Abstract
Reading difficulty (RD), a neurodevelopmental disorder affecting language acquisition in children, necessitates early screening for effective educational interventions. This study proposes the RD-risk Classifier (RDr-C), a novel framework integrating functional near-infrared spectroscopy (fNIRS) with deep learning, specifically combining a dual-layer graph convolutional network (GCN), a bidirectional long short-term memory network (BiLSTM), and multi-head self-attention mechanisms (MSA) for 7-8-year-old children’s literacy assessment. The model was validated using fNIRS signals from 30 participants (16 experimental group, 14 control group) during the visual sign recognition test and phonetic discrimination test, with performance evaluated through 5 runs \(\times\) 5-fold cross-validation experiments. Results show that RDr-C achieved a mean classification accuracy of 99.60% and 99.66% in visual and auditory tests, respectively, significantly outperforming traditional convolutional neural networks (CNN), long short-term memory networks (LSTM), and existing fNIRS classification models (e.g., fNIRS-T, fNIRSNet). Furthermore, leave-one-subject-out cross-validation demonstrates that RDr-C achieves global accuracies of 89.33% and 87.93% on visual and auditory tasks, respectively, with corresponding Kappa coefficients of 0.78 and 0.76, confirming its robustness across individuals. Feature shuffling and wavelet transformation visualizations further confirm robust feature separation, highlighting the model’s ability to capture distinct hemodynamic patterns associated with RD. By integrating the spatial feature extraction of GCN, the temporal modeling of BiLSTM, and the global dependency capture of MSA, this work establishes a non-invasive neuroimaging paradigm for educational neuroscience. The high-precision classification lays a technical foundation for early screening tools, with future applications extending to multimodal brain-computer interfaces and longitudinal intervention monitoring.
Similar content being viewed by others
Data availability
The data is only available on request due to the individual privacy agreement made with parents.
References
World Health Organization. International Classification of Diseases (icd-11) for Mortality And Morbidity Statistics, Technical Report (World Health Organization, 2022).
Association, A. P. Diagnostic and Statistical Manual of Mental Disorders (American Psychiatric Association, 2013).
Döhla, D. & Heim, S. Developmental dyslexia and dysgraphia: What can we learn from the one about the other?. Front. Psychol. 6, 2045. https://doi.org/10.3389/fpsyg.2015.02045 (2015).
Katusic, S. K., Colligan, R. C., Barbaresi, W. J., Schaid, D. J. & Jacobsen, S. J. Incidence of reading disability in a population-based birth cohort. Mayo Clin. Proc. 76, 1081–1092. https://doi.org/10.4065/76.11.1081 (2001).
Casalini, C. & Pecini, C. Telerehabilitation of developmental dyslexia: Critical considerations on intervention methods and their effectiveness. Brain Sci. 14, 793. https://doi.org/10.3390/brainsci14080793 (2024).
Sun, Z. et al. Prevalence and associated risk factors of dyslexic children in a middle-sized city of China: A cross-sectional study. PLoS ONE 8, e56688. https://doi.org/10.1371/journal.pone.0056688 (2013).
Fan, Y., Xianglin, Z., Yuqing, C. & Hong, L. The development of the Chinese dyslexia screening behavior checklist for primary students. Stud. Psychol. Behav. 19, 521–527 (2021).
Hou, F. et al. Validity and reliability of the dyslexia checklist for Chinese children. Front. Psychol. 1915 (2018).
Shu, H., McBride-Chang, C., Wu, S. & Liu, H. Understanding Chinese developmental dyslexia: Morphological awareness as a core cognitive construct. J. Educ. Psychol. 98, 122–133. https://doi.org/10.1037/0022-0663.98.1.122 (2006).
Daniel, J., Clucas, L. & Wang, H. Identifying students with dyslexia: Exploration of current assessment methods. Ann. Dyslexia 75, 19–41. https://doi.org/10.1007/s11881-024-00313-y (2024).
Willows, D. M., Kruk, R. S. & Corcos, E. Visual Processes in Reading and Reading Disabilities (Lawrence Erlbaum Associates, 1993).
Hale, J. et al. Critical issues in response-to-intervention, comprehensive evaluation, and specific learning disabilities identification and intervention: An expert white paper consensus. Learn. Disabil. Q. 33, 223–236. https://doi.org/10.1177/073194871003300310 (2010).
Fenwick, M. E. et al. Neuropsychological profiles of written expression learning disabilities determined by concordance-discordance model criteria. Appl. Neuropsychol. 5, 83–96. https://doi.org/10.1080/21622965.2014.993396 (2015).
Fletcher, J. M. & Miciak, J. Comprehensive cognitive assessments are not necessary for the identification and treatment of learning disabilities. Arch. Clin. Neuropsychol. 32, 2–7. https://doi.org/10.1093/arclin/acw103 (2017).
Kranzler, J. H., Floyd, R. G., Benson, N., Zaboski, B. & Thibodaux, L. Cross-battery assessment pattern of strengths and weaknesses approach to the identification of specific learning disorders: Evidence-based practice or pseudoscience?. Int. J. School Educ. Psychol. 4, 146–157. https://doi.org/10.1080/21683603.2016.1192855 (2016).
Maki, K. E., Kranzler, J. H. & Moody, M. E. Dual discrepancy/consistency pattern of strengths and weaknesses method of specific learning disability identification: Classification accuracy when combining clinical judgment with assessment data. J. Sch. Psychol. 92, 33–48. https://doi.org/10.1016/j.jsp.2022.02.003 (2022).
Miciak, J., Taylor, W. P., Denton, C. A. & Fletcher, J. M. The effect of achievement test selection on identification of learning disabilities within a patterns of strengths and weaknesses framework. Sch. Psychol. Q. 30, 321–334 (2015).
Stuebing, K. K., Fletcher, J. M., Branum-Martin, L., Francis, D. J. & VanDerHeyden, A. Evaluation of the technical adequacy of three methods for identifying specific learning disabilities based on cognitive discrepancies. Sch. Psychol. Rev. 41, 3–22. https://doi.org/10.1080/02796015.2012.12087373 (2012).
Taylor, W. P., Miciak, J., Fletcher, J. M. & Francis, D. J. Cognitive discrepancy models for specific learning disabilities identification: Simulations of psychometric limitations. Psychol. Assess. 29, 446–457. https://doi.org/10.1037/pas0000356 (2017).
Fletcher, J. M. & Vaughn, S. Response to intervention: Preventing and remediating academic difficulties. Child Dev. Perspect. 3, 30–37. https://doi.org/10.1111/j.1750-8606.2008.00072.x (2009).
Fletcher, J. M., Stuebing, K. K., Morris, R. D. & Lyon, G. R. Classification and Definition of Learning Disabilities: A Hybrid Model 33–50 (The Guilford Press, 2014).
Miciak, J. & Fletcher, J. M. The critical role of instructional response for identifying dyslexia and other learning disabilities. J. Learn. Disabil. 53, 343–353. https://doi.org/10.1177/0022219420906801 (2020).
Rice, M. & Gilson, C. B. Dyslexia identification: Tackling current issues in schools. Interv. Sch. Clin. 58, 205–209. https://doi.org/10.1177/10534512221081278 (2023).
Wang, J. J. et al. Expert advice on the diagnosis and intervention of Chinese developmental dyslexia. Chin. Ment. Health J. 37, 185–191. https://doi.org/10.3969/j.issn.1000-6729.2023.03.001 (2023) ((in Chinese)).
Ministry of Education of the People’s Republic of China. Compulsory Education Chinese Curriculum Standards (2022 Edition). Beijing (2022). Official document. Issuance number: Jiao Cai [2022] No. 2.
Xie, T. T., Li, N. J., Lu, S., Li, Y. & Huang, C. F. Accurate assessment of dyslexia in school-age children based on Chinese characteristics. Appl. Linguis. 1, 368–387 (2023) ((in Chinese)).
Fu, Y., Yan, X., Mao, J., Su, H. & Cao, F. Abnormal brain activation during speech perception and production in children and adults with reading difficulty. npj Sci. Learn. https://doi.org/10.1038/s41539-024-00266-2 (2024).
Kovelman, I., Norton, E. S., Christodoulou, J. A. & Gaab, N. Brain basis of phonological awareness for spoken language in children and its disruption in dyslexia. Cereb. Cortex 22, 754–764. https://doi.org/10.1093/cercor/bhr094 (2012).
Cao, F. et al. Neural signatures of phonological deficits in Chinese developmental dyslexia. Neuroimage 146, 301–311. https://doi.org/10.1016/j.neuroimage.2016.11.051 (2017).
Bak, S., Park, J., Shin, J. & Jeong, J. Open-access fnirs dataset for classification of unilateral finger- and foot-tapping. Electronics 8, 1486 (2019).
Nazeer, H. et al. Enhancing classification accuracy of fnirs-bci using features acquired from vector-based phase analysis. J. Neural Eng. 17, 056025. https://doi.org/10.1088/1741-2552/abb417 (2020).
Naseer, N. & Hong, K. S. fnirs-based brain-computer interfaces: A review. Front. Hum. Neurosci. 9, 3. https://doi.org/10.3389/fnhum.2015.00003 (2015).
Janani, A. et al. Investigation of deep convolutional neural network for classification of motor imagery fnirs signals for bci applications. Biomed. Signal Process. Control 62, 102133. https://doi.org/10.1016/j.bspc.2020.102133 (2020).
Trakoolwilaiwan, T., Behboodi, B., Lee, J., Kim, K. & Choi, J. W. Convolutional neural network for high-accuracy functional near-infrared spectroscopy in a brain-computer interface: three-class classification of rest, right-, and left-hand motor execution. Neurophotonics 5, 011008. https://doi.org/10.1117/1.NPh.5.1.011008 (2018).
Zhang, C. et al. Comparing multi-dimensional fnirs features using Bayesian optimization-based neural networks for mild cognitive impairment (mci) detection. IEEE Trans. Neural Syst. Rehabil. Eng. 31, 1019–1029. https://doi.org/10.1109/TNSRE.2023.3236007 (2023).
Asgher, U. et al. Enhanced accuracy for multiclass mental workload detection using long short-term memory for brain–computer interface. Front. Neurosci. https://doi.org/10.3389/fnins.2020.00584 (2020).
Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) 4171–4186, https://doi.org/10.18653/v1/N19-1423 (Association for Computational Linguistics, 2019).
Sun, Z., Huang, Z., Duan, F. & Liu, Y. A novel multimodal approach for hybrid brain–computer interface. IEEE Access 8, 89909–89918. https://doi.org/10.1109/ACCESS.2020.2994226 (2020).
Ke, H., Wang, F., Ma, H. & He, Z. Adhd identification and its interpretation of functional connectivity using deep self-attention factorization. Knowl.-Based Syst. 250, 109082. https://doi.org/10.1016/j.knosys.2022.109082 (2022).
Ke, H. et al. Deep factor learning for accurate brain neuroimaging data analysis on discrimination for structural mri and functional mri. IEEE/ACM Trans. Comput. Biol. Bioinf. 21, 582–595. https://doi.org/10.1109/TCBB.2023.3252577 (2024).
Ke, H. et al. Unsupervised deep frequency-channel attention factorization to non-linear feature extraction: A case study of identification and functional connectivity interpretation of parkinson’s disease. Expert Syst. Appl. 243, 122853. https://doi.org/10.1016/j.eswa.2023.122853 (2024).
Wang, F., Ke, H., Ma, H. & Tang, Y. Deep wavelet temporal-frequency attention for nonlinear fmri factorization in asd. Pattern Recogn. 165, 111543. https://doi.org/10.1016/j.patcog.2025.111543 (2025).
Wang, F., Ke, H. & Cai, C. Deep wavelet self-attention non-negative tensor factorization for non-linear analysis and classification of fmri data. Appl. Soft Comput. 182, 113522. https://doi.org/10.1016/j.asoc.2025.113522 (2025).
Wang, F., Ke, H. & Tang, Y. Fusion of generative adversarial networks and non-negative tensor decomposition for depression fmri data analysis. Inf. Process. Manage. 62, 103961. https://doi.org/10.1016/j.ipm.2024.103961 (2025).
Hoshi, Y. Functional near-infrared optical imaging: Utility and limitations in human brain mapping. Psychophysiology 40, 511–20. https://doi.org/10.1111/1469-8986.00053 (2003).
Strangman, G., Culver, J. P., Thompson, J. H. & Boas, D. A. A quantitative comparison of simultaneous bold fmri and nirs recordings during functional brain activation. Neuroimage 17, 719–731. https://doi.org/10.1006/nimg.2002.1227 (2002).
Wang, Z., Zhang, J., Zhang, X., Chen, P. & Wang, B. Transformer model for functional near-infrared spectroscopy classification. IEEE J. Biomed. Health Inform. 26, 2559–2569. https://doi.org/10.1109/JBHI.2022.3140531 (2022).
Wang, Z., Fang, J. & Zhang, J. Rethinking delayed hemodynamic responses for fnirs classification. IEEE Trans. Neural Syst. Rehabil. Eng. 31, 4528–4538. https://doi.org/10.1109/TNSRE.2023.3330911 (2023).
Yang, J. et al. Mobile application-based phonetic training facilitates Chinese-English learners’ learning of l2. Learn. Instr. 93, 101967. https://doi.org/10.1016/j.learninstruc.2024.101967 (2024).
Wang, L. et al. Influence of high-level mathematical thinking on l2 phonological processing of Chinese efl learners: Evidence from an fnirs study. Think. Skills Creat. 47, 101242. https://doi.org/10.1016/j.tsc.2023.101242 (2023).
Bauernfeind, G., Scherer, R., Pfurtscheller, G. & Neuper, C. Single-trial classification of antagonistic oxyhemoglobin responses during mental arithmetic. Med. Biol. Eng. Comput. 49, 979–84. https://doi.org/10.1007/s11517-011-0792-5 (2011).
Habib, M. The neurological basis of developmental dyslexia: An overview and working hypothesis. Brain 123, 2373–2399. https://doi.org/10.1093/brain/123.12.2373 (2000).
Fliers, E. et al. Motor coordination problems in children and adolescents with adhd rated by parents and teachers: effects of age and gender. J. Neural Transm. 115, 211–220. https://doi.org/10.1007/s00702-007-0827-0 (2008).
Fournier, K., Hass, C. J., Naik, S. K., Lodha, N. & Cauraugh, J. H. Motor coordination in autism spectrum disorders: A synthesis and meta-analysis. J. Autism Dev. Disord. 40, 1227–1240. https://doi.org/10.1007/s10803-010-0981-3 (2010).
Liao, W. et al. Lack of functional brain connectivity was associated with poor inhibition in children with attention-deficit/hyperactivity disorder using near-infrared spectroscopy. Front. Psychiatry 14, 1221242. https://doi.org/10.3389/fpsyt.2023.1221242 (2023).
Miao, S. et al. Reduced prefrontal cortex activation in children with attention-deficit/hyperactivity disorder during go/no-go task: A functional near-infrared spectroscopy study. Front. Neurosci. 11, 367. https://doi.org/10.3389/fnins.2017.00367 (2017).
Kaltner, S. & Jansen, P. Mental rotation and motor performance in children with developmental dyslexia. Res. Dev. Disabil. 35, 741–754. https://doi.org/10.1016/j.ridd.2013.10.003 (2014).
Savage, R. Motor skills, automaticity and developmental dyslexia: A review of the research literature. Read. Writ. 17, 301–324. https://doi.org/10.1023/B:READ.0000017688.67137.80 (2004).
Kearns, D. M. & Fuchs, D. Does cognitively focused instruction improve the academic performance of low-achieving students?. Except. Child. 79, 263–290. https://doi.org/10.1177/001440291307900200 (2013).
Burns, M. K. et al. Meta-analysis of academic interventions derived from neuropsychological data. Sch. Psychol. Q. 31, 28–42. https://doi.org/10.1037/spq0000117 (2016).
Finn, E. S. et al. Disruption of functional networks in dyslexia: A whole-brain, data-driven analysis of connectivity. Biol. Psychiatry 76, 397–404. https://doi.org/10.1016/j.biopsych.2013.08.031 (2014).
Booth, J. R., Bebko, G., Burman, D. D. & Bitan, T. Children with reading disorder show modality independent brain abnormalities during semantic tasks. Neuropsychologia 45, 775–83. https://doi.org/10.1016/j.neuropsychologia.2006.08.015 (2007).
Liu, L. et al. Children with reading disability show brain differences in effective connectivity for visual, but not auditory word comprehension. PLoS ONE 5, e13492. https://doi.org/10.1371/journal.pone.0013492 (2010).
Funding
This work is supported by the Major Science and Technology Special Program of Jiangsu Province [BG2024025]; Research project of Ministry of Education of China [23YJC880062]; the teaching reform and research project of Sichuan Normal University [JWC20240107; JWC20240116].
Author information
Authors and Affiliations
Contributions
P.Y. conceptualised the study and wrote the manuscript. P.Y. and Y.D. conducted the experiments, collected the data, and processed part of the raw data. Y.G. and Y.Z. provided professional guidance and participated in designing the evaluation and intervention methods and hold the teaching reform and research projects of Sichuan Normal University [JWC20240116, JWC20240107]. X.Z. designed, monitored and assessed the Chinese Character Phonetic Notation Test for all participants. L.W. and Z.L. analysed the data, and Z.L. holds the funding “Research project of Ministry of Education of China [23YJC880062]”. D.W. supervised the fNIRS-related processes and provided financial support through the funding “Major Science and Technology Special Program of Jiangsu Province [BG2024025]”. J.Y. was the project administrator and provided overall supervision for the entire research.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Yang, P., Duan, Y., Wang, L. et al. An early detection framework for young Chinese learners at risk of reading difficulty using fNIRS and deep learning. Sci Rep (2026). https://doi.org/10.1038/s41598-026-44379-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-44379-7
