOI":"10.1101\/2024.12.16.24319069"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"ref_18","first-page":"852","article-title":"Alias-Free Generative Adversarial Networks","volume":"Volume 34","author":"Ranzato","year":"2021","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref_19","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016). Improved Techniques for Training GANs. arXiv."},{"key":"ref_20","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., and Hochreiter, S. (2017). GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Kumar, K., Verma, A., Gupta, N., and Yadav, A. (2023). Liquid Neural Networks: A Novel Approach to Dynamic Information Processing. Proceedings of the 2023 International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT), IEEE.","DOI":"10.1109\/ICAICCIT60255.2023.10466162"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Bansal, K., and Kumar, R. (2013). K-Algorithm A Modified Technique for Noise Removal in Handwritten Documents. arXiv.","DOI":"10.5121\/ijist.2013.3301"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.neunet.2019.04.024","article-title":"Deep neural network concepts for background subtraction:A systematic review and comparative evaluation","volume":"117","author":"Bouwmans","year":"2019","journal-title":"Neural Netw."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Ozaydin, U., Georgiou, T., and Lew, M. (2019). A Comparison of CNN and Classic Features for Image Retrieval. Proceedings of the International Workshop on Content-Based Multimedia Indexing, IEEE.","DOI":"10.1109\/CBMI.2019.8877470"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.psychres.2009.07.005","article-title":"Handwriting movement kinematics for quantifying extrapyramidal side effects in patients treated with atypical antipsychotics","volume":"177","author":"Caligiuri","year":"2010","journal-title":"Psychiatry Res."},{"key":"ref_26","unstructured":"Ngiam, J., Peng, D., Vasudevan, V., Kornblith, S., Le, Q.V., and Pang, R. (2018). Domain Adaptive Transfer Learning with Specialist Models. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Hinke-Navarro, A., Nieto-Hidalgo, M., Espin, J.M., and Tapia, J.E. (2025). Enhanced Deep Learning DeepFake Detection Integrating Handcrafted Features, Springer Nature.","DOI":"10.1007\/978-3-032-04968-1_6"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"886","DOI":"10.1109\/CVPR.2005.177","article-title":"Histograms of oriented gradients for human detection","volume":"Volume 1","author":"Dalal","year":"2005","journal-title":"Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905)"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1080\/00220973.1990.10806527","article-title":"Perceptual-Motor Complexity of Printed and Cursive Letters","volume":"58","author":"Meulenbroek","year":"1990","journal-title":"J. Exp. Educ."},{"key":"ref_30","first-page":"100410","article-title":"Dystonic tremor in Writer\u2019s cramp Mimicking primary handwriting tremor","volume":"13","author":"Cataniag","year":"2025","journal-title":"Clin. Park. Relat. Disord."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3890\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T04:57:37Z","timestamp":1782449857000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3890"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,18]]},"references-count":30,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["s26123890"],"URL":"https:\/\/doi.org\/10.3390\/s26123890","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,18]]}}}