Diagnosing Attention-Deficit/Hyperactivity Disorder (ADHD) in young adults: A qualitative review of the utility of assessment measures and recommendations for improving the diagnostic process

Prediction of attention deficit hyperactivity disorder based on explainable artificial intelligence

Accurate assessment of Attention Deficit Hyperactivity Disorder (ADHD) is crucial for the effective treatment of affected individuals. Traditionally, psychometric tests such as the WISC-IV have been utilized to gather evidence and identify patterns or factors contributing to ADHD diagnosis. However, in recent years, the use of machine learning (ML) models in conjunction with post-hoc eXplainable Artificial Intelligence (XAI) techniques has improved our ability to make precise predictions and provide transparent explanations. The objective of this study is twofold: firstly, to predict the likelihood of an individual receiving an ADHD diagnosis using ML algorithms, and secondly, to offer interpretable insights into the decision-making process of the ML model. The dataset under scrutiny comprises 694 cases collected over the past decade in Spain, including information on age, gender, and WISC-IV test scores. The outcome variable is the professional diagnosis. Diverse ML algorithms representing various learning styles were rigorously evaluated through a stratified 10-fold cross-validation, with performance assessed using key metrics, including accuracy, area under the receiver operating characteristic curve, sensitivity, and specificity. Models were compared using both the full set of initial features and a well-suited wrapper-type feature selection algorithm (Boruta). Following the identification of the most suitable model, Shapley additive values were computed to assign weights to each predictor based on their additive contribution to the outcome and to elucidate the predictions. Strikingly, a reduced set of 8 out of the initial 20 variables produced results comparable to using the full feature set. Among the ML models tested, the Random Forest algorithm outperformed others on most metrics (ACC = 0.90, AUC = 0.94, Sensitivity = 0.91, Specificity = 0.92). Notably, the principal predictors, ranked by importance, included GAI - CPI, WMI, CPI, PSI, VCI, WMI - PSI, PRI, and LN. Individual case examples exhibit variations in predictions depending on unique characteristics, including instances of false positives and negatives. Our ML model adeptly predicted ADHD diagnoses in 90% of cases, with potential for further enhancement by expanding our database. Furthermore, the use of XAI techniques enables the elucidation of salient factors in individual cases, thereby aiding inexperienced professionals in the diagnostic process and facilitating comparison with expert assessments. It is important to note that this tool is designed to support the ADHD diagnostic process, where the medical professional always has the final say in decision-making.

Determining cutoff scores on the Conners' adult ADHD rating scales that can definitively rule out the presence of ADHD in a clinical sample

In recent years, the prevalence of Attention Deficit/Hyperactivity Disorder (ADHD) and the number of individuals seeking ADHD assessments has risen significantly, leading to an increased demand for accurate diagnostic tools. This study aimed to identify cutoff scores on the Conners' Adult ADHD Rating Scales (CAARS-S:L) that can definitively rule out the presence of ADHD. Among 102 clinically diagnosed adult ADHD participants and 448 non-ADHD participants who completed the CAARS-S:L, a receiver operating characteristic curve analysis established a perfectly discriminant cutoff T-score of <44 on the ADHD Symptoms Total subscale when looking at any ADHD diagnosis and <54 on the Inattentive Symptoms subscale when looking at individuals diagnosed with the inattentive subtype of ADHD. Alternative cutoffs of <54 (ADHD Symptoms Total subscale) and <63 (Inattentive Symptoms subscale) were also identified, both with a sensitivity of 0.95 or higher. Furthermore, the analysis found the ADHD Index to be a poor predictor of a negative ADHD diagnosis, suggesting against the use of this scale for cutoff determination. Despite this limitation, these findings indicate that with specific cutoffs, the CAARS-S:L may have the potential to conclusively rule out ADHD, effectively streamlining the diagnostic process and reducing unnecessary comprehensive assessments in clear negative cases.

ADHD-AID: Aiding Tool for Detecting Children's Attention Deficit Hyperactivity Disorder via EEG-Based Multi-Resolution Analysis and Feature Selection

The severe effects of attention deficit hyperactivity disorder (ADHD) among adolescents can be prevented by timely identification and prompt therapeutic intervention. Traditional diagnostic techniques are complicated and time-consuming because they are subjective-based assessments. Machine learning (ML) techniques can automate this process and prevent the limitations of manual evaluation. However, most of the ML-based models extract few features from a single domain. Furthermore, most ML-based studies have not examined the most effective electrode placement on the skull, which affects the identification process, while others have not employed feature selection approaches to reduce the feature space dimension and consequently the complexity of the training models. This study presents an ML-based tool for automatically identifying ADHD entitled "ADHD-AID". The present study uses several multi-resolution analysis techniques including variational mode decomposition, discrete wavelet transform, and empirical wavelet decomposition. ADHD-AID extracts thirty features from the time and time-frequency domains to identify ADHD, including nonlinear features, band-power features, entropy-based features, and statistical features. The present study also looks at the best EEG electrode placement for detecting ADHD. Additionally, it looks into the location combinations that have the most significant impact on identification accuracy. Additionally, it uses a variety of feature selection methods to choose those features that have the greatest influence on the diagnosis of ADHD, reducing the classification's complexity and training time. The results show that ADHD-AID has provided scores for accuracy, sensitivity, specificity, F1-score, and Mathew correlation coefficients of 0.991, 0.989, 0.992, 0.989, and 0.982, respectively, in identifying ADHD with 10-fold cross-validation. Also, the area under the curve has reached 0.9958. ADHD-AID's results are significantly higher than those of all earlier studies for the detection of ADHD in adolescents. These notable and trustworthy findings support the use of such an automated tool as a means of assistance for doctors in the prompt identification of ADHD in youngsters.

Review of Studies on Incremental Validity of Assessment Measures Used in Psychological Assessment of Attention-Deficit Hyperactivity Disorder

Few studies have summarized the literature relevant to the incremental validity of tools and procedures for the assessment of attention-deficit hyperactivity disorder (ADHD). The current project reviewed such studies published in the prior 18 years. Results from studies on the incremental validity of measures used in the assessment of ADHD were reviewed. Measures included symptom reports, clinical interviews, behavioral observation, continuous performance and other psychomotor tasks, intelligence tests, and measures of executive function. Twenty-nine published studies and two reviews were identified from 2004 to 2022. Incremental validity was determined using various statistics including R2, classification metrics, odds ratios, and post-test probabilities. Findings suggest that symptom reports from a collateral source and continuous performance test measures have incremental validity over self-reports and clinical interviews. Measures of intellectual and executive functioning did not show incremental validity in the diagnosis of ADHD. Findings are relevant to the practitioner, as they bear on the optimization of both the cost-effectiveness and the diagnostic accuracy of combined procedures in the assessment of ADHD.

ADHD Adults Show Lower Interindividual Similarity in Ex-Gaussian Reaction Time Vectors for Congruent Stimuli Compared to Control Peers

OBJECTIVE

Interindividual similarity refers to how similarly individuals respond when receiving the same stimulus or intervention. In this study, we aimed to examine interindividual similarity in adults with ADHD.

METHOD

We used the cosine similarity index of ex-Gaussian reaction time (RT) vectors of mu, sigma, and tau parameters during a Stroop task.

RESULTS

Our results demonstrate that the ADHD group exhibits a reduced interindividual similarity index in their ex-Gaussian RT vectors for congruent stimuli compared to the healthy control group. Importantly, we did not find significant differences in the interindividual similarity index to incongruent stimuli between both groups, thus suggesting that this reduced index was selective for congruent stimuli.

CONCLUSION

Our findings highlight that ADHD adults exhibit more significant interindividual differences in cognitive functioning when processing congruent stimuli than healthy controls. These results provide new insights into the selective mechanisms underlying ADHD and may contribute to developing new targeted interventions for this disorder.

Reducing Risk in the Treatment of Attention-Deficit/Hyperactivity Disorder Among Adults With Comorbidities

Recent widely publicized shortages in the U.S. supply of first-line medications for treatment of attention-deficit/hyperactivity disorder (ADHD) are thought to reflect increases in public awareness, help seeking, and treatment. ADHD is one of the most common neurodevelopmental disorders and is typically identified in childhood. In adulthood, ADHD symptoms are less likely to include hyperactivity, but inattention, impulsivity, and emotional dysregulation are common. Clinical evaluation of symptomatic adults who were not diagnosed as children requires corroboration of ADHD diagnostic symptoms in childhood and careful differentiation of ADHD from frequently co-occurring psychiatric and substance use disorders. Treatment of adult ADHD can result in improved functioning across multiple dimensions and comorbid disorders. Existing guidelines and consensus statements recommend an integrated approach to treating ADHD and all existing comorbid disorders, prioritizing the disorder that is creating the most difficulty for the individual. [Journal of Psychosocial Nursing and Mental Health Services, 62(1), 8-11.].

The Ability of Self-Report Methods to Accurately Diagnose Attention Deficit Hyperactivity Disorder: A Systematic Review

OBJECTIVE

To identify and analyze all studies validating rating scales or interview-based screeners commonly used to evaluate ADHD in adults.

METHOD

A systematic literature search identified all studies providing diagnostic accuracy statistics, including sensitivity and specificity, supplemented by relevant articles or test manuals referenced in reviewed manuscripts.

RESULTS

Only 20 published studies or manuals provided data regarding sensitivity and specificity when tasked with differentiating those with and without ADHD. While all screening measures have excellent ability to correctly classify non-ADHD individuals (with negative predictive values exceeding 96%), false positive rates were high. At best, positive predictive values in clinical samples reached 61%, but most fell below 20%.

CONCLUSION

Clinicians cannot rely on scales alone to diagnose ADHD and must undertake more rigorous evaluation of clients who screen positive. Furthermore, relevant classification statistics must be included in publications to help clinicians make statistically defensible decisions. Otherwise, clinicians risk inappropriately diagnosing ADHD.

College students who believe they have ADHD report more neuropsychological deficits than non-ADHD peers

Objective: Attention-deficit/hyperactivity disorder (ADHD) diagnosis in college students has been associated with poor academic outcomes and greater neuropsychological and emotional difficulties. The present study sought to determine whether college students who believe they have ADHD report more neuropsychological deficits than non-ADHD peers. Method: College students (N = 1,520) completed a confidential online survey designed to explore ADHD beliefs and subjective neuropsychological impairment. MANOVA was used to examine the association between ADHD beliefs and neuropsychological symptoms. LSD post hoc analysis was used to examine pairwise comparisons across groups. Results: College students who believe they have ADHD reported more neuropsychological deficits than those without ADHD and similar levels of neuropsychological impairment as peers with a self-reported diagnosis of ADHD. Conclusion: Results show a statistically and clinically significant relationship between ADHD belief and neuropsychological impairment among college students. These findings highlight the need for qualified ADHD assessment in college students who believe they have ADHD.

Effects of Near-Infrared Pulsed Light on the Attention of Human Beings Using Electroencephalography

In our previous studies, photobiomodulation (PBM) stimulation can induce significant brain activation in normal subjects. In an open-eye study, the PBM stimulation was able to increase the power of alpha rhythms and theta waves, as well as decrease the beta activities after PBM stimulation. However, in the closed eyes study, the alpha rhythms in the laser group were reduced. This means the PBM stimulation can induce specific brainwaves under different conditions. Thus, to investigate the effects of PBM stimulation on human's attention, forty students were recruited in this single-blind randomized trial. A PBM stimulator, with seven pcs laser diodes (LDs), frequency 10 Hz, 30 mW/each LD, and wavelength 830 nm, was used to radiate the palm of the subject. PBM stimulation was found to induce significant variation in beta activity in most of the regions of the brain in the laser group. Compared to the placebo group, the PBM stimulation has a significant change in beta activity on electroencephalography (EEG). Three types of tests, the random number test, the Stroop color-word test, and the Multiple-Dimension Attention Test (MDAT), were used to evaluate the effects of the PBM stimulation. The scores of MDAT in the laser group increased more significantly than those in the placebo group after PBM stimulation (p < 0.01). An improvement in attention was observed in this study.

Short form Conners' Adult ADHD Rating Scales: Factor structure and measurement invariance by sex in emerging adults

INTRODUCTION

The short version of the Conners' Adult ADHD Rating Scales (CAARS-S:S) is a self-report measure used to identify symptoms of Attention Deficit/Hyperactivity Disorder (ADHD) during adulthood. However, its psychometric properties specifically in emerging adults, or the transitional age group between adolescence and adulthood, remain understudied. This study aimed to validate the factor structure of the CAARS-S:S in a sample of emerging adults.

METHOD

The CAARS-S:S measure was completed by adults (n = 591) aged 18 to 29 located in English-speaking countries, including Australia, Canada and the United States. Confirmatory factor analysis was used to test a four-factor model of Inattention/Memory Problems, Hyperactivity/Restlessness, Impulsivity/Emotional Lability and Problems with Self-Concept, as well as the model's invariance by sex. Sex was also included as a covariate in the model to examine differences in males' and females' scores on each factor.

RESULTS

Overall, the four-factor structure fit the data and was invariant across males and females. All factors demonstrated high internal reliability (average ωt and α = .86). It was observed that males tended to score higher on Inattention/Memory Problems while females scored higher on Problems with Self-Concept.

CONCLUSION

This research establishes the psychometric properties of the CAARS-S:S, placing greater confidence in using it to screen for ADHD symptoms in emerging adults living in a Westernized cultural context. The detailed findings of this research, implications for the use of the CAARS-S:S in this age group and potential future directions for examining the properties of the measure are discussed.

The parent-reported ADHD symptom infrequency scale (PRASIS): a parent report measure of ADHD symptom exaggeration

The present article outlines the development of the parent-reported ADHD symptom infrequency scale (PRASIS), a novel stand-alone questionnaire designed to discriminate between parents exaggerating ratings of ADHD symptoms of their child from parents more accurately reporting symptoms. The PRASIS includes an Infrequency scale (INF) to measure infrequently reported symptoms of ADHD and a clinical scale to measure Diagnostic and Statistical Manual of Mental Disorders-5^th Edition (DSM-5) defined ADHD symptoms (ADHD Total). An initial list of infrequency and clinical items was revised over the course of three studies, each conducted on a different sample of participants (n₁ = 154, n₂ = 203, n₃ = 167) recruited via CloudResearch and consisting of mothers of children 4-12 years old. Analyses on the final version of the measure demonstrated good to excellent internal consistency (INF α = .87 , ADHD Total α = .94) and high convergent validity of the PRASIS ADHD Total scores with ADHD Rating Scale-5 Total scores (r = .87, p < .001). Omnibus ANOVA comparisons demonstrated excellent group discrimination of both the PRASIS Infrequency scale and the PRASIS ADHD scale (Cohen's f = 0.81-0-90). Specificity was above the minimum requirement set a priori (≥.80) and resulting sensitivity was similar or higher than other non-ADHD measures in the symptom validity literature. Specificity and sensitivity are reported for multiple cutoff scores, and positive predictive values (PPV) and negative predictive values (NPV) are presented for several base rates.

The Effect of Spatial Uncertainty on Visual Search in Older School-Aged Children with and without ADHD

OBJECTIVE

Numerous studies support that simple visual search tests may not be sufficient to differentiate children with and without attention-deficit/hyperactivity disorder (ADHD), especially for older school-aged children. This study aimed to explore whether the high spatial uncertainty visual search tasks can effectively discriminate older school-aged children with ADHD from their typically developing (TD) peers.

METHOD

In a randomized, two-period crossover design, 122 school-aged children (61 ADHD and 61 TD subjects), aged 10-12 years old, were measured using comparable visual search tasks with structured and unstructured layouts.

RESULTS

First, the discriminant effectiveness of unstructured visual search tasks, which are associated with high-level spatial uncertainty, is superior to structured ones. Second, combining accuracy and speed into a Q score is a more sensitive measure than accuracy or time calculated alone in visual search tasks. A more in-depth ROC analysis showed that all variables could accurately identify ADHD from their TD peers under unstructured visual search tasks, with the index of the Q score performing best (AUR = 0.956). Third, the development of detectability, which represents the ability to distinguish between target and non-target, is approaching maturity in 10-12-year-old children with ADHD. However, these children showed severe deficits in dealing with disorganized distractors when performing visual search tasks with high-level spatial uncertainty.

CONCLUSIONS

The findings of this study support that older school-aged children with ADHD demonstrate less efficient search performance than their TD peers in complex/difficult visual search tasks, especially under higher spatial uncertainty.

Validation of an adult ADHD measure of feigning in a sample including individuals with depression and anxiety symptoms

Few studies of measures or techniques designed to detect feigning of Attention-Deficit/Hyperactivity Disorder (ADHD) have included groups reporting symptoms of depression and anxiety. Based on the high rate of comorbidity between ADHD and mood disorders, inclusion of such groups is important to mimic clinical referral patterns. The current study evaluated the validity of the ADHD Symptom Infrequency Scale (ASIS), a measure designed to detect malingered symptoms of ADHD, in a four-known groups design that included a group consisting of subjects with symptoms of anxiety and depression. Four groups were included in the current study: (1) control, (2) simulator, (3) ADHD diagnosed, (4) individuals with elevated symptoms of depression/anxiety. The ASIS Infrequency scale showed strong internal consistency (α = .83). Discriminant validity for the Infrequency Scale was established through a low correlation between the ASIS scale assessing feigning and a measure of anxiety and depression (r = -.02). Sensitivity was high for detection of simulation (.71), while specificity was high across comparisons, ranging from .86 to .99. Results support the ASIS as a reliable and valid measure of ADHD that is sensitive to feigning, even when including a sample of individuals reporting symptoms of depression and anxiety.

Validating Embedded Validity Indicators of Feigned ADHD-Associated Cognitive Impairment Using the MOXO-d-CPT

BACKGROUND

The current study aimed to validate the utility of previously established validity indicators derived from MOXO-d-CPT's continuous performance test.

METHOD

Healthy simulators feigned impairment after searching online for relevant information, an ecologically valid coaching condition (n = 39). They were compared to ADHD patients (n = 36) and healthy controls (n = 38).

RESULTS

Simulators performed significantly worse than ADHD patients in all MOXO-d-CPT indices, as well as a scale that integrates their contributions (feigned ADHD scale). Three indices (attention, hyperactivity, and impulsivity) and the latter scale exhibited adequate discriminative capacity. Higher education was associated with an exaggerated impairment among simulators, easing their detection.

CONCLUSION

Similarity between the current study and a previous study which examned the utlity of the MOXO-d-CPT validity indicators, increases our confidence in the efficacy of the latters embedded validity indicators. Though the findings provide initial validation of these validity indicators, generalizing beyond highly functioning participants necessitates further research.

Stability of Attention Performance of Adults with ADHD over Time: Evidence from Repeated Neuropsychological Assessments in One-Month Intervals

Neuropsychological assessments of attention are valuable sources of information in the clinical evaluation of adults with attention-deficit/hyperactivity disorder (ADHD). However, it is unclear whether the attention performance of adults with ADHD is stable or fluctuates over time, which is of great importance in the interpretation of clinical assessments. This study aimed to explore the stability of attention performance of adults with ADHD in repeated assessments at one-month intervals. Twenty-one adults diagnosed with ADHD took part in this study by completing selective attention and vigilance tests three times, each one month apart. Test scores of participants were compared with and interpreted based on test norms. A considerable proportion of 'below average' performance scores were observed in most of the variables of selective attention and vigilance in all three assessments. Further, selective attention and vigilance performance scores did not differ significantly between the three repeated assessments. Finally, the majority of participants received consistent test score interpretations across the three repeated assessments. This study confirms previous research and highlights abnormal selective attention and vigilance performance in adults with ADHD. Further, this study preliminarily demonstrates relatively stable attention performance across repeated assessments, which has the potential to support clinical assessment, treatment planning, and evaluation.

Online search strategies utilized in feigning attention deficit/hyperactivity disorder (ADHD) while performing a continuous performance test (CPT)

BACKGROUND

The availability of information regarding neuropsychological tests threatens their confidentiality. This concern may be particularly relevant to Attention-Deficit/Hyperactivity Disorder (ADHD) considering its widespread online coverage. The present study explored simulators' online search strategies.

METHOD

Simulators (n = 39) searched for information before undergoing an evaluation which included performing a continuous performance test (CPT). Their search strategies were analyzed, and their performance was compared to that of ADHD patients (n = 36) and healthy controls (n = 38).

RESULTS

Most simulators reached high-risk websites that provided written and video-based information regarding the test. Sixty percent, comprised mostly of 3rd-year students, reached Google Scholar. These students were also easier to detect as simulators. Common strategies included performing the CPT in accordance with typical ADHD symptoms and avoiding the endorsement of both unusual and stereotypical symptoms.

CONCLUSION

Simulators can access online information that contains key test data. Higher education may increase the ability to reach academic research while decreasing the ability to convincingly feign impairment. While additional research is needed to examine coaching effects on neuropsychological testing, the risk to test security that many websites pose should be acknowledged and steps, including ones taken by test publishers, should be undertaken to minimize it.

Caring for adolescents and young adults with attention-deficit/hyperactivity disorder in primary care: seizing opportunities to address youth mental health needs

PURPOSE OF REVIEW

To provide primary care providers (PCPs) with updated practical guidance around the assessment and management of attention-deficit/hyperactivity disorder (ADHD) in adolescents and young adults (AYA).

RECENT FINDINGS

Of the three different presentations of ADHD delineated in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5), the Predominantly Inattentive presentation is the most common among AYA. Multiple rating scales exist to assist clinicians in identifying ADHD symptoms and monitoring treatment effects. Importantly, ADHD frequently persists into adulthood with negative impacts in many life domains if left untreated. It is important for PCPs to provide support for AYA as they transition to adulthood, as treatment adherence often drops sharply at that time, and, once treatment is discontinued, it is rarely restarted. Further, clinicians should be aware of the negative psychological, behavioral, and social impacts that COVID-19 has had on AYA with ADHD.

SUMMARY

AYA with ADHD often seek care first from PCPs. However, diagnosis and management of ADHD among AYA are challenging, and many clinicians feel ill-equipped, creating concern that many youth may go undiagnosed and untreated. Despite these long-standing challenges, recent advances have opened up critical opportunities for PCPs to proactively address ADHD in primary care settings and make a profound impact on youth as they seek to realize their full potential.

Assessing performance validity during attention-deficit/hyperactivity disorder evaluations: Cross-validation of non-memory embedded validity indicators

Embedded performance validity tests (PVTs) are key components of neuropsychological evaluations. However, most are memory-based and may be less useful in the assessment of attention-deficit/hyperactivity disorder (ADHD). Four non-memory-based validity indices derived from processing speed and executive functioning measures commonly included in ADHD evaluations, namely Verbal Fluency (VF) and the Trail Making Test (TMT), were cross-validated using the Rey 15-Item Test (RFIT) Recall and Recall/Recognition as memory-based comparison measures. This consecutive case series included data from 416 demographically-diverse adults who underwent outpatient neuropsychological evaluation for ADHD. Validity classifications were established, with ≤1 PVT failure of five independent criterion PVTs as indicative of valid performance (374 valid performers/42 invalid performers). Among the statistically significant validity indicators, TMT-A and TMT-B T-scores (AUCs = .707-.723) had acceptable classification accuracy ranges and sensitivities ranging from 29%-36% (≥89% specificity). RFIT Recall/Recognition produced similar results as TMT-B T-score with 42% sensitivity/90% specificity, but with lower classification accuracy. In evaluating adult ADHD, VF and TMT embedded PVTs demonstrated comparable sensitivity and specificity values to those found in other clinical populations but necessitated alternate cut-scores. Results also support use of RFIT Recall/Recognition over the standard RFIT Recall as a PVT for adult ADHD evaluations.

Feigned ADHD Associated Cognitive Impairment: Utility of Integrating an Eye-tracker and the MOXO-dCPT

OBJECTIVE

The current study assessed the utility of eye-movements measures, gathered while participants performed a commercially available Continuous Performance Test (CPT), to detect feigned ADHD-associated cognitive impairment.

METHOD

Healthy simulators (n = 37), ADHD patients (n = 33), and healthy controls (n = 36) performed an eye-tracker integrated MOXO-dCPT and a stand-alone validity indicator.

RESULTS

Simulators gazed significantly longer at regions that were irrelevant for successful MOXO-dCPT performance compared to ADHD patients and healthy controls. This eye-movement measure, however, had lower sensitivity than traditional MOXO-dCPT indices.

DISCUSSION

Gaze direction measures, gathered while performing a CPT, show initial promise as validity indicators. Traditional CPT measures, however, are more sensitive and therefore offer a more promising path for the establishment of CPT-based validity indicators. The current study is an initial exploration of the issue and further evaluation of both theoretical and practical aspects is mandated.

ADHD symptoms and use of anabolic androgenic steroids among male weightlifters

Use of anabolic androgenic steroids (AAS) is associated with adverse health effects. The factors that predispose to AAS use among athletes are poorly understood, but attention deficit/hyperactivity disorder (ADHD), which is known to occur among athletes more often than in the general population, is associated with risk behaviors, including substance abuse. We aimed to see if AAS use in male weightlifters was associated with ADHD symptoms, and test the link between ADHD symptoms and cognitive performance. Hundred and forty male weightlifters, 72 AAS users and 68 weightlifting controls (WLC), completed the Achenbach system of empirically based assessment (ASEBA) for ADHD symptoms and underwent cognitive examination. Self-reported ADHD symptom scores were significantly higher among AAS users compared to WLC, and scores in the range indicating clinically important ADHD was significantly more common in the AAS-using group. Age of onset of AAS use correlated inversely with ADHD scale score (r = - 0.35; p = 0.003). ADHD score correlated inversely with cognitive scores for working memory (r = - 0.25, p < 0.001), processing speed (r = - 0.24, p < 0.001), verbal learning and memory (r = - 0.19, p = 0.03), and problem solving (r = - 0.20, p = 0.02). AAS use among weightlifters is associated with ADHD symptoms and corresponding lower cognitive performance. Recognising a relationship between ADHD symptoms and AAS use may guide drug prevention strategies in sports.

Sparse representations of high dimensional neural data

Conventional Vector Autoregressive (VAR) modelling methods applied to high dimensional neural time series data result in noisy solutions that are dense or have a large number of spurious coefficients. This reduces the speed and accuracy of auxiliary computations downstream and inflates the time required to compute functional connectivity networks by a factor that is at least inversely proportional to the true network density. As these noisy solutions have distorted coefficients, thresholding them as per some criterion, statistical or otherwise, does not alleviate the problem. Thus obtaining a sparse representation of such data is important since it provides an efficient representation of the data and facilitates its further analysis. We propose a fast Sparse Vector Autoregressive Greedy Search (SVARGS) method that works well for high dimensional data, even when the number of time points is relatively low, by incorporating only statistically significant coefficients. In numerical experiments, our methods show high accuracy in recovering the true sparse model. The relative absence of spurious coefficients permits accurate, stable and fast evaluation of derived quantities such as power spectrum, coherence and Granger causality. Consequently, sparse functional connectivity networks can be computed, in a reasonable time, from data comprising tens of thousands of channels/voxels. This enables a much higher resolution analysis of functional connectivity patterns and community structures in such large networks than is possible using existing time series methods. We apply our method to EEG data where computed network measures and community structures are used to distinguish emotional states as well as to ADHD fMRI data where it is used to distinguish children with ADHD from typically developing children.

Eye Tracking During a Continuous Performance Test: Utility for Assessing ADHD Patients

OBJECTIVE

The use of continuous performance tests (CPTs) for assessing ADHD related cognitive impairment is ubiquitous. Novel psychophysiological measures may enhance the data that is derived from CPTs and thereby improve clinical decision-making regarding diagnosis and treatment. As part of the current study, we integrated an eye tracker with the MOXO-dCPT and assessed the utility of eye movement measures to differentiate ADHD patients and healthy controls.

METHOD

Adult ADHD patients and gender/age-matched healthy controls performed the MOXO-dCPT while their eye movements were monitored (n = 33 per group).

RESULTS

ADHD patients spent significantly more time gazing at irrelevant regions, both on the screen and outside of it, than healthy controls. The eye movement measures showed adequate ability to classify ADHD patients. Moreover, a scale that combined eye movement measures enhanced group prediction, compared to the sole use of conventional MOXO-dCPT indices.

CONCLUSIONS

Integrating an eye tracker with CPTs is a feasible way of enhancing diagnostic precision and shows initial promise for clarifying the cognitive profile of ADHD patients. Pending replication, these findings point toward a promising path for the evolution of existing CPTs.

Accommodation decision-making for postsecondary students with ADHD: Implications for neuropsychologists

Neuropsychologists are often asked to evaluate students for attention-deficit/hyperactivity disorder (ADHD) and to provide documentation to support their requests for academic accommodations in college. Research points to the importance of multi-method, multi-informant data when evaluating ADHD and determining the need for accommodations. However, the Association on Higher Education and Disability (AHEAD) directs disability service providers to give primacy to students' self-reports and their own impressions of students' narratives over objective, third-party data when rendering accommodation decisions. The organization asserts that in many cases information from parents, teachers, and psychologists is not needed to confirm the existence of a disability or students' need for accommodations. In this article, we describe the way disability service providers are directed to evaluate accommodation requests, the limitations of these procedures, and the dangers of well-intentioned, but indiscriminate accommodation-granting. We then provide recommendations for neuropsychologists who conduct ADHD evaluations for college students in light of these professional guidelines.

Diagnose ADHD disorder in children using convolutional neural network based on continuous mental task EEG

BACKGROUND AND OBJECTIVE

Attention-Deficit/Hyperactivity Disorder (ADHD) is a chronic behavioral disorder in children. Children with ADHD face many difficulties in maintaining their concentration and controlling their behaviors. Early diagnosis of this disorder is one of the most important challenges in its control and treatment. No definitive expert method has been found to detect this disorder early. Our goal in this study is to develop an assistive tool for physicians to recognize ADHD children from healthy children using electroencephalography (EEG) based on a continuous mental task.

METHODS

We used EEG signals recorded from 31 ADHD children and 30 healthy children. In this study, we developed a deep learning model using a convolutional neural network that have had significant performance in image processing fields. For this purpose, we first preprocessed EEG signals to eliminate noise and artifacts. Then we segmented preprocessed samples into more samples. We extracted the theta, alpha, beta, and gamma frequency bands from each segmented sample and formed a color RGB image with three channels. Eventually, we imported the resulting images into a 13-layer convolutional neural network for feature extraction and classification.

RESULTS

The proposed model was evaluated by 5-fold cross validation for train, evaluation, and test data and achieved an average accuracy of 99.06%, 97.81%, 97.47% for segmented samples. The average accuracy for subject-based test samples was 98.48%. Also, the performance of the model was evaluated using the confusion matrix with precision, recall, and f1-score metrics. The results of these metrics also confirmed the outstanding performance of the model.

CONCLUSIONS

The accuracy, precision, recall, and f1-score of our model were better than all previous works for diagnosing ADHD in children. Based on these prominent and reliable results, this technique can be used as an assistive tool for the physicians in the early diagnosis of ADHD in children.

Attention-Deficit/Hyperactivity Disorder (ADHD): Integrating the MOXO-dCPT with an Eye Tracker Enhances Diagnostic Precision

Clinical decision-making may be enhanced when combining psychophysiological sensors with computerized neuropsychological tests. The current study explored the utility of integrating an eye tracker with a commercially available continuous performance test (CPT), the MOXO-dCPT. As part of the study, the performance of adult attention-deficit/hyperactivity disorder (ADHD) patients and healthy controls (n = 43, n = 42, respectively) was compared in the integrated system. More specifically, the MOXO-dCPT has four stages, which differ in their combinations of ecological visual and auditory dynamic distractors. By exploring the participants' performance in each of the stages, we were able to show that: (a) ADHD patients spend significantly more time gazing at irrelevant areas of interest (AOIs) compared to healthy controls; (b) visual distractors are particularly effective in impacting ADHD patients' eye movements, suggesting their enhanced utility in diagnostic procedures; (c) combining gaze direction data and conventional CPT indices enhances group prediction, compared to the sole use of conventional indices. Overall, the findings indicate the utility of eye tracker-integrated CPTs and their enhanced diagnostic precision. They also suggest that the use of attention-grabbing visual distractors may be a promising path for the evolution of existing CPTs by shortening their duration and enhancing diagnostic precision.

Use of machine learning to classify adult ADHD and other conditions based on the Conners' Adult ADHD Rating Scales

A reliable diagnosis of adult Attention Deficit/Hyperactivity Disorder (ADHD) is challenging as many of the symptoms of ADHD resemble symptoms of other disorders. ADHD is associated with gambling disorder and obesity, showing overlaps of about 20% with each diagnosis. It is important for clinical practice to differentiate between conditions displaying similar symptoms via established diagnostic instruments. Applying the LightGBM algorithm in machine learning, we were able to differentiate subjects with ADHD, obesity, problematic gambling, and a control group using all 26 items of the Conners' Adult ADHD Rating Scales (CAARS-S: S) with a global accuracy of .80; precision (positive predictive value) ranged between .78 (gambling) and .92 (obesity), recall (sensitivity) between .58 for obesity and .87 for ADHD. Models with the best 5 and best 10 items resulted in less satisfactory fits. The CAARS-S seems to be a promising instrument to be applied in clinical practice also for multiclassifying disorders displaying symptoms resembling ADHD.

Comorbidity Matters: Social Visual Attention in a Comparative Study of Autism Spectrum Disorder, Attention-Deficit/Hyperactivity Disorder and Their Comorbidity

Autism Spectrum Disorder (ASD) and Attention-Deficit/Hyperactivity Disorder (ADHD) represent two common neurodevelopmental disorders with considerable co-occurrence. Their comorbidity (ASD + ADHD) has been included in the latest diagnostic guidelines (DSM-V, 2013). The present study focuses on social visual attention that i) is a main aspect of social attention reflecting social cognition and ii) its atypicalities have been suggested as a potential biomarker for ASD. Considering the possible shared background of both disorders and their comorbidity, it is important to compare such traits directly. Here, 73 children and adolescents paired for age and IQ diagnosed with ASD (N = 12), ADHD (N = 21), comorbid ASD + ADHD (N = 15), and "typically developing" (TD) controls (N = 25), were shown static real-life social scenes while their gaze movements were recorded with eye-tracking. Scenes with two levels of social complexity were presented: low complexity (one person depicted) and high (four interacting individuals). Gaze fixation variables were investigated. Fixation duration on faces was significantly reduced only in ASD + ADHD which also required longer time to fixate all faces at least once. Fixation duration on faces in ASD was reduced, compared to TD, only when looking at scenes with high versus low social complexity. ADHD individuals did not differ from TD. Concluding, the observed alterations of social visual attention support the existence of possible dysfunctional particularities differentiating ASD, ADHD, and ASD + ADHD, which can be revealed with the new method of eye-tracking technique. The objective gaze measurements provided contribute to the development of biomarkers enabling early diagnosis, amelioration of care and further interventions specified for each group.