Identifications of developmental dysgraphia on the basis of dynamic handwriting features

Document Type : Research Paper

Authors

1 Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran

2 Department of Computer Science, Shahid Beheshti University, Tehran, Iran

3 Health Management and Economics Research Center, Iran University of Medical Sciences, Tehran, Iran

4 Computer Science, University of Human Development, Sulaymaniyah, Iraq

5 Department of Mechatronics Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran

6 Research Center of Addiction and Behavioral Sciences, Shahid Sadoughi University of Medical Sciences, Yazd, Iran

7 Diabetes Research Center, Shahid Sadoughi University of Medical Sciences, Yazd, Iran

Abstract

Developmental disorders are regularly observed in developmental writing skills (developmental dysgraphia) with considerable concerns. Physicians do their diagnosis on the basis of the juvenile’s written products as well as the attitudes and feedback taken from their teachers. This is a very laborious process and yet subjective in nature. Consequently, many juveniles suffering from this defect, particularly those with lower levels of the disorder remain undiagnosed. The aim of the present work was to find a new method for the automatic identification of dysgraphia even at minute levels. Utilizing the most sensitive pen tablet available to gather the desired dataset, we could extract all the considered datasets, i.e. temporal, spatial, kinematic, and pressure parameters with the greatest possible accuracy. On the whole, 102 students (both male and female) from the second, third, and fourth grades of primary schools were participated in the data collection phase by being asked to write a short paragraph. 51 students, in an age range of eight to ten years, were participated in each group, i.e. dysgraphic and non-dysgraphic. Next, a huge set of features (more than two thousand features) was extracted in the preprocessing phase. In the feature selection phase, we eventually ended up with sixteen features that proved to be the most effective in diagnosing dysgraphia. To distinguish between the dysgraphic and non-dysgraphic students, three different types of classifiers, i.e. random forests, AdaBoost classifiers, and support vector machines (SVM) were considered and compared. For the prediction of dysgraphia based on incessant handwriting features, the SVM was revealed to be the best model with a classification performance accuracy of 93.65%. Our work exhibited that online handwriting features including time, jerk, and altitude/azimuth may be utilized to automatically reveal dysgraphia in juveniles with this writing disorder.

Keywords

[1] A. Ammour, I. Aouraghe, G. Khaissidi, M. Mrabti, G. Aboulem, and F. Belahsen, Online Arabic and French handwriting of Parkinson’s disease: The impact of segmentation techniques on the classification results, Biomed. Signal Process. Control 66 (2021), 102429.
[2] T. Asselborn, T. Gargot, L. Kidzi´nski, W. Johal, D. Cohen, C. Jolly, and P. Dillenbourg, Automated human-level diagnosis of dysgraphia using a consumer tablet, NPJ Digital Medicine 1 (2018), no. 1, 1–9.
[3] R.E. Bellman, Adaptive control processes: A guided tour, Princeton university press, 2015.
[4] V.W. Berninger, Coordinating transcription and text generation in working memory during composing: Automatic and constructive processes, Learn. Disabil. Quart. 22 (1999), no. 2, 99–112.
[5] M.P. Broderick, A.W.A. Van Gemmert, H.A. Shill, and G.E. Stelmach, Hypometria and bradykinesia during drawing movements in individuals with parkinson’s disease, Exper. Brain Res. 197 (2009), no. 3, 223–233.
[6] M. Brossard-Racine, A. Majnemer, M. Shevell, L. Snider, and S.A. B´elanger, Handwriting capacity in children newly diagnosed with attention deficit hyperactivity disorder, Res. Deve. Disabil. 32 (2011), no. 6, 2927–2934.
[7] C.J. Daly, G.T. Kelley, and A. Krauss, Relationship between visual-motor integration and handwriting skills of children in kindergarten: A modified replication study, Amer. Occup. Therapy 57 (2003), no. 4, 459–462.
[8] L. Deschamps, C. Gaffet, S. Aloui, J. Boutet, V. Brault, and E. Labyt, Methodological issues in the creation of a diagnosis tool for dysgraphia, NPJ Digital Medicine 2 (2019), no. 1, 1–3.
[9] S. D¨ohla, D.and Heim, Developmental dyslexia and dysgraphia: What can we learn from the one about the other?, Front. Psych. 6 (2016), 2045.
[10] P. Drot´ar and M. Dobeˇs, Dysgraphia detection through machine learning, Sci. Rep. 10 (2020), no. 1, 1–11.
[11] P. Drot´ar, J. Mekyska, I. Rektorov´a, L. Masarov´a, Z. Sm´ekal, and M. Faundez-Zanuy, Analysis of in-air movement in handwriting: A novel marker for parkinson’s disease, Comput. Meth. Programs Biomed. 117 (2014), no. 3, 405–411.
[12] , Decision support framework for parkinson’s disease based on novel handwriting markers, IEEE Trans. Neural Syst. Rehabil. Engin. 23 (2014), no. 3, 508–516.
[13] P.r Drot´ar, J. Mekyska, I. Rektorov´a, L. Masarov´a, Z. Sm´ekal, and M. Faundez-Zanuy, A new modality for quantitative evaluation of Parkinson’s disease: In-air movement, 13th IEEE Int. Conf. Bioinf. Bioengin., IEEE, 2013, pp. 1–4.
[14] K.P. Feder and A. Majnemer, Handwriting development, competency, and intervention, Dev. Medicine Child Neuro. 49 (2007), no. 4, 312–317.
[15] Y. Freund and R.E. Schapire, A decision-theoretic generalization of on-line learning and an application to boosting, J. Comput. Syst. Sci. 55 (1997), no. 1, 119–139.
[16] T. Gargot, T. Asselborn, H. Pellerin, I. Zammouri, S. M. Anzalone, L. Casteran, W. Johal, P. Dillenbourg, D. Cohen, and C. Jolly, Acquisition of handwriting in children with and without dysgraphia: A computational approach, PLoS One 15 (2020), no. 9, e0237575.
[17] R. Gra¸ca, R. Sarmento e Castro, and J. Cevada, Parkdetect: Early diagnosing Parkinson’s disease, IEEE Int. Symp. Medical Measur. Appl. (MeMeA), IEEE, 2014, pp. 1–6.
[18] S. Graham, V.W. Berninger, R.D. Abbott, S.P. Abbott, and D. Whitaker, Role of mechanics in composing of elementary school students: A new methodological approach, J. Educ. Psych. 89 (1997), no. 1, 170.
[19] I. Guyon, J. Weston, S. Barnhill, and V. Vapnik, Gene selection for cancer classification using support vector machines, Machine learning 46 (2002), no. 1, 389–422.
[20] S. Han, C. Qubo, and H. Meng, Parameter selection in svm with rbf kernel function, World Autom. Cong., IEEE, 2012, pp. 1–4.
[21] T. Hastie, S. Rosset, J. Zhu, and H. Zou, Multi-class adaboost, Statistics Interface 2 (2009), no. 3, 349–360.
[22] T.K. Ho, Proceedings of 3rd international conference on document analysis and recognition, IEEE, 1995, pp. 278– 282.
[23] M.-L. Kaiser, J.-M. Albaret, and P.-A. Doudin, Relationship between visual-motor integration, eye-hand coordination, and quality of handwriting, J. Occupat. Therapy Schools Early Interven. 2 (2009), no. 2, 87–95.
[24] P.I. Khalid, J. Yunus, and R. Adnan, Extraction of dynamic features from hand drawn data for the identification of children with handwriting difficulty, Res. Dev. Disabil. 31 (2010), no. 1, 256–262.
[25] C. Kotsavasiloglou, N. Kostikis, D. Hristu-Varsakelis, and M. Arnaoutoglou, Machine learning-based classification of simple drawing movements in Parkinson’s disease, Biomed. Signal Process. Control 31 (2017), 174–180.
[26] R.A. Langmaid, N. Papadopoulos, B.P. Johnson, J.G. Phillips, and N.J. Rinehart, Handwriting in children with ADHD, J. Atten. Disord. 18 (2014), no. 6, 504–510.
[27] J. Medwell and D. Wray, Handwriting automaticity: The search for performance thresholds, Language Educ. 28 (2014), no. 1, 34–51.
[28] J. Mekyska, M. Faundez-Zanuy, Z. Mzourek, Z. Galaz, Z. Smekal, and S. Rosenblum, Identification and rating of developmental dysgraphia by handwriting analysis, IEEE Trans. Human-Machine Syst. 47 (2016), no. 2, 235–248.
[29] M. Moetesum, I. Siddiqi, N. Vincent, and F. Cloppet, Assessing visual attributes of handwriting for prediction of neurological disorders—a case study on Parkinson’s disease, Pattern Recogn. Lett. 121 (2019), 19–27.
[30] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O.r Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, , and J. Vanderplas, Scikit-learn: Machine learning in Python, J. Machine Learn. Res. 12
(2011), 2825–2830.
[31] C.R. Pereira, S.A.T. Weber, C. Hook, G.H. Rosa, and J.P. Papa, Deep learning-aided Parkinson’s disease diagnosis from handwritten dynamics, 29th Conf. Graph. Patterns Images (SIBGRAPI), IEEE, 2016, pp. 340–346.
[32] M.B. Racine, A. Majnemer, M. Shevell, and L. Snider, Handwriting performance in children with attention deficit hyperactivity disorder (ADHD), J. Child Neuro. 23 (2008), no. 4, 399–406.
[33] S. Rosenblum and G. Dror, Identifying developmental dysgraphia characteristics utilizing handwriting classification methods, IEEE Trans. Human-Machine Syst. 47 (2016), no. 2, 293–298.
[34] Sara Rosenblum, Development, reliability, and validity of the handwriting proficiency screening questionnaire (HPSQ), Amer. J. Occupat. Therapy 62 (2008), no. 3, 298–307.
[35] T.-Y. Shen, I.-H.and Lee and C.-L. Chen, Handwriting performance and underlying factors in children with attention deficit hyperactivity disorder, Res. Deve. Disabil. 33 (2012), no. 4, 1301–1309.
[36] M.H. Tseng and S.M.K. Chow, Perceptual-motor function of school-age children with slow handwriting speed, Amer. J. Occup. Therapy 54 (2000), no. 1, 83–88.
[37] M. Wallen, S. Duff, T.-A. Goyen, and E. Froude, Respecting the evidence: Responsible assessment and effective intervention for children with handwriting difficulties, Austr. Occupat. Therapy J. 60 (2013), no. 5, 366–369.
[38] Y. Wang and L. Feng, An adaptive boosting algorithm based on weighted feature selection and category classification confidence, Applied Intel. 51 (2021), no. 10, 6837–6858.
Volume 14, Issue 1
January 2023
Pages 3179-3188
  • Receive Date: 30 November 2021
  • Revise Date: 28 February 2022
  • Accept Date: 07 April 2022