Attention-decit/hyperactivity disorder (ADHD) is a common neuropsychiatric disorder that impairs social, academic, and occupational functioning in children, adolescents and adults. It is estimated that approximately as high as 10% of South African children have ADHD. Some dilemmas are however present in terms of the treatment of the disorder: rstly, there are no risk-free methods for its treatment and secondly, no fully objective diagnostic assessments exist. To date, very few quantitative methods have been successfully implemented. It is therefore necessary to further investigate methods that objectively diagnose, treat, and manage the disorder. The aim of the study is thus to develop a novel method that can be used as an aid to provide screening of ADHD. The method proposed is the form of a tablet-based game with underlying algorithms. The objective of the method is to dierentiate between an ADHD individual versus a non-ADHD individual, based on the way they play the game. A beta-testing phase was done and comprised of 30 children (19 non-ADHD and 11 ADHD) between the ages of 4 and 18 years old. The machine learning model that was used was linear support vector machine (SVM). Two datasets were used: 1) game-play dataset which included data such as task completion time and number of mistakes made and 2) accelerometer data set from the tri-axial accelerometer. A feature set was extracted from these two datasets and the best features were selected using sequential forward selection. These best features were then used for developing the classier. A test set accuracy of 85.7% was achieved. Leave-one-out cross-validation (LOOCV) was performed and its accuracy was 83.5%. An overall classication accuracy of 86.5% was achieved. For the application of a screening tool, sensitivity was deemed an important metric and. The model achieved a sensitivity of 75% which was seen as acceptable. The results of the classier were indicative that a quantitative tool could indeed be developed to screen for ADHD. iv Stellenbosch University https://scholar.sun.ac.za I would like to extend the most sincere gratitude and thanks to the following individuals: Prof. Pieter Fourie, for his guidance, vision, enthusiasm and inspiration, without which this project would not be possible. Prof. Fourie spoke to me at the end of my nal year undergrad and convinced me to join him on this project. Ever since then, it's been a great journey towards creating a tangible solution that would change many people's lives for the better. Romano Swart, my colleague, whose support and teamwork in the conceptualisation phases of the game design was very valuable. Mark Atkinson and his team, for delivering a high quality game that met the requirements of the project within a feasible budget and time frame. My family, for being an ever-present support structure throughout the course of the study and throughout all of my endeavours. Lastly, I would like to extend great gratitude to Ms. Veronica Mwamfupe, whose moral support has been tremendous. She's encouraged me an...
Attention-deficit/hyperactivity disorder (ADHD) is a common neuropsychiatric disorder that impairs social, academic and occupational functioning in children, adolescents and adults. In South Africa, youth prevalence of ADHD is estimated as 10%. It is therefore necessary to further investigate methods that objectively diagnose, treat and manage the disorder. The aim of the study was to develop a novel method that could be used as an aid to provide screening for ADHD. The study comprised of a beta-testing phase that included 30 children (19 non-ADHD and 11 ADHD) between the ages of 5 and 16 years old. The strategy was to use a tablet-based game that gathered real-time user data during game-play. This data was then used to train a linear binary support vector machine (SVM). The objective of the SVM was to differentiate between an ADHD individual versus a non-ADHD individual. A feature set was extracted from the gathered data and sequential forward selection (SFS) was performed to select the most significant features. The test set accuracy of 85.7% and leave-one-out cross-validation (LOOCV) accuracy of 83.5% were achieved. Overall, the classification accuracy of the trained SVM was 86.5%. Finally, the sensitivity of the model was 75% and this was seen as a moderate result. Since the sample size was fairly small, the results of the classifier were only seen as suggestive rather than conclusive. Therefore, the performance of the classifier was indicative that a quantitative tool could indeed be developed to perform screening for ADHD.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.