scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Diagnosis of ADHD using SVM algorithm

J. Anuradha1, Tisha1, Varun Ramachandran1, K. V. Arulalan, B. K. Tripathy1 
22 Jan 2010-pp 29
TL;DR: This is the first attempt at diagnosing ADHD using SVM algorithm, and it is expected that AI techniques like SVM will certainly play an essential role in future ADHD diagnosis applications.
Abstract: Attention Deficit Hyperactivity Disorder (ADHD) is a Disruptive Behaviour Disorder characterized by the presence of a set of chronic and impairing behaviour patterns that display abnormal levels of inattention, hyperactivity, or their combination. Since most individuals especially children display these behaviours from time to time, it is be difficult to differentiate behaviours that reflect ADHD from those that are a normal part of growing up which makes the diagnosis a tricky job. In this paper, we apply a well known artificial intelligence technique, the SVM algorithm, for the diagnosis of the disorder. The major advantage of using SVM is that it helps in controlling the complexity of the problem of diagnosing. There has not been much development or research on ADHD using SVM algorithm. Hence this is the first attempt at diagnosing the problems using the algorithm. To improve on the overall identification accuracy; we also make use of the GA-based, Feature Selection Algorithm. Genetic algorithms are known to give good solution to very complex problems. In conclusion, we expect that AI techniques like SVM will certainly play an essential role in future ADHD diagnosis applications.
Citations
More filters
Journal ArticleDOI
TL;DR: This study proposes a DL framework for the ADHD identification problem by combining an EEG-based brain network with the CNN, and proposes a new form of the connectivity matrix to adapt the concept of the convolution operation of the CNN.

92 citations

Journal ArticleDOI
TL;DR: A brief review of the most representative research papers for computer-based applications for diagnosis and intervention purposes included the mobile learning and social media for technology enhanced learning for people with Attention Deficit Hyperactivity Disorder.
Abstract: Recent development in the role of Information and Communication Technologies (ICTs) at the field of special education is thought significant. ICT nowadays is recognized as a tool that can foster the knowledge and the experiences in the areas of needs it serves as it is considered significant for teaching and learning process. In the last decade, a number of studies have demonstrated the benefits of various forms of ICTs tools for children with attention difficulties and hyperactivity disorders (ADHD). These tools can be employed to facilitate and train young learners, as well as can help them to increase their quality of life and functional independence. In this paper we present a brief review of the most representative research papers for computer-based applications for diagnosis and intervention purposes included the mobile learning and social media for technology enhanced learning for people with Attention Deficit Hyperactivity Disorder.

60 citations


Cites background from "Diagnosis of ADHD using SVM algorit..."

  • ...Additionally, [Anuradha et al., 10] presented a platform for a more accurate and less time consuming assessment of Attention Deficit Hyperactivity Disorder (ADHD)....

    [...]

Journal ArticleDOI
TL;DR: A support vector machine classifier trained and tested for identification of robust marker of EEG patterns for accurate diagnosis of ADHD group and it is demonstrated that the applicability of the proposed approach provides higher accuracy in diagnostic process of ADHD disorder than the few currently available methods.
Abstract: Attention deficit hyperactivity disorder is a complex brain disorder which is usually difficult to diagnose As a result many literature reports about the increasing rate of misdiagnosis of ADHD disorder with other types of brain disorder There is also a risk of normal children to be associated with ADHD if practical diagnostic criteria are not supported To this end we propose a decision support system in diagnosing of ADHD disorder through brain electroencephalographic signals Subjects of 10 children participated in this study, 7 of them were diagnosed with ADHD disorder and remaining 3 children are normal group Our main goal of this sthudy is to present a supporting diagnostic tool that uses signal processing for feature selection and machine learning algorithms for diagnosisParticularly, for a feature selection we propose information theoretic which is based on entropy and mutual information measure We propose a maximal discrepancy criterion for selecting distinct (most distinguishing) features of two groups as well as a semi-supervised formulation for efficiently updating the training set Further, support vector machine classifier trained and tested for identification of robust marker of EEG patterns for accurate diagnosis of ADHD group We demonstrate that the applicability of the proposed approach provides higher accuracy in diagnostic process of ADHD disorder than the few currently available methods

51 citations

Journal ArticleDOI
TL;DR: A novel computer aided diagnosis system based on deep learning approach to classify the EEG signal of Healthy children (Control) from ADHD children with two subtypes of Combined ADHD (ADHD-C) and Inattentive ADHD ( ADHD-I).

44 citations

Journal Article
TL;DR: Several representative studies over the last decade are introduced, which use AI methods in making accurate diagnosis and prompt intervention action in the field of special educational needs.
Abstract: Artificial Intelligence (AI) technology has developed computer tools for carrying out a number of tasks, simulating the intelligent way of problem solving by humans. AI techniques have also been identified as one of the most valuable applications in the field of special educational needs (SEN). The goal of these tools is to enhance the way children interact with their environment to promote learning and to enrich their daily life. Due to the implicit characteristics of special educational needs, the diagnosis has been an issue ofmajor importance. At the same time intervention strategies need to be highly individualized to be effective. In this reportwe introduce some of themost representative studies over the last decade (2001–2010), which use AI methods in making accurate diagnosis and prompt intervention action.

42 citations

References
More filters
Book
03 Nov 2005
TL;DR: Barkley et al. as discussed by the authors discussed the nature of ADHD, primary symptoms, diagnosis criteria, prevalence, and gender differences, and the treatment of ADHD in adults.
Abstract: Part I: The Nature of ADHD. Barkley, History. Barkley, Primary Symptoms, Diagnostic Criteria, Prevalence, and Gender Differences. Barkley, Associated Cognitive, Developmental, and Health Problems. Barkley, Comorbid Disorders, Social and Family Adjustment, and Subtyping. Barkley, Etiologies. Barkley, ADHD in Adults: Developmental Course and Outcome of Children with ADHD, and ADHD in Clinic-referred Adults. Barkley, A Theory of ADHD. Part II: Assessment. Barkley, Edwards, Diagnostic Interview, Behavior Rating Scales, and the Medical Examination.Gordon, Barkley, Lovett, Tests and Observational Measures. Hathaway, Dooling-Litfin, Edwards, Integrating the Results of an Evaluation: Ten Clinical Cases. Murphy, Gordon, Assessment of Adults with ADHD. Part III: Treatment. Anastopoulos, Rhoads, Farley, Counseling and Training Parents. Cunningham, COPE: Large-group, Community-based, Family-centered Parent Training. Robin, Training Families with Adolescents with ADHD. Pfiffner, Barkley, DuPaul, Treatment of ADHD in School Settings. Cunningham, Cunningham, Student-mediated Conflict Resolution Programs. Connor, Stimulants. Spencer, Antidepressant and Specific Norepinephrine Reuptake Inhibitor Treatments. Connor, Other Medications. Smith, Barkley, Shapiro, Combined Child Therapies. Murphy, Psychological Counseling of Adults with ADHD. Prince, Wilens, Spencer, Biederman, Pharmacotherapy of ADHD in Adults.

4,151 citations

Journal ArticleDOI
TL;DR: The third edition of the classic textbook on Attention Deficit/hyperactivity disorder (ADHD) as mentioned in this paper was published in 1998 and has been widely used in the field of mental health.
Abstract: Psychiatric practitioners, seasoned and new alike, should welcome the recent publication of the third edition of Russell Barkley’s classic textbook on attention-deficit/hyperactivity disorder (ADHD). The first edition was published in 1981 and was followed by the second edition, which was published 17 years later in 1998. Fortunately, Dr. Barkley has not waited another 17 years to update his classic textbook, as research in the field of ADHD has accelerated considerably in recent years, making this new edition a much needed and anticipated addition to any practicing clinician’s library. While the structure of the new edition is basically the same in terms of chapters and topics (with the exception of 1 new chapter on combined child therapies), there are many new and welcome added features. Most notably, there is now a section at the end of each chapter entitled “Key Clinical Points,” which highlights and summarizes learning points for the reader. The value of this cannot be overstated, particularly for the busy clinician! Furthermore, Dr. Barkley has included in Appendix I, at the end of chapter 1, an International Consensus Statement on ADHD that he and many other experts coauthored in 2002, which does much to dispel many of the myths about ADHD propagated in the media and by some special interest groups. The book is very well written, well edited, and well referenced and includes material dated through the year 2004 and some references from 2005. The lag between the date of these articles and the publication date of this book in 2006 is to be expected, given the long lead time for the compilation and publication of textbooks. Lastly, there is now an accompanying “Clinical Workbook” that provides many useful forms and rating scales for the busy practitioner. Dr. Barkley invited back all of the principal authors of chapters from the 1998 edition of the book, and some chapters were written by other experts. The first-time reader of any edition of this book will find the initial chapters particularly fascinating, especially chapter 1 on the history of ADHD, as these chapters summarize trends and changes in the field that have occurred since the 1930s. It is also noteworthy in this era of massive textbooks with multiple contributors that Part I of this book on the “Nature of ADHD,” with 7 chapters, is written and updated entirely by Dr. Barkley. This section forms a solid basis upon which the other 2 sections of the book, “Assessment” and “Treatment,” can build. A high point in the first part of the book is Dr. Barkley’s conceptual, theoretical model of self-regulation and executive dysfunction presented in chapter 7, which integrates quite well extant research findings in imaging, neurobiology, and neuropsychology. Part II of this new edition, “Assessment,” includes 4 expanded and improved chapters on topics such as the diagnostic interview, rating scales, tests, and the assessment of adults with ADHD. There is also an expanded chapter 10, which includes 10 clinical cases presented to integrate and facilitate the development of diagnosis and treatment strategies. This chapter will be particularly useful for clinicians, since it presents a variety of cases of ADHD and the common or challenging psychiatric comorbid disorders such as oppositional defiant, anxiety, and bipolar disorder. Part III, “Treatment,” includes 11 chapters on interventions, such as medications, psychotherapy, and psychoeducation for patients and their families. A particularly well written chapter is chapter 20 on combined child therapies, in which Dr. Barkley and his coauthors review findings from the historic National Institute of Mental Health Multimodal Treatment Study of Children With ADHD. There are a few minor suggestions for the next edition that would make this already valuable book even better. Expansion of the number of figures and tables, particularly in the section on treatment, and the addition of flowcharts to aid in decision making would highlight key recommendations in the text. It would also be helpful if such decision trees included further recommendations or even algorithms on addressing the psychiatric comorbid disorders such as tic disorders, obsessive-compulsive disorder, and the others described in chapter 10. The author index is valuable; perhaps one comprehensive bibliography at the end of the book might reduce some redundancy incurred with the individual chapter bibliographies. In this era of the Internet, a future edition could include a CD-ROM or a linked Web page, where at least the bibliography would be incorporated so as to facilitate retrieval of the primary research articles and references for future research. In summary, this new edition is a compelling update to a vast and ever-growing literature on a very prevalent, potentially devastating disorder. We highly recommend this book to clinicians and investigators in mental health.

2,493 citations

Proceedings Article
01 Jan 2002
TL;DR: The proposed extensions of the Support Vector Machine learning approach lead to mixed integer quadratic programs that can be solved heuristic ally and a generalization of SVMs makes a state-of-the-art classification technique, including non-linear classification via kernels, available to an area that up to now has been largely dominated by special purpose methods.
Abstract: This paper presents two new formulations of multiple-instance learning as a maximum margin problem. The proposed extensions of the Support Vector Machine (SVM) learning approach lead to mixed integer quadratic programs that can be solved heuristic ally. Our generalization of SVMs makes a state-of-the-art classification technique, including non-linear classification via kernels, available to an area that up to now has been largely dominated by special purpose methods. We present experimental results on a pharmaceutical data set and on applications in automated image indexing and document categorization.

1,556 citations


"Diagnosis of ADHD using SVM algorit..." refers background in this paper

  • ...Parameter C determines the trade off between the model complexity (flatness) and the degree to which deviations larger than are tolerated in optimization formulation for example, if C is too large (infinity), then the objective is to minimize the empirical risk only, without regard to model complexity part in the optimization formulation [ 4 ]....

    [...]

Proceedings Article
01 Jan 2000
TL;DR: The resulting algorithms are shown to be superior to some standard feature selection algorithms on both toy data and real-life problems of face recognition, pedestrian detection and analyzing DNA microarray data.
Abstract: We introduce a method of feature selection for Support Vector Machines. The method is based upon finding those features which minimize bounds on the leave-one-out error. This search can be efficiently performed via gradient descent. The resulting algorithms are shown to be superior to some standard feature selection algorithms on both toy data and real-life problems of face recognition, pedestrian detection and analyzing DNA microarray data.

1,112 citations


"Diagnosis of ADHD using SVM algorit..." refers background in this paper

  • ...…Dr. B.K.Tripathy Senior Professor VIT University Tamil Nadu tripathybk@rediffmail.com Varun Ramachandran B.Tech(IT) VIT University Tamil Nadu +91-9952212336 varun.ramachandran89@gmail.com Abstract Attention Deficit Hyperactivity Disorder (ADHD) is a Disruptive Behaviour Disorder…...

    [...]

Journal ArticleDOI
TL;DR: This clinical practice guideline provides recommendations for the assessment and diagnosis of school-aged children with attention-deficit/hyperactivity disorder (ADHD).
Abstract: This clinical practice guideline provides recommendations for the assessment and diagnosis of school-aged children with attention-deficit/hyperactivity disorder (ADHD). This guideline, the first of 2 sets of guidelines to provide recommendations on this condition, is intended for use by primary care clinicians working in primary care settings. The second set of guidelines will address the issue of treatment of children with ADHD. The Committee on Quality Improvement of the American Academy of Pediatrics selected a committee composed of pediatricians and other experts in the fields of neurology, psychology, child psychiatry, development, and education, as well as experts from epidemiology and pediatric practice. In addition, this panel consists of experts in education and family practice. The panel worked with Technical Resources International, Washington, DC, under the auspices of the Agency for Healthcare Research and Quality, to develop the evidence base of literature on this topic. The resulting evidence report was used to formulate recommendations for evaluation of the child with ADHD. Major issues contained within the guideline address child and family assessment; school assessment, including the use of various rating scales; and conditions seen frequently among children with ADHD. Information is also included on the use of current diagnostic coding strategies. The deliberations of the committee were informed by a systematic review of evidence about prevalence, coexisting conditions, and diagnostic tests. Committee decisions were made by consensus where definitive evidence was not available. The committee report underwent review by sections of the American Academy of Pediatrics and external organizations before approval by the Board of Directors. The guideline contains the following recommendations for diagnosis of ADHD: 1) in a child 6 to 12 years old who presents with inattention, hyperactivity, impulsivity, academic underachievement, or behavior problems, primary care clinicians should initiate an evaluation for ADHD; 2) the diagnosis of ADHD requires that a child meet Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition criteria; 3) the assessment of ADHD requires evidence directly obtained from parents or caregivers regarding the core symptoms of ADHD in various settings, the age of onset, duration of symptoms, and degree of functional impairment; 4) the assessment of ADHD requires evidence directly obtained from the classroom teacher (or other school professional) regarding the core symptoms of ADHD, duration of symptoms, degree of functional impairment, and associated conditions; 5) evaluation of the child with ADHD should include assessment for associated (coexisting) conditions; and 6) other diagnostic tests are not routinely indicated to establish the diagnosis of ADHD but may be used for the assessment of other coexisting conditions (eg, learning disabilities and mental retardation). This clinical practice guideline is not intended as a sole source of guidance in the evaluation of children with ADHD. Rather, it is designed to assist primary care clinicians by providing a framework for diagnostic decisionmaking. It is not intended to replace clinical judgment or to establish a protocol for all children with this condition and may not provide the only appropriate approach to this problem.

1,033 citations