{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T16:56:47Z","timestamp":1791046607197,"version":"4.1.0"},"reference-count":49,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T00:00:00Z","timestamp":1752451200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LZ21F020008"],"award-info":[{"award-number":["LZ21F020008"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013139","name":"Humanities and Social Science Fund of Ministry of Education of China","doi-asserted-by":"publisher","award":["24YJAZH131"],"award-info":[{"award-number":["24YJAZH131"]}],"id":[{"id":"10.13039\/501100013139","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec023\">\n<jats:title>Background<\/jats:title>\n<jats:p>Parkinson\u2019s disease (PD), a progressive neurodegenerative disorder prevalent in aging populations, manifests clinically through characteristic motor impairments including bradykinesia, rigidity, and resting tremor. Early detection and timely intervention may delay disease progression. Spiral drawing tasks have been established as effective auxiliary diagnostic tools. This study developed a hybrid deep learning model to analyze motion data from finger drawings of spiral and wave lines on smartphone screens, aiming to detect early Parkinson\u2019s disease.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec024\">\n<jats:title>Methods<\/jats:title>\n<jats:p>We recruited 58 age-matched participants (28 early idiopathic PD patients: 68.4\u2009\u00b1\u20095.7 years; 30 healthy controls: 68.0\u2009\u00b1\u20094.5 years) for two smartphone-based drawing tasks (spiral and wave). A custom-developed app recorded finger touch coordinates, instantaneous movement speed, and timestamps at a sampling frequency of 60 Hz. Our hybrid model combined multi-scale convolutional feature extraction (using parallel 1D-Convolutional branches) with bidirectional temporal pattern recognition (via gated recurrent unit [GRU] networks) to analyze movement abnormalities and detect the disease.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec025\">\n<jats:title>Results<\/jats:title>\n<jats:p>The proposed model demonstrated robust diagnostic performance, achieving a cross-validation accuracy of 87.93% for spiral drawings (89.64% sensitivity, 86.33% specificity). Wave drawings yielded 87.24% accuracy (86.79% sensitivity, 87.67% specificity). The integration of both tasks achieved 91.20% accuracy (95% CI: 89.2%\u221293.2%) with balanced sensitivity (91.43%) and specificity (91.00%).<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec026\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>This study establishes the technical feasibility of a hybrid deep learning framework for early PD detection using smartphone-captured finger motion dynamics. The developed model effectively combines one-dimensional convolutional neural networks with bidirectional GRUs to analyze drawing tasks. Distinct from existing approaches that rely on clinical rating scales, neuroimaging modalities, or stylus-based digital assessments, this telemedicine-compatible method requires only bare-finger interactions on consumer-grade smartphones and enables operator-independent assessments. Furthermore, it facilitates cost-effective and convenient PD assessment in remote healthcare and patient monitoring, particularly in resource-limited settings.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0327733","type":"journal-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T17:26:58Z","timestamp":1752514018000},"page":"e0327733","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":12,"title":["Finger drawing on smartphone screens enables early Parkinson\u2019s disease detection through hybrid 1D-CNN and BiGRU deep learning architecture"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8494-0152","authenticated-orcid":true,"given":"Zhaohui","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"E","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Leng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingming","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhigeng","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,7,14]]},"reference":[{"issue":"1","key":"pone.0327733.ref001","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1111\/ene.14108","article-title":"Parkinson disease","volume":"27","author":"R Balestrino","year":"2020","journal-title":"Eur J Neurol"},{"key":"pone.0327733.ref002","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1111\/jnc.13691","article-title":"The clinical symptoms of Parkinson\u2019s disease","author":"S Sveinbjornsdottir","year":"2016","journal-title":"J Neurochem"},{"key":"pone.0327733.ref003","article-title":"Early diagnosis of Parkinson\u2019s disease","author":"G Becker","year":"2002","journal-title":"J Neurol"},{"issue":"10","key":"pone.0327733.ref004","doi-asserted-by":"crossref","first-page":"1551","DOI":"10.1002\/mds.27485","article-title":"Importance of low diagnostic Accuracy for early Parkinson\u2019s disease","volume":"33","author":"TG Beach","year":"2018","journal-title":"Movement Disorders"},{"issue":"1","key":"pone.0327733.ref005","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40658-024-00651-1","article-title":"Radiomics incorporating deep features for predicting Parkinson\u2019s disease in 123I-Ioflupane SPECT","volume":"11","author":"H Jiang","year":"2024","journal-title":"EJNMMI Phys"},{"issue":"12","key":"pone.0327733.ref006","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e32947","article-title":"Facial emotion recognition and judgment of affective scenes in Parkinson\u2019s disease","volume":"10","author":"F Salfi","year":"2024","journal-title":"Heliyon"},{"issue":"1","key":"pone.0327733.ref007","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1186\/s12984-021-00932-1","article-title":"Muscle activation strategies of people with early-stage Parkinson\u2019s during walking","volume":"18","author":"SM Keloth","year":"2021","journal-title":"J Neuroeng Rehabil"},{"issue":"20","key":"pone.0327733.ref008","doi-asserted-by":"crossref","first-page":"5963","DOI":"10.3390\/s20205963","article-title":"Quantification of Arm Swing during Walking in Healthy Adults and Parkinson\u2019s Disease Patients: Wearable Sensor-Based Algorithm Development and Validation","volume":"20","author":"E Warmerdam","year":"2020","journal-title":"Sensors (Basel)"},{"key":"pone.0327733.ref009","doi-asserted-by":"crossref","first-page":"668291","DOI":"10.3389\/fpsyg.2021.668291","article-title":"Speech Rhythm Variation in Early-Stage Parkinson\u2019s Disease: A Study on Different Speaking Tasks","volume":"12","author":"M Maffia","year":"2021","journal-title":"Front Psychol"},{"key":"pone.0327733.ref010","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1186\/s12911-019-0989-3","article-title":"Biometric handwriting analysis to support Parkinson\u2019s Disease assessment and grading","volume":"19","author":"GD Cascarano","year":"2019","journal-title":"BMC Med Inform Decis Mak"},{"key":"pone.0327733.ref011","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.patrec.2019.08.018","article-title":"Dynamically enhanced static handwriting representation for Parkinson\u2019s disease detection","volume":"128","author":"M Diaz","year":"2019","journal-title":"Pattern Recognition Letters"},{"key":"pone.0327733.ref012","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/j.artmed.2016.01.004","article-title":"Evaluation of handwriting kinematics and pressure for differential diagnosis of Parkinson\u2019s disease","volume":"67","author":"P Drot\u00e1r","year":"2016","journal-title":"Artif Intell Med"},{"issue":"5","key":"pone.0327733.ref013","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0097614","article-title":"Standardized handwriting to assess bradykinesia, micrographia and tremor in Parkinson\u2019s disease","volume":"9","author":"EJ Smits","year":"2014","journal-title":"PLoS One"},{"key":"pone.0327733.ref014","doi-asserted-by":"crossref","first-page":"106220","DOI":"10.1016\/j.bspc.2024.106220","article-title":"Cosine deep convolutional neural network for Parkinson\u2019s disease detection and severity level classification using hand drawing spiral image in IoT platform","volume":"94","author":"S Pragadeeswaran","year":"2024","journal-title":"Biomedical Signal Processing and Control"},{"issue":"10","key":"pone.0327733.ref015","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0162799","article-title":"Digitized Spiral Drawing: A Possible Biomarker for Early Parkinson\u2019s Disease","volume":"11","author":"M San Luciano","year":"2016","journal-title":"PLoS One"},{"key":"pone.0327733.ref016","doi-asserted-by":"crossref","first-page":"1093690","DOI":"10.3389\/fneur.2023.1093690","article-title":"Spiral drawing analysis with a smart ink pen to identify Parkinson\u2019s disease fine motor deficits","volume":"14","author":"S Toffoli","year":"2023","journal-title":"Front Neurol"},{"key":"pone.0327733.ref017","doi-asserted-by":"crossref","DOI":"10.1109\/CBMS.2015.34","article-title":"A step towards the automated diagnosis of parkinson\u2019s disease: analyzing handwriting movements","volume-title":"Proc IEEE Symp Comput-Based Med Syst.","author":"CR Pereira","year":"2015"},{"key":"pone.0327733.ref018","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.cmpb.2016.08.005","article-title":"A new computer vision-based approach to aid the diagnosis of Parkinson\u2019s disease","volume":"136","author":"CR Pereira","year":"2016","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0327733.ref019","doi-asserted-by":"crossref","first-page":"108066","DOI":"10.1016\/j.cmpb.2024.108066","article-title":"LSTM-CNN: An efficient diagnostic network for Parkinson\u2019s disease utilizing dynamic handwriting analysis","volume":"247","author":"X Wang","year":"2024","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0327733.ref020","doi-asserted-by":"crossref","first-page":"104283","DOI":"10.1016\/j.ijmedinf.2020.104283","article-title":"A novel ensemble of random forest for assisting diagnosis of Parkinson\u2019s disease on small handwritten dynamics dataset","volume":"144","author":"S Xu","year":"2020","journal-title":"Int J Med Inform"},{"issue":"11","key":"pone.0327733.ref021","doi-asserted-by":"crossref","DOI":"10.2196\/21543","article-title":"Smartphone-Based Monitoring of Parkinson Disease: Quasi-Experimental Study to Quantify Hand Tremor Severity and Medication Effectiveness","volume":"8","author":"E Kuosmanen","year":"2020","journal-title":"JMIR Mhealth Uhealth"},{"key":"pone.0327733.ref022","doi-asserted-by":"crossref","DOI":"10.1145\/3313831.3376864","article-title":"Let\u2019s Draw: Detecting and Measuring Parkinson\u2019s Disease on Smartphones","volume-title":". Conf Hum Fact Comput Syst Proc","author":"E Kuosmanen","year":"2020"},{"key":"pone.0327733.ref023","doi-asserted-by":"crossref","first-page":"861668","DOI":"10.3389\/fnins.2022.861668","article-title":"Tremor evaluation using smartphone accelerometry in standardized settings","volume":"16","author":"G Sahin","year":"2022","journal-title":"Front Neurosci"},{"issue":"8","key":"pone.0327733.ref024","doi-asserted-by":"crossref","first-page":"3848","DOI":"10.1109\/JBHI.2022.3162386","article-title":"Vision-Based Finger Tapping Test in Patients With Parkinson\u2019s Disease via Spatial-Temporal 3D Hand Pose Estimation","volume":"26","author":"Z Guo","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"pone.0327733.ref025","doi-asserted-by":"crossref","first-page":"110002","DOI":"10.1016\/j.compeleceng.2024.110002","article-title":"Internet of thing-based hand tremor monitoring system and automated detection of hand tremor frequency","volume":"122","author":"M \u00d6nder","year":"2025","journal-title":"Computers and Electrical Engineering"},{"issue":"1","key":"pone.0327733.ref026","article-title":"A novel feature extraction method based on dynamic handwriting for Parkinson\u2019s disease detection","volume":"20","author":"H Lu","year":"2025","journal-title":"PLoS One"},{"issue":"3","key":"pone.0327733.ref027","doi-asserted-by":"crossref","first-page":"381","DOI":"10.3390\/diagnostics15030381","article-title":"Towards Parkinson\u2019s Disease Detection Through Analysis of Everyday Handwriting","volume":"15","author":"JD Gallo-Aristizabal","year":"2025","journal-title":"Diagnostics (Basel)"},{"issue":"1","key":"pone.0327733.ref028","doi-asserted-by":"crossref","DOI":"10.1002\/ima.22948","article-title":"Diagnosing of Parkinson\u2019s disease based on hand drawing analysis using Bi\u2010Directional LSTM equipped with fuzzy inferential soft\u2010max classifier","volume":"34","author":"E Ramzani","year":"2023","journal-title":"Int J Imaging Syst Tech"},{"key":"pone.0327733.ref029","doi-asserted-by":"crossref","first-page":"114405","DOI":"10.1016\/j.eswa.2020.114405","article-title":"Sequence-based dynamic handwriting analysis for Parkinson\u2019s disease detection with one-dimensional convolutions and BiGRUs","volume":"168","author":"M Diaz","year":"2021","journal-title":"Expert Syst Appl"},{"key":"pone.0327733.ref030","doi-asserted-by":"crossref","first-page":"101984","DOI":"10.1016\/j.artmed.2020.101984","article-title":"Cartesian genetic programming for diagnosis of Parkinson disease through handwriting analysis: Performance vs. interpretability issues","volume":"111","author":"A Parziale","year":"2021","journal-title":"Artif Intell Med"},{"key":"pone.0327733.ref031","article-title":"Deep Learning-Aided Parkinson\u2019s Disease Diagnosis from Handwritten Dynamics","author":"CR Pereira","year":"2016","journal-title":"Proc - SIBGRAPI Conf Graph, Patterns Images, SIBGRAPI"},{"key":"pone.0327733.ref032","doi-asserted-by":"crossref","first-page":"3603","DOI":"10.1109\/TNSRE.2024.3462392","article-title":"Early Detection of Parkinson\u2019s Disease Using Deep NeuroEnhanceNet With Smartphone Walking Recordings","volume":"32","author":"T He","year":"2024","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"issue":"1","key":"pone.0327733.ref033","doi-asserted-by":"crossref","DOI":"10.1155\/2023\/9921809","article-title":"A Spatio\u2010Temporal Siamese Neural Network for Multimodal Handwriting Abnormality Screening of Parkinson\u2019s Disease","volume":"2023","author":"A Zhao","year":"2023","journal-title":"International Journal of Intelligent Systems"},{"issue":"9","key":"pone.0327733.ref034","doi-asserted-by":"crossref","first-page":"1020","DOI":"10.1002\/mds.20213","article-title":"Movement Disorder Society Task Force report on the Hoehn and Yahr staging scale: status and recommendations","volume":"19","author":"CG Goetz","year":"2004","journal-title":"Mov Disord"},{"issue":"7553","key":"pone.0327733.ref035","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Y LeCun","year":"2015","journal-title":"Nature"},{"key":"pone.0327733.ref036","article-title":"Xception: Deep Learning with Depthwise Separable Convolutions","author":"F Chollet","year":"2017","journal-title":"Proc IEEE Comput Soc Conf Comput Vision Pattern Recognit"},{"key":"pone.0327733.ref037","doi-asserted-by":"crossref","first-page":"105305","DOI":"10.1016\/j.cmpb.2019.105305","article-title":"An improved sex-specific and age-dependent classification model for Parkinson\u2019s diagnosis using handwriting measurement","volume":"189","author":"U Gupta","year":"2020","journal-title":"Comput Methods Programs Biomed"},{"issue":"24","key":"pone.0327733.ref038","doi-asserted-by":"crossref","first-page":"1976","DOI":"10.1049\/el.2016.3113","article-title":"Mobile application of finger tapping task assessment for early diagnosis of Parkinson\u2019s disease","volume":"52","author":"U Lee","year":"2016","journal-title":"Electronics Letters"},{"issue":"20","key":"pone.0327733.ref039","doi-asserted-by":"crossref","first-page":"33207","DOI":"10.1109\/JSEN.2024.3452092","article-title":"Smartphone-Based Detection of Early Parkinson\u2019s Disease With Tapping Records and a Multimodal-Multiscale Ensemble Network","volume":"24","author":"T He","year":"2024","journal-title":"IEEE Sensors J"},{"key":"pone.0327733.ref040","doi-asserted-by":"crossref","first-page":"105021","DOI":"10.1016\/j.compbiomed.2021.105021","article-title":"Convolutional neural network ensemble for Parkinson\u2019s disease detection from voice recordings","volume":"141","author":"M Hire\u0161","year":"2022","journal-title":"Comput Biol Med"},{"key":"pone.0327733.ref041","first-page":"1","article-title":"Exploiting Smartphone Voice Recording as a Digital Biomarker for Parkinson\u2019s Disease Diagnosis","volume":"73","author":"T He","year":"2024","journal-title":"IEEE Trans Instrum Meas"},{"key":"pone.0327733.ref042","doi-asserted-by":"crossref","first-page":"103362","DOI":"10.1016\/j.jbi.2019.103362","article-title":"Investigating voice as a biomarker: Deep phenotyping methods for early detection of Parkinson\u2019s disease","volume":"104","author":"JM Tracy","year":"2020","journal-title":"J Biomed Inform"},{"issue":"18","key":"pone.0327733.ref043","doi-asserted-by":"crossref","first-page":"7850","DOI":"10.3390\/s23187850","article-title":"Detecting Minor Symptoms of Parkinson\u2019s Disease in the Wild Using Bi-LSTM with Attention Mechanism","volume":"23","author":"V Skaramagkas","year":"2023","journal-title":"Sensors (Basel)"},{"issue":"6","key":"pone.0327733.ref044","doi-asserted-by":"crossref","first-page":"1835","DOI":"10.1109\/JBHI.2015.2471093","article-title":"A Smartphone-Based Tool for Assessing Parkinsonian Hand Tremor","volume":"19","author":"N Kostikis","year":"2015","journal-title":"IEEE J Biomed Health Inform"},{"issue":"12","key":"pone.0327733.ref045","doi-asserted-by":"crossref","first-page":"3491","DOI":"10.1109\/TBME.2020.2988942","article-title":"Building a Machine-Learning Framework to Remotely Assess Parkinson\u2019s Disease Using Smartphones","volume":"67","author":"OY Chen","year":"2020","journal-title":"IEEE Trans Biomed Eng"},{"issue":"6","key":"pone.0327733.ref046","doi-asserted-by":"crossref","first-page":"2361","DOI":"10.1152\/jn.00648.2020","article-title":"New roles for dopamine in motor skill acquisition: lessons from primates, rodents, and songbirds","volume":"125","author":"AN Wood","year":"2021","journal-title":"J Neurophysiol"},{"issue":"3","key":"pone.0327733.ref047","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s002210100829","article-title":"Multijoint movement control in Parkinson\u2019s disease","volume":"140","author":"RD Seidler","year":"2001","journal-title":"Exp Brain Res"},{"key":"pone.0327733.ref048","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.77216","article-title":"Self-configuring feedback loops for sensorimotor control","volume":"11","author":"SO Verduzco-Flores","year":"2022","journal-title":"Elife"},{"key":"pone.0327733.ref049","doi-asserted-by":"crossref","first-page":"1142","DOI":"10.1109\/TSP.2022.3153135","article-title":"Robust Aggregation for Federated Learning","volume":"70","author":"K Pillutla","year":"2022","journal-title":"IEEE Trans Signal Process"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0327733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T17:27:09Z","timestamp":1752514029000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0327733"}},"subtitle":[],"editor":[{"given":"Luigi","family":"Borz\u00ec","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,7,14]]},"references-count":49,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7,14]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0327733","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,14]]}}}