{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T00:59:03Z","timestamp":1792803543087,"version":"4.5.0"},"reference-count":43,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T00:00:00Z","timestamp":1714348800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hong Kong Government Research Grant Council to Shelley Xiuli Tong","award":["RFS2021-7H05"],"award-info":[{"award-number":["RFS2021-7H05"]}],"id":[{"id":"https:\/\/ror.org\/034179816","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Hong Kong Government Research Grant Council to Shelley Xiuli Tong","award":["17612222"],"award-info":[{"award-number":["17612222"]}],"id":[{"id":"https:\/\/ror.org\/034179816","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Hong Kong Government Research Grant Council to Shelley Xiuli Tong","award":["17616323"],"award-info":[{"award-number":["17616323"]}],"id":[{"id":"https:\/\/ror.org\/034179816","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Brain Sciences"],"abstract":"<jats:p>Handwriting difficulty is a defining feature of Chinese developmental dyslexia (DD) due to the complex structure and dense information contained within compound characters. Despite previous attempts to use deep neural network models to extract handwriting features, the temporal property of writing characters in sequential order during dictation tasks has been neglected. By combining transfer learning of convolutional neural network (CNN) and positional encoding with the temporal-sequential encoding of long short-term memory (LSTM) and attention mechanism, we trained and tested the model with handwriting images of 100,000 Chinese characters from 1064 children in Grades 2\u20136 (DD = 483; Typically Developing [TD] = 581). Using handwriting features only, the best model reached 83.2% accuracy, 79.2% sensitivity, 86.4% specificity, and 91.2% AUC. With grade information, the best model achieved 85.0% classification accuracy, 83.3% sensitivity, 86.4% specificity, and 89.7% AUC. These findings suggest the potential of utilizing machine learning technology to identify children at risk for dyslexia at an early age.<\/jats:p>","DOI":"10.3390\/brainsci14050444","type":"journal-article","created":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T09:50:07Z","timestamp":1714470607000},"page":"444","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["DysDiTect: Dyslexia Identification Using CNN-Positional-LSTM-Attention Modeling with Chinese Dictation Task"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1913-5541","authenticated-orcid":false,"given":"Hey Wing","family":"Liu","sequence":"first","affiliation":[{"name":"Human Communication, Learning, and Development (HCLD), Faculty of Education, The University of Hong Kong, Hong Kong 999077, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"Human Communication, Learning, and Development (HCLD), Faculty of Education, The University of Hong Kong, Hong Kong 999077, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shelley Xiuli","family":"Tong","sequence":"additional","affiliation":[{"name":"Human Communication, Learning, and Development (HCLD), Faculty of Education, The University of Hong Kong, Hong Kong 999077, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,4,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1080\/03054985.2020.1765756","article-title":"Defining and Understanding Dyslexia: Past, Present and Future","volume":"46","author":"Snowling","year":"2020","journal-title":"Oxf. Rev. Educ."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1007\/s40474-018-0149-y","article-title":"Dyslexia in Chinese","volume":"5","author":"McBride","year":"2018","journal-title":"Curr. Dev. Disord. Rep."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1080\/02643294.2020.1765754","article-title":"Spelling in Developmental Dyslexia in Chinese: Evidence of Deficits in Statistical Learning and over-Reliance on Phonology","volume":"37","author":"Lee","year":"2020","journal-title":"Cogn. Neuropsychol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1080\/10409289.2010.536441","article-title":"Adapting Western Pedagogies for Chinese Literacy Instruction: Case Studies of Hong Kong, Shenzhen, and Singapore Preschools","volume":"23","author":"Li","year":"2012","journal-title":"Early Educ. Dev."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1016\/j.jecp.2011.04.014","article-title":"Copying Skills in Relation to Word Reading and Writing in Chinese Children with and without Dyslexia","volume":"110","author":"Chung","year":"2011","journal-title":"J. Exp. Child Psychol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1745","DOI":"10.1016\/j.ridd.2011.03.001","article-title":"Chinese Handwriting Performance of Primary School Children with Dyslexia","volume":"32","author":"Lam","year":"2011","journal-title":"Res. Dev. Disabil."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"3372","DOI":"10.1016\/j.ridd.2013.06.039","article-title":"Writing to Dictation and Handwriting Performance among Chinese Children with Dyslexia: Relationships with Orthographic Knowledge and Perceptual-Motor Skills","volume":"34","author":"Chan","year":"2013","journal-title":"Res. Dev. Disabil."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e13161","DOI":"10.1111\/desc.13161","article-title":"The Brain Basis of Handwriting Deficits in Chinese Children with Developmental Dyslexia","volume":"25","author":"Yang","year":"2022","journal-title":"Dev. Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"919440","DOI":"10.3389\/fnins.2022.919440","article-title":"Disruption of Functional Brain Networks Underlies the Handwriting Deficit in Children with Developmental Dyslexia","volume":"16","author":"Liu","year":"2022","journal-title":"Front. Neurosci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1016\/j.patcog.2016.08.005","article-title":"Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark","volume":"61","author":"Zhang","year":"2017","journal-title":"Pattern Recognit."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"An, W. (2019, January 2\u20134). Quality Evaluation and Key Defects Correction for Handwritten Chinese Characters. Proceedings of the 2019 6th International Conference on Systems and Informatics (ICSAI), Shanghai, China.","DOI":"10.1109\/ICSAI48974.2019.9010226"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"101","DOI":"10.4304\/jsw.4.2.101-107","article-title":"A Chinese Handwriting Education System with Automatic Error Detection","volume":"4","author":"Hu","year":"2009","journal-title":"J. Softw."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wu, J., Han, Q., and Li, Y. (2019, January 5\u20138). Study on Correctness Judgement of Handwritten Chinese Characters Based on Feature Matrix for Similarity Matching. Proceedings of the 2019 Twelfth International Conference on Ubi-Media Computing (Ubi-Media), Bali, Indonesia.","DOI":"10.1109\/Ubi-Media.2019.00025"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Bai, X., and Qiao, X. (2017, January 1\u20134). A Method of Chinese Character Shape Representation and Its Application in the Error Correction for Normative Handwritten Chinese Characters. Proceedings of the 2017 10th International Conference on Ubi-media Computing and Workshops (Ubi-Media), Pattaya, Thailand.","DOI":"10.1109\/UMEDIA.2017.8074142"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3615","DOI":"10.1109\/TMM.2022.3163517","article-title":"A Tree-Structure Analysis Network on Handwritten Chinese Character Error Correction","volume":"25","author":"Li","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hu, P., Ma, J., Zhang, Z., Du, J., and Zhang, J. (2023). Count, Decode and Fetch: A New Approach to Handwritten Chinese Character Error Correction. arXiv.","DOI":"10.2139\/ssrn.4518260"},{"key":"ref_17","unstructured":"Zhong, S., Song, S., Tang, T., Nie, F., Zhou, X., Zhao, Y., Zhao, Y., Sin, K.F., and Chan, S.H.G. (2023). Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Association for Computing Machinery."},{"key":"ref_18","unstructured":"Ho, C.S.H., Chan, D.W.O., Chung, K.K.H., Tsang, S.M., Lee, S.H., and Cheng, W.Y.R. (2007). The Hong Kong Test of Specific Learning Difficulties in Reading and Writing for Primary School Students, Hong Kong Specific Learning Difficulties Research Team. [2nd ed.]. [HKT-P(II)]."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e20193046","DOI":"10.1542\/peds.2019-3046","article-title":"Reintroducing Dyslexia: Early Identification and Implications for Pediatric Practice","volume":"146","author":"Sanfilippo","year":"2020","journal-title":"Pediatrics"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"36879","DOI":"10.1109\/ACCESS.2021.3062709","article-title":"Advance Machine Learning Methods for Dyslexia Biomarker Detection: A Review of Implementation Details and Challenges","volume":"9","author":"Usman","year":"2021","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.icte.2020.05.006","article-title":"Developmental Dyslexia Detection Using Machine Learning Techniques: A Survey","volume":"6","author":"Kaisar","year":"2020","journal-title":"ICT Express"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Alqahtani, N.D., Alzahrani, B., and Ramzan, M.S. (2023). Deep Learning Applications for Dyslexia Prediction. Appl. Sci., 13.","DOI":"10.3390\/app13052804"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Rosli, M.S.A.B., Isa, I.S., Ramlan, S.A., Sulaiman, S.N., and Maruzuki, M.I.F. (2021, January 27\u201328). Development of CNN Transfer Learning for Dyslexia Handwriting Recognition. Proceedings of the 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE), Penang, Malaysia.","DOI":"10.1109\/ICCSCE52189.2021.9530971"},{"key":"ref_24","unstructured":"Spoon, K., Crandall, D., and Siek, K. (2019, January 15). Towards Detecting Dyslexia in Children\u2019s Handwriting Using Neural Networks. Proceedings of the International Conference on Machine Learning AI for Social Good Workshop, Long Beach, CA, USA."},{"key":"ref_25","unstructured":"Spoon, K., Siek, K., Crandall, D., and Fillmore, M. (2019, January 13). Can We (and Should We) Use AI to Detect Dyslexia in Children\u2019s Handwriting?. Proceedings of the Artificial Intelligence for Social Good (NeurIPS 2019), Vancouver, BC, Canada."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1016\/j.procs.2019.12.127","article-title":"Automated Detection of Dyslexia Symptom Based on Handwriting Image for Primary School Children","volume":"163","author":"Isa","year":"2019","journal-title":"Procedia Comput. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Danna, J., Puyjarinet, F., and Jolly, C. (2023). Tools and Methods for Diagnosing Developmental Dysgraphia in the Digital Age: A State of the Art. Children, 10.","DOI":"10.20944\/preprints202311.1132.v1"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1587\/transinf.2017EDP7224","article-title":"Automated Detection of Children at Risk of Chinese Handwriting Difficulties Using Handwriting Process Information: An Exploratory Study","volume":"102","author":"Wu","year":"2019","journal-title":"IEICE Trans. Inf. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1080\/10888438.2022.2088373","article-title":"Identifying Chinese Children with Dyslexia Using Machine Learning with Character Dictation","volume":"27","author":"Lee","year":"2023","journal-title":"Sci. Stud. Read."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Sultana, F., Sufian, A., and Dutta, P. (2018, January 22\u201323). Advancements in Image Classification Using Convolutional Neural Network. Proceedings of the 2018 Fourth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN), Kolkata, India.","DOI":"10.1109\/ICRCICN.2018.8718718"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"739","DOI":"10.31763\/ijrcs.v2i4.888","article-title":"Understanding of Convolutional Neural Network (CNN): A Review","volume":"2","author":"Purwono","year":"2022","journal-title":"Int. J. Robot. Control Syst."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Jogin, M., Madhulika, M.S., Divya, G.D., Meghana, R.K., and Apoorva, S. (2018, January 18\u201319). Feature Extraction Using Convolution Neural Networks (CNN) and Deep Learning. Proceedings of the 2018 3rd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT), Bangalore, India.","DOI":"10.1109\/RTEICT42901.2018.9012507"},{"key":"ref_33","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017, January 4\u20139). Attention Is All You Need. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.1162\/neco_a_01199","article-title":"A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures","volume":"31","author":"Yu","year":"2019","journal-title":"Neural Comput."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"110314","DOI":"10.1016\/j.asoc.2023.110314","article-title":"Policy Gradient Empowered LSTM with Dynamic Skips for Irregular Time Series Data","volume":"142","author":"Weerakody","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.neucom.2021.03.091","article-title":"A Review on the Attention Mechanism of Deep Learning","volume":"452","author":"Niu","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_38","first-page":"17236","article-title":"Co-Tuning for Transfer Learning","volume":"33","author":"You","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/j.aiopen.2021.08.002","article-title":"Pre-Trained Models: Past, Present and Future","volume":"2","author":"Han","year":"2021","journal-title":"AI Open"},{"key":"ref_40","first-page":"12","article-title":"CNN Comparisons Models on Dyslexia Handwriting Classification","volume":"17","author":"Isa","year":"2021","journal-title":"ESTEEM Acad. J."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Jasira, K.T., Laila, V., and Jemsheer Ahmed, P. (2023, January 13\u201314). DyslexiScan: A Dyslexia Detection Method from Handwriting Using CNN LSTM Model. Proceedings of the 2023 International Conference on Innovations in Engineering and Technology (ICIET), Muvattupuzha, India.","DOI":"10.1109\/ICIET57285.2023.10220750"},{"key":"ref_42","unstructured":"Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L.C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., and Pang, R. (November, January 27). Searching for MobileNetV3. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_43","unstructured":"Yogarajah, P. (2020, January 10\u201315). Deep Learning Approach to Automated Detection of Dyslexia-Dysgraphia. Proceedings of the 25th IEEE International Conference on Pattern Recognition, Milan, Italy."}],"container-title":["Brain Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3425\/14\/5\/444\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:36:19Z","timestamp":1760106979000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3425\/14\/5\/444"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,29]]},"references-count":43,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,5]]}},"alternative-id":["brainsci14050444"],"URL":"https:\/\/doi.org\/10.3390\/brainsci14050444","relation":{},"ISSN":["2076-3425"],"issn-type":[{"value":"2076-3425","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,29]]}}}