Investigating sensitivity to multi-domain prediction errors in chronic auditory phantom perception.

The perception of a continuous phantom in a sensory domain in the absence of an external stimulus is explained as a maladaptive compensation of aberrant predictive coding, a proposed unified theory of brain functioning. If this were true, these changes would occur not only in the domain of the phantom percept but in other sensory domains as well. We confirm this hypothesis by using tinnitus (continuous phantom sound) as a model and probe the predictive coding mechanism using the established local-global oddball paradigm in both the auditory and visual domains. We observe that tinnitus patients are sensitive to changes in predictive coding not only in the auditory but also in the visual domain. We report changes in well-established components of event-related EEG such as the mismatch negativity. Furthermore, deviations in stimulus characteristics were correlated with the subjective tinnitus distress. These results provide an empirical confirmation that aberrant perceptions are a symptom of a higher-order systemic disorder transcending the domain of the percept.

The P300 wave is decomposed into components reflecting response selection and automatic reactivation of stimulus-response links.

The parietal P300 wave of event-related potentials (ERPs) has been associated with various psychological operations in numerous laboratory tasks. This study aims to decompose the P3 wave of ERPs into subcomponents and link them with behavioral parameters, such as the strength of stimulus-response (S-R) links and GO/NOGO responses. EEGs (31 channels), referenced to linked ears, were recorded from 172 healthy adults (107 women) who participated in two cued GO/NOGO tasks, where the strength of S-R links was manipulated through instructions. P300 waves were observed in active conditions in response to cues, GO/NOGO stimuli, and in passive conditions when no manual response was required. Utilizing a combination of current source density transformation and blind source separation methods, we decomposed the P300 wave into two distinct components, purportedly originating from different parts of the parietal lobules. The amplitude of the parietal midline component (with current sources around Pz) closely mirrored the strength of the S-R link across proactive, reactive, and passive conditions. The amplitude of the lateral parietal component (with current sources around P3 and P4) resembled the push-pull activity of the output nuclei of the basal ganglia in action selection-inhibition operations. These findings provide insights into the neural mechanisms underlying action selection processes and the reactivation of S-R links.

Is Visual Prediction Impaired in Adolescents with Autism spectrum Disorder? Event-Related Potentials in a Cued Visual GO/NOGO Task.

Aim: Deviant visual processing has been observed in autism spectrum disorder (ASD), manifesting as decreased P1 and P2 components of visual event-related potentials (ERPs). Alterations have been attributed to a failure of Bayesian inference, characterized by hypo-activation of top-down predictive abilities. To test this hypothesis, we measured the visual negativity (vN) as an ERP index of visual preparation hypothesized to mirror predictive brain activity. Method: ERPs in a cued visual GO/NOGO task in 63 adolescents with ASD (IQ > 70, attention-deficit hyperactivity disorder excluded) were compared with ERPs in a sex- and age-matched group of 60 typically developing (TD) controls. Results: The behavioral variables (omissions, commissions, reaction time, and reaction time variability), as well as ERP components reflecting, among other processes, cognitive control (contingent negative variation, P3 GO, P3 NOGO, N2 NOGO) did not differ between the groups. There were group differences in visually based ERPs. Besides P1 and P2 differences, the vN component differentiated the 2 groups with the highest effect size (d = 0.74).Conclusion: This ERP study lends support to the hypothesis suggesting that a Bayesian hypo-prediction could underlie unique perceptual experiences in individuals with ASD. This could lead to a predisposition to perceive the world with reduced influence and modulation from contextual cues, prior experiences, and pre-existing expectations.

The enigma of infra-slow fluctuations in the human EEG.

Spontaneous Infra-Slow Fluctuations (ISFs) of the human EEG (EEG-ISFs) were discovered 60 years ago when appropriate amplifiers for their recordings were designed. To avoid skin-related artifacts the recording of EEG-ISFs required puncturing the skin under the electrode. In the beginning of the 21st century the interest in EEG-ISFs was renewed with the appearance of commercially available DC-coupled amplified and by observation of ISFs of the blood oxygen level-dependent (BOLD) functional magnetic resonance imaging signal at a similar frequency. The independent components of irregular EEG-ISFs were shown to correlate with BOLD signals which in turn were driven by changes in arousal level measured by galvanic skin response (GSR), pupil size and HRV. There is no consensus regarding the temporal organization of EEG-ISFs: some studies emphasize the absence of peaks on EEG-ISFs spectra, some studies report prominent oscillations with frequency around 0.1 or 0.02 Hz, while some emphasize multiple discrete infraslow oscillations. No studies used parameters of EEG-ISFs as neuromarkers to discriminate psychiatric patients from healthy controls. Finally, a set of working hypotheses is suggested that must be tested in future research to solve the enigma of EEG-ISFs.

Event Related Potentials (ERPs) and other EEG Based Methods for Extracting Biomarkers of Brain Dysfunction: Examples from Pediatric Attention Deficit/Hyperactivity Disorder (ADHD).

Neuropsychiatric diagnoses like ADHD are based on subjective methods like interviews, rating scales and observations. There is a need for more brain-based supplements. Stimulant medication is the most common treatment for ADHD. Clinically useful predictors of response have so far not been reported. The aim of this paper is to describe the EEG based methods we apply to extract potential biomarkers for brain dysfunction. Examples relate to biomarkers for pediatric ADHD, and prediction of medication response. The main emphasis is on Event Related Potentials (ERPs). A nineteen channel EEG is recorded during a 3 min eyes-opened task, a 3 min eyes-closed task, and a 20 min cued visual GO/NOGO task (VCPT). ERPs are recorded during this task. The goal of the ERP protocol is to extract biomarkers of assumed brain dysfunctions that significantly differentiate between a patient group and healthy controls. The protocol includes recording during standard conditions and artifact correction. ERP waves can be used or transformed into latent components. The components of the patient group are compared with controls, empathizing components that, when compared, show relatively high effect sizes. Sub-groups of the patients are selected on the basis of the cluster analysis in the space of the components. Treatment procedure (such as medication, tDCS or neurofeedback protocol) can be applied and the changes in components related to treatment in the subgroups are observed, forming the basis for clinical recommendations. The methods described were applied in a study of 87 pediatric ADHD patients. The index of medication response discriminated significantly between responders and non-responders with a large, and clinically meaningful effect size (d = 1.84). In an ongoing study comparing ADHD children with matched controls, several variables discriminate significantly between patients and controls. The global index will exceed d = .8. The EEG based methods described here could be clinically meaningful.

EEG/ERP-based biomarker/neuroalgorithms in adults with ADHD: Development, reliability, and application in clinical practice.

Objectives: The electrophysiological characteristics of attention-deficit/hyperactivity disorder (ADHD) and recent machine-learning methods promise easy-to-use approaches that can complement existing diagnostic tools when sufficiently large samples are used. Neuroalgorithms are models of multidimensional brain networks by means of which ADHD patient data can be separated from healthy control data.Methods: Spontaneous electroencephalographic and event-related potential (ERP) data were collected three times over the course of 2 years from a multicentre sample of adults comprising 181 patients with ADHD and 147 healthy controls. Spectral power and ERP amplitude and latency measures were used as input data for a semi-automatic machine-learning framework.Results: ADHD patients and healthy controls could be classified with a sensitivity ranging from 75% to 83% and specificity values of 71% to 77%. In the analysis of the repeated measurements, sensitivity values of the selected logistic regression model remained high (72% and 76%), while specificity values slightly decreased over time (64% and 67%).Conclusions: Implementation of the system in clinical practice requires facilities to track affected networks, as well as expertise in neuropathophysiology. Therefore, the use of neuroalgorithms can enhance the diagnostic process by making it less subjective and more reliable and linking it to the underlying pathology.

Latent ERP components of cognitive dysfunctions in ADHD and schizophrenia.

OBJECTIVE: The main goal was to assess common and specific deficits of cognitive control in (Attention Deficit Hyperactivity Disorder) ADHD and schizophrenia (SZ) using event-related potentials (ERPs). METHOD: Behavioral and EEG data in cued GO/NOGO task were recorded in 132 healthy controls (HC) and age, gender and education matched 63 ADHD adults, and 68 SZ patients. RESULTS: N2d wave in NOGO-GO contrast of ERPs did not differ between the groups while the P3d wave discriminated SZ group from two other groups. Latent components of ERPs were extracted by blind source separation method based on second-order statistics Kropotov et al. (2017) and compared between the groups. A counterpart of N2d wave of a frontally distributed latent component was smaller in SZ indicating a specific frontal dysfunction of conflict detection in SZ. Two centrally distributed P3 sub-components were reduced in both groups indicating a non-specific dysfunction of action inhibition operations in ADHD and SZ. CONCLUSION: A pattern of specific and common dysfunctions in terms of latent ERP components shows a more complex picture of functional impairment in schizophrenia and ADHD in comparison to conventional N2/P3 ERP description. SIGNIFICANCE: The latent component approach shows a functionally different pattern of cognitive control impairment in comparison to the conventional ERP analysis.

Predicting Clinical Gains and Side Effects of Stimulant Medication in Pediatric Attention-Deficit/Hyperactivity Disorder by Combining Measures From qEEG and ERPs in a Cued GO/NOGO Task.

OBJECTIVES: The study aim was to develop 2 scales: predicting clinical gains and risk of acute side effects of stimulant medication in pediatric attention-deficit/hyperactivity disorder (ADHD), combining measures from EEG spectra, event-related potentials (ERPs), and a cued visual GO/NOGO task. METHODS: Based on 4-week systematic medication trials, 87 ADHD patients aged 8 to 17 years were classified as responders (REs, n = 62) or non-REs (n = 25), and belonging to the side effects (SEs, n = 42) or no-SEs (n = 45) groups. Before starting the trial, a 19-channel EEG was registered twice: Test 1 (T1) without medication and T2 on a single dose of stimulant medication a few days before the trial. EEG was registered T1 and T2: 3 minutes eyes-closed, 3 minutes eyes-open, and 20 minutes cued GO/NOGO. EEG spectra, ERPs, omissions, commissions, reaction time (RT), and RT variability were computed. Groups were compared at T1 and T2 on quantitative EEG (qEEG), ERPs and behavioral parameters; effect sizes ( d) were estimated. Variables with d > 0.5 were converted to quartiles, multiplied by corresponding d, and summed to obtain 2 global scales. RESULTS: Six variables differed significantly between REs and non-REs (T1: theta/alpha ratio, P3NOGO amplitude. Differences T2-T1: Omissions, RT variability, P3NOGO, contingent negative variation [CNV]). The global scale d was 1.86. Accuracy (receiver operating characteristic) was 0.92. SEs and no-SEs differed significantly on 4 variables. (T1: RT, T2: novelty component and alpha peak frequency, and RT changes. Global scale d = 1.08 and accuracy = 0.78. CONCLUSION: Gains and side effects of stimulants in pediatric ADHD can be predicted with high accuracy by combining EEG spectra, ERPs, and behavior from baseline and single-dose tests. ClinicalTrials.gov identifier: NCT02695355.

Functional indexes of reactive cognitive control: ERPs in cued go/no-go tasks.

We aimed to determine the functional meaning of latent (hidden) components decomposed from ERPs, in the context of a go/no-go paradigm. To accomplish this, we used a new group blind source separation method, based on joint diagonalization of covariance matrices of ERPs. Four variants of a frequently used go/no-go paradigm were designed, in which operations of reactive cognitive control, such as conflict detection and action inhibition, were independently manipulated. The results showed that a latent component, generated in the anterior cingulate cortex, induced N2/P3 fluctuation only in conditions in which the prepotent model was violated, and thus can be associated with conflict detection operations. In contrast, the two latent components generated in the vicinity of the central sulcus induced P3-like fluctuations in conditions in which the prepared action was suppressed, and thus can be associated with action inhibition operations. The advantages and limitations of the new blind source separation method in relation to ERP research are also discussed.

Neuromarkers of Post-Traumatic Stress Disorder (PTSD) in a patient after bilateral hand amputation - ERP case study.

Introduction. There is a lack in the worldwide literature of reports on the Neuromarkers of Post-Traumatic Stress Disorder (PTSD) in patients after bilateral hand amputation The aim of this study was to test a hypothesis regarding developing Post-Traumatic Stress Disorder (PTSD) in a patient after bilateral hand amputation with the use of Event Related Potentials (ERPs). On the basis of previous research, the amplitudes of P3 ERP components elicited in the cued GO/NOGO tasks have been chosen as candidates for neuromarkers of PTSD. Case study. A 24-year-old patient had undergone bilateral hand amputation 12 months previously. The patient was repeatedly operated on (he had undergone successful bilateral hand replantation) and despite the severity of the injuries, he recovered. However, the patient complained of flashbacks, anxiety and sleep difficulties. Specialist tests showed the presence of PTSD. The patient participated in the cued GO/NOGO task (Kropotov, 2009) with recording 19-channel EEG. P3 GO and NOGO waves in this task were found to be significantly smaller, in comparison to a group of healthy control subjects of the same age (N=23) taken from the HBI normative database (https://www.hbimed.com/). This observed pattern of ERP waves in the patient corresponds to the pattern found in PTSD patients. Conclusions. ERPs in a GO/NOGO task can be used in the assessment of the functional brain changes induced by chronic PTSD.

Application of ERPs neuromarkers for assessment and treatment of a patient with chronic crossed aphasia after severe TBI and long-term coma - Case Report.

 Objective. The study aimed to evaluate the application of ERPs neuromarkers for the assessment and treatment of a patient with chronic crossed aphasia after severe TBI and a long-term coma. CASE REPORT: An ambidextrous female patient, aged 29, suffered from posttraumatic chronic crossed aphasia, severe TBI and a prolonged coma after a car accident. The patient took part in two differentiated rehabilitation programmes of neurotherapy included 20 sessions of relative beta training and 20 sessions of rTMS; both programmes were combined with behavioural training. The patient was tested 3 times: before the experiment, after completion of programme A, and after completion of programme B. RESULTS: In the 1st recording, the neuromarker of aphasia was found - an excess of the P2 wave over the left temporal area. There was a cognitive control deficit - an excess of omission errors and an increase of RT variability - all indexes of sporadic ADHD. In the 2nd recording, slight improvements in cognitive control, and language functions were found. In the 3rd recording, after the rTMS sessions most of her cognitive dysfunctions had been resolved, including language functions. It should be stressed that the activation (especially the increase in the ERP potential of the right side over the frontal lobe) was found. The neuromarker of aphasia did not change, only the location had slightly moved frontally. CONCLUSIONS: The application of ERP neuromarkers assists in the diagnosis, treatment, and academic success of an ambidextrous patient with chronic posttraumatic aphasia and sporadic ADHD. ERPs can be used to assess the functional brain changes induced by neurotherapeutical programmes.

Local and Widely Distributed EEG Activity in Schizophrenia With Prevalence of Negative Symptoms.

We evaluated EEG frequency abnormalities in resting state (eyes closed and eyes open) EEG in a group of chronic schizophrenia patients as compared with healthy subjects. The study included 3 methods of analysis of deviation of EEG characteristics: genuine EEG, current source density (CSD), and group independent component (gIC). All 3 methods have shown that the EEG in schizophrenia patients is characterized by enhanced low-frequency (delta and theta) and high-frequency (beta) activity in comparison with the control group. However, the spatial pattern of differences was dependent on the type of method used. Comparative analysis has shown that increased EEG power in schizophrenia patients apparently concerns both widely spatially distributed components and local components of signal. Furthermore, the observed differences in the delta and theta range can be described mainly by the local components, and those in the beta range mostly by spatially widely distributed ones. The possible nature of the widely distributed activity is discussed.

Hyper-frontality in an OCD patient - evidence from event-related potentials in a cued GO/NOGO task.

OBJECTIVE: The study aimed to evaluate the hyperactivity of the frontal lobes in a patient with obsessive-compulsive disorders. CASE DESCRIPTION: A 21-year-old female met the diagnostic criteria of DSM-5 since her behaviour was characterized by a preoccupations with negative thoughts and by repetitive attempts to decrease or stop those behaviours. Two working hypotheses were tested to find neuromarkers of OCD and anxiety in the patient described. In agreement with the 'OCD hypothesis' an increase of the frontal beta activity and an increase of the parietalalpha activity pattern was found. The 'anxiety' hypothesis found confirmation in an increased left temporal P1 wave in response to the visual stimuli observed in ERPs. In all three conditions (EO, EC, GO/NOGO task), two characteristics were deviant from the normative average data in EEG spectra. First, an increase of frontal beta activity and the increase of parietal alpha activity was noted. The independent component analysis applied for 700 ms EEG fragments in GO and NOGO conditions revealed a strong activation over the central areas. CONCLUSIONS: Specific patterns of QEEG and ERPs, the increase of beta activity frontally, and the increase of parietal alpha activity pattern which produce hyper-frontality, might be useful in the diagnosis of an OCD patient. ERPs in a GO/NOGO task can be used in the assessment of functional brain changes in OCD patients.

Neuromarkers of anxiety and depression in a patient after neuro-ophthalmic surgery of the meningioma - effect of individually-tailored tDCS and neurofeedback.

UNLABELLED: The aim of the study was to evaluate the effectiveness of individually tailored anodal tDCs/ neurofeedback protocol for the reduction of post-operative depression after a neuroophtalmological operation of the meningioma. The neuromarkers in Quantitative EEG (QEEG) and Event-related potentials (ERPs) were utilized in the construction of protocol and evaluation. CASE DESCRIPTION: A 45-year-old female after successful neuro-ophthalmic surgery of the meningioma, complained of severe pain and anxiety, difficulties with sleeping, attention and memory problems, as well as inability to continue working in her given profession. Neuropsychological testing showed lack of cognitive disturbances and post-operative depression. Two working hypotheses were tested to find neuromarkers of depression and anxiety. In line with the 'depression hypothesis' a frontal alpha asymmetry pattern was found in the patient, and in line with the 'anxiety' hypothesis an increased left temporal P1 wave in response to visual stimuli was found in ERPs. A specific alpha asymmetry neurofeedback protocol combined with an anodal tDCS was suggested. Twenty sessions of individually-tailored anodal tDCs/ neurofeedback protocol were performed. The QEEG frontal asymmetry pattern and the excessive temporal P1 wave were normalized after the intervention. CONCLUSIONS: The patient recovered from post-operative depression and returned to work after 20 sessions of the combined neurofeedback/tDCS protocol. Specific patterns of QEEG and ERPs serve as neuromarkers for constructing the protocol and for monitoring the results of intervention.

Evaluation of the effectiveness of neurofeedback in the reduction of Posttraumatic stress disorder (PTSD) in a patient following high-voltage electric shock with the use of ERPs.

BACKGROUND: The aim of our research was an evaluation of the effectiveness of neurofeedback in reducing the symptoms of Post-trauma stress disorder (PTSD), which had developed as a result of a high-voltage electric burn to the head. Quantitative EEG (QEEG) and Event related potentials (ERPs) were utilised in the evaluation. CASE STUDY: A 21-year-old patient, experienced 4(th) degree burns to his head as a result of a high-voltage electric burn. The patient was repeatedly operated on and despite the severity of the injuries was to recover. However the patient complained of flashbacks, difficulties with sleeping as well as an inability to continue work in his given profession. Specialist tests were to show the presence within him of PTSD. As a result of which the patient was provided with neurofeedback therapy. The effectiveness of this therapy in the reduction (eradication) of the symptoms of PTSD were evaluated through the utilisation of qantitative eeg (Qeeg) and event related potentials (ERPs). RESULTS: It was found that in the first examination that ERPs display the most significant deviations from the reference in the two components: (1) the one component is generated within the cingulate cortex. The pattern of its deviation from the norms is similar to that found in a group of OCD patients. In contrast to healthy subjects the component repeats itself twice; (2) the second component is generated in the medial prefrontal cortex. Its pattern (neuromarker) is similar to that found in PTSD patients. There is a delay in the late part of the component, which probably reflects the flashbacks. In the second examination, after neurofeedback training, the ERPs were similar to the norm. The patient returned to work. CONCLUSIONS: Chronic PTSD developed within the patient as a result of a high-voltage electric burn. The application of a method of therapy (neurofeedback) resulted in the withdrawal of the syndrome symptoms. ERPs in a GO/NOGO task can be used to plan neurofeedback and in the assessment of functional brain changes induced by neurotherapeutic programmes. Funds Collection: Private sources.

Neuropsychological rehabilitation for traumatic brain injury patients.

The aim of this review is to discuss the basic forms of neuropsychological rehabilitation for patients with traumatic brain injury (TBI). More broadly, we discussed cognitive rehabilitation therapy (CRT) which constitutes a fundamental component in therapeutic interaction at many centres worldwide. Equally presented is a comprehensive model of rehabilitation, the fundamental component of which is CRT. It should be noted that the principles of this approach first arose in Poland in the 1970s, in other words, several decades before their appearance in other programmemes. Taken into consideration are four factors conditioning the effectiveness of such a process: comprehensiveness, earlier interaction, universality and its individualized character. A comprehensive programmeme of rehabilitation covers: cognitive rehabilitation, individual and group rehabilitation with the application of a therapeutic environment, specialist vocational rehabilitation, as well as family psychotherapy. These training programmemes are conducted within the scope of the 'Academy of Life,' which provides support for the patients in their efforts and shows them the means by which they can overcome existing difficulties. Equally emphasized is the close cooperation of the whole team of specialists, as well as the active participation of the family as an essential condition for the effectiveness of rehabilitation and, in effect, a return of the patient to a relatively normal life. Also presented are newly developing neurothechnologies and the neuromarkers of brain injuries. This enables a correct diagnosis to be made and, as a result, the selection of appropriate methods for neuropsychological rehabilitation, including neurotherapy.

Differentiation of neuronal operations in latent components of event-related potentials in delayed match-to-sample tasks.

The goal of this study was to decompose ERPs into latent components associated with hypothetical processes of category discrimination, comparison to working memory and action-related operations. In five variants of the delayed match-to-sample s1-s2 task, instructions were varied for manipulation of the processes. The blind source separation was applied to the collection of ERPs. The category discrimination operation is attributed to three latent components with peak latencies of 130 to 170 ms, which are generated in different parts of the prestriate cortex. The comparison to working memory operation is attributed to a latent component that is generated in the temporal cortex and manifested in a positive deflection with a peak latency of 250 ms after s2. The category discrimination and comparison to working memory effects were dissociated spatially and temporally from attention and action selection effects.

Group Independent Component Analysis (gICA) and Current Source Density (CSD) in the study of EEG in ADHD adults.

OBJECTIVE: To investigate the performance of the spectral analysis of resting EEG, Current Source Density (CSD) and group independent components (gIC) in diagnosing ADHD adults. METHODS: Power spectra of resting EEG, CSD and gIC (19 channels, linked ears reference, eyes open/closed) from 96 ADHD and 376 healthy adults were compared between eyes open and eyes closed conditions, and between groups of subjects. RESULTS: Pattern of differences in gIC and CSD spectral power between conditions was approximately similar, whereas it was more widely spatially distributed for EEG. Size effect (Cohen's d) of differences in gIC and CSD spectral power between groups of subjects was considerably greater than in the case of EEG. Significant reduction of gIC and CSD spectral power depending on conditions was found in ADHD patients. Reducing power in a wide frequency range in the fronto-central areas is a common phenomenon regardless of whether the eyes were open or closed. CONCLUSIONS: Spectral power of local EEG activity isolated by gICA or CSD in the fronto-central areas may be a suitable marker for discrimination of ADHD and healthy adults. SIGNIFICANCE: Spectral analysis of gIC and CSD provides better sensitivity to discriminate ADHD and healthy adults.

Evaluation of differentiated neurotherapy programs for a patient after severe TBI and long term coma using event-related potentials.

BACKGROUND: This article examines the effectiveness of differentiated rehabilitation programs for a patient with frontal syndrome after severe TBI and long-term coma. We hypothesized that there would be a small response to relative beta training, and a good response to rTMS, applied to regulate the dynamics of brain function. CASE REPORT: M. L-S, age 26, suffered from anosognosia, executive dysfunction, and behavioral changes, after a skiing accident and prolonged coma, rendering him unable to function independently in many situations of everyday life. Only slight progress was made after traditional rehabilitation. The patient took part in 20 sessions of relative beta training (program A) and later in 20 sessions of rTMS (program B); both programs were combined with behavioral training. We used standardized neuropsychological testing, as well as ERPs before the experiment, after the completion of program A, and again after the completion of program B. As hypothesized, patient M.L-S showed small improvements in executive dysfunction and behavioral disorders after the conclusion of program A, and major improvement after program B. Similarly, in physiological changes the patient showed small improvement after relative beta training and a significant improvement of the P300 NOGO component after the rTMS program. CONCLUSIONS: The rTMS program produced larger physiological and behavioral changes than did relative beta training. A combination of different neurotherapeutical approaches (such as neurofeedback, rTMS, tDCS) can be suggested for similar severe cases of TBI. ERPs can be used to assess functional brain changes induced by neurotherapeutical programs.

Discriminating between ADHD adults and controls using independent ERP components and a support vector machine: a validation study.

BACKGROUND: There are numerous event-related potential (ERP) studies in relation to attention-deficit hyperactivity disorder (ADHD), and a substantial number of ERP correlates of the disorder have been identified. However, most of the studies are limited to group differences in children. Independent component analysis (ICA) separates a set of mixed event-related potentials into a corresponding set of statistically independent source signals, which are likely to represent different functional processes. Using a support vector machine (SVM), a classification method originating from machine learning, this study aimed at investigating the use of such independent ERP components in differentiating adult ADHD patients from non-clinical controls by selecting a most informative feature set. A second aim was to validate the predictive power of the SVM classifier by means of an independent ADHD sample recruited at a different laboratory. METHODS: Two groups of age-matched adults (75 ADHD, 75 controls) performed a visual two stimulus go/no-go task. ERP responses were decomposed into independent components, and a selected set of independent ERP component features was used for SVM classification. RESULTS: Using a 10-fold cross-validation approach, classification accuracy was 91%. Predictive power of the SVM classifier was verified on the basis of the independent ADHD sample (17 ADHD patients), resulting in a classification accuracy of 94%. The latency and amplitude measures which in combination differentiated best between ADHD patients and non-clinical subjects primarily originated from independent components associated with inhibitory and other executive operations. CONCLUSIONS: This study shows that ERPs can substantially contribute to the diagnosis of ADHD when combined with up-to-date methods.