Machine-based classification of ADHD and nonADHD participants using time/frequency features of event-related neuroelectric activity

Öztoprak, Hüseyin; Toycan, Mehmet; Kemal, Yaşar; Arıkan, Orhan; Doğutepe, Elvin; Karakaş, Sirel

doi:10.1016/j.clinph.2017.09.105

Cited by 31 publications

(22 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These frequency bands are classically decomposed as delta (1–4 Hz), theta (4–7 Hz), alpha (8–15 Hz), beta (15–30 Hz) and gamma (30 Hz and more). Several studies investigated EEG rhythm in children with ADHD compared to TDC during event-related task [ 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 ]. In particular, studies showed atypical delta activity in ADHD during continuous performance task (CPT) [ 27 , 30 , 37 ].…”

Section: Introductionmentioning

confidence: 99%

EEG Dynamics of a Go/Nogo Task in Children with ADHD

et al. 2017

View full text Add to dashboard Cite

Background: Studies investigating event-related potential (ERP) evoked in a Cue-Go/NoGo paradigm have shown lower frontal N1, N2 and central P3 in children with attention-deficit/hyperactivity disorder (ADHD) compared to typically developing children (TDC). However, the electroencephalographic (EEG) dynamics underlying these ERPs remain largely unexplored in ADHD. Methods: We investigate the event-related spectral perturbation and inter-trial coherence linked to the ERP triggered by visual Cue-Go/NoGo stimuli, in 14 children (7 ADHD and 7 TDC) aged 8 to 12 years. Results: Compared to TDC, the EEG dynamics of children with ADHD showed a lower theta-alpha ITC concomitant to lower occipito-parietal P1-N2 and frontal N1-P2 potentials in response to Cue, Go and Nogo stimuli; an upper alpha power preceding lower central Go-P3; a lower theta-alpha power and ITC were coupled to a lower frontal Nogo-N3; a lower low-gamma power overall scalp at 300 ms after Go and Nogo stimuli. Conclusion: These findings suggest impaired ability in children with ADHD to conserve the brain oscillations phase associated with stimulus processing. This physiological trait might serve as a target for therapeutic intervention or be used as monitoring of their effects.

show abstract

Section: Introductionmentioning

confidence: 99%

EEG Dynamics of a Go/Nogo Task in Children with ADHD

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Artificial Intelligence (AI) and its most widely used form, machine learning, are another major topic not only in psychiatry but also in medicine in general due to its huge implications for promises and concerns. A growing number of studies rely on or utilize machine learning [54,55]. Contrary to many, studies have reported that patients could be more comfortable or encouraged to report their symptoms to so-called "Conversational Artificial Intelligence" [56].…”

Section: Recognizing Current Clinical Challengesmentioning

confidence: 99%

Developing a Digitally Informed Curriculum in Psychiatry Education and Clinical Practice

Kim

Torous

Chan³

et al. 2018

Acad Psychiatry

View full text Add to dashboard Cite

Technology is rapidly permeating the lives of our patients and influencing the clinical practice of psychiatry [1]. From electronic health record (EHR) systems to patient-focused smartphone apps, the way healthcare professionals communicate information with other professionals and with patients have been reshaped dramatically in the last decade [2]. This is partly due to increased access to smartphones [3], and partly due to nationwide initiatives to modernize the healthcare system with a goal to increase accuracy and efficiency. With increased access to technology, patients and their families have become proactive in obtaining information, rather than relying solely on education from their healthcare providers. Social media use also serves as an alternate avenue in obtaining medical information, including subscribing to interest groups and connecting to others with similar medical conditions [4,5].Millennial students and trainees in medicine have also developed proficiency and, even more so, preference for incorporating technology in their practice, learning, and daily lives [6]. However, they cite lack of guidance in education as a major barrier in incorporating technology fully in their practice [7]. Elements of teaching technology for child and adolescent psychiatry [8], rural and underserved psychiatry [9], and general adult psychiatry have been described. Despite demonstrated efficacy and desire among the early career physicians to incorporate technology in their practice, there is a notable discrepancy in culture and expectation of restraint around use of technology in various settings between generations [10].To further formalize the practice of incorporating technology in health systems and clinical practice, the Accreditation Council for Graduate Medical Education (ACGME) has accredited a new fellowship, named Clinical Informatics. To date, there are currently 26 Clinical Informatics fellowships across the country [11]. This new subspecialty enables candidates from any medical specialty to become experts in the informatics and analytics of medical care [12]. Despite the clear trend of increased technology use and need for defined competencies on this topic, there remains a lack of education in technology in general psychiatry and other psychiatry subspecialty trainings despite the rising number of issues associated with rapid infiltration of technology in our daily lives and thus our daily practice.In this article, we aim to explore the current state of technology education and the impact of technology on mental health, and discuss a pilot curriculum in providing a framework for evaluating various technologies in practice. To achieve such aims, the objectives of this article include (a) to develop a conceptual approach related to technology for clinical care, (b) to grasp the factors that drive the use of technology services and expected outcomes of its many users related to health, communication, and care, and (c) to discuss case examples of technology use utilizing the conceptualized approach.The Cha...

show abstract

“…By repeating the CV process n times, repeated CV (RCV) can provide greater diversity than CV. RCV has been shown to be an effective ensemble FS technique [4]; however, it has not been compared with BS. To the authors’ knowledge, this investigation is the first study in which RCV and BS are compared as ensemble FS methods.…”

Section: Introductionmentioning

confidence: 99%

Microarray‐based cancer diagnosis: repeated cross‐validation‐based ensemble feature selection

Guney

Öztoprak

2018

Electron. lett.

View full text Add to dashboard Cite

The influence of data resampling on ensemble methods, and repeated cross-validation (RCV)-based ensemble feature selection (FS) is proposed. To evaluate the proposed method, support vector machine and its extension and recursive feature elimination were used as the underlying classification and FS techniques, respectively. Experimental evaluation was performed using four microarray datasets. The results show that especially for extremely small signature sizes, increasing ensemble size increases both classification performance and the robustness of gene selection (stability) for both RCV and bootstrap (BS). However, for ensembles of the same size, RCV outperforms BS in terms of performance and especially stability. When compared to the top results obtained by two other studies in which BS is utilised, RCV performs similar or better in terms of area under the receiver operator curve and better in terms of stability.

show abstract

Machine-based classification of ADHD and nonADHD participants using time/frequency features of event-related neuroelectric activity

Abstract: The features obtained in this study can potentially contribute to the neuroelectrical understanding and clinical diagnosis of ADHD.

Cited by 31 publications

References 51 publications

EEG Dynamics of a Go/Nogo Task in Children with ADHD

EEG Dynamics of a Go/Nogo Task in Children with ADHD

Developing a Digitally Informed Curriculum in Psychiatry Education and Clinical Practice

Microarray‐based cancer diagnosis: repeated cross‐validation‐based ensemble feature selection

Contact Info

Product

Resources

About