Advance Machine Learning Methods for Dyslexia Biomarker Detection: A Review of Implementation Details and Challenges

Dyslexia is a neurological disorder that is characterized by imprecise comprehension of words and generally poor reading performance. It affects a significant population of school-age children, with more occurrences in males, thus, putting them at risk of poor academic performance and low self-esteem for a lifetime. The long-term hope is to have a dyslexia diagnostic method that is informed by neural-biomarkers. In this regard, large numbers of machine learning methods and, more recently, deep learning methods have been implemented across various types of dataset with the above-chance classification accuracy. However, attainment of clinical acceptability of these state-of-the-art methods is bedeviled by certain challenges including lack of biologically-interpretable biomarkers, privacy of dataset and classifiers, hyper-parameter selection/optimization, and overfitting problem among others. This review paper critically analyzes recent machine learning methods for detecting dyslexia and its biomarkers and discusses challenges that require proper attentions from the users of deep learning methods in order to enable them to attain clinically relevance and acceptable level. The review is conducted within the premise of implementation and experimental outcomes for each of the 22 selected articles using the Preferred Reporting Items for Systematic review and Meta-Analyses (PRISMA) protocol, with a view to outlining some critical challenges for achieving high accuracy and reliability of the state-of-the-art machine learning methods. As an evidence-based protocol for reporting in systematic reviews and meta-analyses, PRISMA helps to ensure clarity and transparency of this paper by showing a four-phase flow diagram of the selection process for articles used in this review. It is therefore, envisaged that higher classification performance of clinical relevance can be achieved using deep learning models for dyslexia and its biomarkers by addressing identified potential challenges.

[1]  Piotr Bogorodzki,et al.  Dealing with the Heterogeneous Multi-site Neuroimaging Data Sets: A Discrimination Study of Children Dyslexia , 2014, Brain Informatics and Health.

[2]  Stefanos D. Kollias,et al.  Adaptive Reading Assistance for the Inclusion of Students with Dyslexia: The AGENT-DYSL Approach , 2008, 2008 Eighth IEEE International Conference on Advanced Learning Technologies.

[3]  Franck Ramus,et al.  Neuroanatomy of developmental dyslexia: Pitfalls and promise , 2018, Neuroscience & Biobehavioral Reviews.

[4]  Ayman El-Baz,et al.  Image-based detection of Corpus Callosum variability for more accurate discrimination between autistic and normal brains , 2010, ICIP.

[5]  M. Altan,et al.  What every teacher needs to know , 2004 .

[6]  Ravie Chandren Muniyandi,et al.  Accelerated execution of P systems with active membranes to solve the N-queens problem , 2014, Theor. Comput. Sci..

[7]  Robert Dony,et al.  Improving the Security of the Medical Images , 2013 .

[8]  D. Moher,et al.  Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. , 2010, International journal of surgery.

[9]  Kok Wai Wong,et al.  EEG signal analysis of passage reading and rapid automatized naming between adults with dyslexia and normal controls , 2017, 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS).

[10]  Heikki Lyytinen,et al.  This Reprint May Differ from the Original in Pagination and Typographic Detail. the Graphogame Method: the Theoretical and Methodological Background of the Technology-enhanced Learning Environment for Learning to Read the Graphogame Method: the Theoretical and Methodological Background of the Techno , 2022 .

[11]  Mufti Mahmud,et al.  Deep Learning in Mining Biological Data , 2020, Cognitive Computation.

[12]  F. Abdul Rahman,et al.  INTERACTIVE MULTIMEDIA LEARNING OBJECT (IMLO) FOR DYSLEXIC CHILDREN , 2010 .

[13]  Novia Admodisastro,et al.  Dyslexia Adaptive Learning Model: Student Engagement Prediction Using Machine Learning Approach , 2018, SCDM.

[14]  T. Pansell,et al.  Screening for Dyslexia Using Eye Tracking during Reading , 2016, PloS one.

[15]  Kok Wai Wong,et al.  Review of EEG-based pattern classification frameworks for dyslexia , 2018, Brain Informatics.

[16]  Yin Bee Oon,et al.  Machine Learning and Dyslexia-Diagnostic and Classification System (DCS) for Kids with Learning Disabilities , 2018 .

[17]  N. Bell,et al.  Comparison of the Peabody Picture Vocabulary Test-Third Edition and Wechsler Adult Intelligence Scale-Third Edition with university students. , 2001, Journal of clinical psychology.

[18]  S. Holland,et al.  An fMRI Study of a Dyslexia Biomarker , 2014 .

[19]  Louis Danielson,et al.  Identification of learning disabilities : research to practice , 2002 .

[20]  Enrique Romero,et al.  Screening Dyslexia for English Using HCI Measures and Machine Learning , 2018, DH.

[21]  Mohammed Ali Al-Garadi,et al.  Application of Machine Learning Methods in Mental Health Detection: A Systematic Review , 2020, IEEE Access.

[22]  Salwani Mohd Daud,et al.  'Dyslexia Baca' Mobile App -- The Learning Ecosystem for Dyslexic Children , 2013, 2013 International Conference on Advanced Computer Science Applications and Technologies.

[23]  I. Karim,et al.  Classification of dyslexic and normal children during resting condition using KDE and MLP , 2013, 2013 5th International Conference on Information and Communication Technology for the Muslim World (ICT4M).

[24]  Dimitrios Zissis,et al.  EasyLexia: A Mobile Application for Children with Learning Difficulties , 2013, DSAI.

[25]  Richard K. Olson,et al.  Classification of learning disabilities: An evidence-based evaluation. , 2001 .

[26]  Amir Hussain,et al.  Applications of Deep Learning and Reinforcement Learning to Biological Data , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[27]  Giuseppe Aceto,et al.  Toward effective mobile encrypted traffic classification through deep learning , 2020, Neurocomputing.

[28]  Heikki Lyytinen,et al.  GraphoGame – a catalyst for multi-level promotion of literacy in diverse contexts , 2015 .

[29]  David J. Crandall,et al.  Towards Detecting Dyslexia in Children’s Handwriting Using Neural Networks , 2019 .

[30]  Kevin Kok Wai Wong,et al.  EEG Signal Analysis of Writing and Typing between Adults with Dyslexia and Normal Controls , 2018, Int. J. Interact. Multim. Artif. Intell..

[31]  R. Bhargavi,et al.  Prediction of Dyslexia from Eye Movements Using Machine Learning , 2019, IETE Journal of Research.

[32]  Ravie Chandren Muniyandi,et al.  CryptoDL: Predicting Dyslexia Biomarkers from Encrypted Neuroimaging Dataset Using Energy-Efficient Residue Number System and Deep Convolutional Neural Network , 2020, Symmetry.

[33]  Gal Chechik,et al.  Probabilistic Graphical Models of Dyslexia , 2015, KDD.

[34]  Md. Tanwir Uddin Haider,et al.  Personalized assessment model for alphabets learning with learning objects in e-learning environment for dyslexia , 2017, J. King Saud Univ. Comput. Inf. Sci..

[35]  Samuel O. Wajuihian,et al.  Neurobiology of developmental dyslexia: Part 1: A review of evidence from autopsy and structural neuro-imaging studies , 2011 .

[36]  Stanislaw J. Piestrak,et al.  Design of RNS Reverse Converters with Constant Shifting to Residue Datapath Channels , 2018, J. Signal Process. Syst..

[37]  Giuseppe Aceto,et al.  MIMETIC: Mobile encrypted traffic classification using multimodal deep learning , 2019, Comput. Networks.

[38]  T. V. Prasad.  Identifying Dyslexic Students by Using Artificial Neural Networks , 2010 .

[39]  Larry M. Manevitz,et al.  Features and Machine Learning for Correlating and Classifying between Brain Areas and Dyslexia , 2018, ArXiv.

[40]  Joseph K. Torgesen,et al.  Comprehensive Test of Phonological Processing , 1997 .

[41]  Been Kim,et al.  Considerations for Evaluation and Generalization in Interpretable Machine Learning , 2018 .

[42]  Luz Rello,et al.  Detecting readers with dyslexia using machine learning with eye tracking measures , 2015, W4A.

[43]  A. Simmons,et al.  Multivariate data analysis and machine learning in Alzheimer's disease with a focus on structural magnetic resonance imaging. , 2014, Journal of Alzheimer's disease : JAD.

[44]  Shahriar Kaisar,et al.  Developmental dyslexia detection using machine learning techniques : A survey , 2020, ICT Express.

[45]  D. Moher,et al.  Reprint--preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. , 2009, Physical therapy.

[46]  D. Harun,et al.  Interventions for children with dyslexia: A review on current intervention methods. , 2018, The Medical journal of Malaysia.

[47]  Cindy Ann Dell,et al.  Test Review: Wilkinson, G. S., & Robertson, G. J. (2006). Wide Range Achievement Test—Fourth Edition. Lutz, FL: Psychological Assessment Resources. WRAT4 Introductory Kit (includes manual, 25 test/response forms [blue and green], and accompanying test materials): $243.00 , 2008 .

[48]  A. Frid,et al.  An SVM based algorithm for analysis and discrimination of dyslexic readers from regular readers using ERPs , 2012, 2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel.

[49]  F. Ramus,et al.  Multi‐parameter machine learning approach to the neuroanatomical basis of developmental dyslexia , 2017, Human brain mapping.

[50]  Ricardo Baeza-Yates,et al.  Towards Language Independent Detection of Dyslexia with a Web-based Game , 2018, W4A.

[51]  Fatima Ezzahra Benmarrakchi,et al.  The 12 th International Conference on Future Networks and Communications ( FNC 2017 ) Communication Technology for Users with Specific Learning Disabilities , 2018 .

[52]  G. F. González,et al.  Machine learning Classification of Dyslexic Children based on EEG Local Network Features , 2019, bioRxiv.

[53]  Rachelle M. Bruno,et al.  Comprehensive Test of Phonological Processing (CTOPP) , 1999 .

[54]  Yolanda García Chimeno,et al.  Automatic classification of dyslexic children by applying machine learning to fMRI images. , 2014, Bio-medical materials and engineering.

[55]  Asifullah Khan,et al.  A survey of the recent architectures of deep convolutional neural networks , 2019, Artificial Intelligence Review.

[56]  Arvid Lundervold,et al.  An overview of deep learning in medical imaging focusing on MRI , 2018, Zeitschrift fur medizinische Physik.

[57]  Hassanin M. Al-Barhamtoshy,et al.  Diagnosis of Dyslexia using computation analysis , 2017, 2017 International Conference on Informatics, Health & Technology (ICIHT).

[58]  F. Ferri,et al.  Neural intersections of the phonological, visual magnocellular and motor/cerebellar systems in normal readers: Implications for imaging studies on dyslexia , 2013, Human brain mapping.

[59]  Begonya Garcia-Zapirain,et al.  Dyslexia detection using 3D convolutional neural networks and functional magnetic resonance imaging , 2020, Comput. Methods Programs Biomed..

[60]  Maria Papadopouli,et al.  DysLexML: Screening Tool for Dyslexia Using Machine Learning , 2019, ArXiv.

[61]  Karl J. Friston,et al.  Voxel-Based Morphometry—The Methods , 2000, NeuroImage.

[62]  W. Mansor,et al.  Comparison between characteristics of EEG signal generated from dyslexic and normal children , 2012, 2012 IEEE-EMBS Conference on Biomedical Engineering and Sciences.

[63]  Syariffanor Hisham,et al.  MyLexics: an assistive courseware for Dyslexic children to learn basic Malay language , 2009, ASAC.

[64]  Pengfei Xu,et al.  PANDA: a pipeline toolbox for analyzing brain diffusion images , 2013, Front. Hum. Neurosci..

[65]  F. Zwarts,et al.  GraphoGame SI: the development of a technology-enhanced literacy learning tool for Standard Indonesian , 2017, European Journal of Psychology of Education.

[66]  Michael Naehrig,et al.  CryptoNets: applying neural networks to encrypted data with high throughput and accuracy , 2016, ICML 2016.

[67]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[68]  Mufti Mahmud,et al.  Application of Convolutional Neural Network in Segmenting Brain Regions from MRI Data , 2019, BI.

[69]  Daniel Rueckert,et al.  Tract-based spatial statistics: Voxelwise analysis of multi-subject diffusion data , 2006, NeuroImage.

[70]  Nawaz Khan,et al.  An empirical approach to validate the Dyslexia Adaptive E-Learning (DAEL) framework , 2015, 2015 10th International Conference on Computer Science & Education (ICCSE).

[71]  Mufti Mahmud,et al.  Application of deep learning in detecting neurological disorders from magnetic resonance images: a survey on the detection of Alzheimer’s disease, Parkinson’s disease and schizophrenia , 2020, Brain Informatics.

[72]  F. Parker.  Dyslexia: an Overview , 2012 .

[73]  F. Ramus,et al.  How reliable are gray matter disruptions in specific reading disability across multiple countries and languages? insights from a large‐scale voxel‐based morphometry study , 2015, Human brain mapping.

[74]  Angela D. Friederici,et al.  The emergence of dyslexia in the developing brain , 2020, NeuroImage.

[75]  Hitoshi Kiya,et al.  Privacy-Preserving Deep Neural Networks with Pixel-Based Image Encryption Considering Data Augmentation in the Encrypted Domain , 2019, 2019 IEEE International Conference on Image Processing (ICIP).

[76]  Randy G. Floyd,et al.  Test Review: Wechsler Abbreviated Scale of Intelligence, Second Edition , 2013 .

[77]  Ravie Chandren Muniyandi,et al.  Review of GPU implementation to process of RNA sequence on cancer , 2018 .

[78]  Linjie Xing,et al.  DeepWriter: A Multi-stream Deep CNN for Text-Independent Writer Identification , 2016, 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR).

[79]  Zaixu Cui,et al.  Disrupted white matter connectivity underlying developmental dyslexia: A machine learning approach , 2016, Human brain mapping.

[80]  Jamie Zibulsky,et al.  Wide Range Achievement Test–Fourth Edition , 2014 .

[81]  A. Jothi Prabha,et al.  Predictive Model for Dyslexia from Fixations and Saccadic Eye Movement Events , 2020, Comput. Methods Programs Biomed..