scholarly journals Machine-learning-based diagnosis of drug-naive adult patients with attention-deficit hyperactivity disorder using mismatch negativity

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Sungkean Kim ◽  
Ji Hyun Baek ◽  
Young Joon Kwon ◽  
Hwa Young Lee ◽  
Jae Hyun Yoo ◽  
...  

AbstractRelatively little is investigated regarding the neurophysiology of adult attention-deficit/hyperactivity disorder (ADHD). Mismatch negativity (MMN) is an event-related potential component representing pre-attentive auditory processing, which is closely associated with cognitive status. We investigated MMN features as biomarkers to classify drug-naive adult patients with ADHD and healthy controls (HCs). Sensor-level features (amplitude and latency) and source-level features (source activation) of MMN were investigated and compared between the electroencephalograms of 34 patients with ADHD and 45 HCs using a passive auditory oddball paradigm. Correlations between MMN features and ADHD symptoms were analyzed. Finally, we applied machine learning to differentiate the two groups using sensor- and source-level features of MMN. Adult patients with ADHD showed significantly lower MMN amplitudes at the frontocentral electrodes and reduced MMN source activation in the frontal, temporal, and limbic lobes, which were closely associated with MMN generators and ADHD pathophysiology. Source activities were significantly correlated with ADHD symptoms. The best classification performance for adult ADHD patients and HCs showed an 81.01% accuracy, 82.35% sensitivity, and 80.00% specificity based on MMN source activity features. Our results suggest that abnormal MMN reflects the adult ADHD patients’ pathophysiological characteristics and might serve clinically as a neuromarker of adult ADHD.

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 976
Author(s):  
Sunhae Kim ◽  
Hyekyung Lee ◽  
Kounseok Lee

(1) Background: Adult attention-deficit/hyperactivity disorder (ADHD) symptoms cause various social difficulties due to attention deficit and impulsivity. In addition, in contrast to ADHD in childhood, ADHD in adulthood is difficult to diagnose due to mixed psychopathologies. This study aimed to determine whether it is possible to predict ADHD symptoms in adults using the Minnesota Multiphasic Personality Inventory-2 (MMPI-2) with machine learning (ML) techniques; (2) Methods: Data collected from 5726 college students were analyzed. The MMPI-2-Restructured Form (MMPI-2-RF) was used, and ADHD symptoms in adults were evaluated using the Attention-Deficit/Hyperactivity Disorder Self-Report Scale (ASRS). For statistical analysis, three ML algorithms were used, i.e., K-nearest neighbors (KNN), linear discriminant analysis (LDA), and random forest, with the ASRS evaluation result as the dependent variable and the 50 MMPI-2-RF scales as predictors; (3) Results: When the KNN, LDA, and random forest techniques were applied, the accuracy was 93.1%, 91.2%, and 93.6%, respectively, and the area under the curve (AUC) was 0.722, 0.806, and 0.790, respectively. The AUC of the LDA method was the largest, with an excellent level of diagnostic accuracy; (4) Conclusions: ML using the MMPI-2 in a large group could provide reliable accuracy in screening for adult ADHD.


2021 ◽  
pp. 1-11
Author(s):  
Ming H. Hsieh ◽  
Yi-Ling Chien ◽  
Susan Shur-Fen Gau

Abstract Background Individuals with attention-deficit hyperactivity disorder (ADHD) often display over-response to stimuli that are irrelevant to the ongoing task, and their attentional abilities disproportionately worsen in the presence of competing stimuli. Auditory event-related potentials (ERPs) such as mismatch negativity (MMN) and P3a using the passive oddball paradigm have been studied in children and adolescents with ADHD. Still, there is no such data for adults with ADHD. This study aimed to compare the MMN and P3a and their clinical and neurocognitive correlations between drug-naive adults with ADHD and control adults. Methods We recruited 52 adults with ADHD (26.5 ± 6.2 years), and 62 age-matched controls (25.6 ± 5.6 years). They received the psychiatric interviews, auditory ERP, the Conners' continuous performance test (CCPT), and the Cambridge gambling test (CGT). They also completed the questionnaires about ADHD symptoms and real-world executive functions. MMN and P3a were assessed during a passive duration-deviant auditory oddball paradigm from the midline electrodes Cz. Results Adults with ADHD demonstrated smaller Cz MMN amplitude, more severe ADHD symptoms, poorer attention profiles (CCPT), and a wide range of executive dysfunctions than controls. As for the correlates, Cz peak amplitude of MMN correlated with inattention symptoms, executive dysfunctions, attentional vigilance (CCPT), and decision-making (CGT) in ADHD adults but only with decision-making in controls. Conclusions Our findings that smaller amplitude of MMN and its differential associated pattern with inattention, real-world executive dysfunction, and decision-making, in drug-naive adults with ADHD from adult controls, provide evidence to support the potential electrophysiological biomarker for adult ADHD.


2015 ◽  
Vol 30 (S2) ◽  
pp. S27-S28
Author(s):  
B. Rolland ◽  
D. Da Fonseca ◽  
M. Fatseas ◽  
N. Simon

Attention-deficit/hyperactivity disorder (ADHD) was initially considered as a childhood psychiatric disorder. However, longitudinal observations have revealed that ADHD symptoms may persist in adulthood among approximately 50% of the patients . Adult ADHD is associated with impaired social outcome and frequent comorbidities such as mood disorders, personality disorders, and substance use disorders [2,3]. Correctly identifying and treating ADHD can significantly improve the global functioning and cognition of adult subjects, and reduce the intensity and frequency of the comorbid states [2,3]. Nonetheless, the clinical features of adult ADHD are clearly different from the youth form [1,2], and ADHD symptoms are easily mixed up in adults with symptoms of the comorbid conditions [2,3]. These clinical intricacies can make the diagnosis of ADHD difficult in adults. Moreover, the management of methylphenidate in adult subjects is also associated with specific risks and pitfalls, such as abuse and tampering behaviors, and additional safety risks . Put together, it appears crucial to identify and treat ADHD in adults, but the clinical and therapeutic complexities of adult ADHD require improved expertise and caution from adult psychiatrists and addiction specialists. In this thematic session of the 2015 French Psychiatry Congress, three French leading experts of adult ADHD will address the aforementioned clinical and therapeutic issues of the adulthood form of this disorder. David Da Fonseca, professor of child psychiatry in Marseille, will disentangle the clinical features of adult ADHD from the typical symptoms observed in the youth form. Mélina FATSEAS, associate professor of psychiatry and addiction medicine in Bordeaux, will specifically focus on the many and complex relationships observed between adult ADHD and substance use disorders. Last, Nicolas Simon, professor of addiction medicine and psychopharmacology in Marseille, will synthesize what are the very risks and issues with prescribing methylphenidate in adults.


2017 ◽  
Vol 41 (S1) ◽  
pp. S396-S397
Author(s):  
B. Tuzun Mutluer ◽  
T.G. Yener Orum ◽  
S. Sertcelik

ObjectiveIn this study, it was aimed to determine the internet use properties of Adult Attention Deficit Hyperactivity Disorder (ADHD) patients who were followed-up at Haydarpasa Numune Research and Training Hospital, Psychiatry Department; ADHD Outpatient Clinic.MethodThirty participants who were diagnosed with adult ADHD aged between 18–31 years rated their ADHD symptoms in childhood retrospectively, using Wender Utah Rating Scale. Patients rated current adult ADHD symptoms with the Adult ADHD DSM-IV-Based Diagnostic Screening and Rating Scale (DSRS) and severity of symptoms measured by Adult ADHD Self-Report Scale (ASRS). Internet addiction (IA) was assessed with Young's Internet Addiction Scale (IAS). It was determined that, none of 30 Adult ADHD patients have been diagnosed with IA.29 of patient have moderate internet use although 1 of patients have risky internet use. The results revealed that total ASRS score (P = 0.020), total Adult ADHD DSM-IV-Based DSRS score (P = 0.036) and the Attention Deficit related properties subscale total score (P = 0.042) were significantly correlated with the IAS total score. Subscale of the self-report scales including; failing to finish schoolworks, chores, or duties at workplace, difficulty of following through on instructions (P = 0.017), restiveness; impaired inhibitory performance (P = 0.017), feeling not confident (P = 0.017), difficulty of managing time (P = 0.047), failing to give close attention to details or making careless mistakes (P = 0.037) are closely relevant to IAS total score.ResultIn conclusion, clinical features, which are characteristic of Adult ADHD could have same shared etiology with IA. Furthermore, ADHD patients are more likely to have an IA diagnosis. However, it was thought that this result had to be supported with studies including larger samples.Disclosure of interestThe authors have not supplied their declaration of competing interest.


Author(s):  
Cuneyt Evren ◽  
Elvan Cicekci ◽  
Gokhan Umut ◽  
Bilge Evren ◽  
Kubra Durmus Cicek

Objective: The first objective of this research was to examine the association of the symptom severity of social anxiety with the adult attention deficit hyperactivity disorder (ADHD) symptom severity in Turkish patients with alcohol use disorder (AUD). The second objective was to examine if harm avoidance and self-esteem mediated this relationship. Method: This cross-sectional analysis was performed among 151 inpatients with AUD at the Bakirkoy/AMATEM, a treatment center for substance use disorder, in Istanbul. Patients were examined with the Liebowitz Social Anxiety Scale (LSAS), the Adult ADHD Self-Report Scale (ASRS), the Rosenberg Self-Esteem Scale (SES), and the temperament dimension of Harm Avoidance (HA). Using SPSS-20 software, the data was analyzed using Pearson correlations, multivariate analysis of covariance (MANCOVA), and multiple linear regressions. Results: The scales scores were mildly correlated with each other. The low self-esteem and high HA were related with the inattentive (IN) dimension of ADHD, whereas low self-esteem solely predicted hyperactivity/impulsivity (HI) dimension of ADHD in MANCOVA. In the linear regression analysis, the severity of social anxiety, particularly avoidance dimension, was associated with the symptom severity of ADHD. In the second step of the analysis, together with the avoidance dimension of social anxiety, self-esteem was associated with the symptom severity of ADHD. However, in the third step, after including HA as an independent variable in the analysis, the avoidance dimension of social anxiety was no longer associated with the severity of adult ADHD symptoms, whereas self-esteem together with HA (particularly “anticipatory worry and pessimism” [HA-1], and “asthenia and fatigability” [HA-4]) predicted. Conclusion: Findings of the present study shows that although the symptom severity of social anxiety is associated with the severity of ADHD symptoms among inpatients with AUD, among dimensions of social anxiety, the avoidance dimension plays a main role in this relationship. Also, while the self-esteem partially mediates this relationship, HA seems to have a full mediator effect on this relationship.


2020 ◽  
Vol 17 (2) ◽  
Author(s):  
Woon LS ◽  
Hazli Z ◽  
Gan LLY

Comorbid adult attention-deficit hyperactivity disorder (ADHD) and stimulant dependence is widely recognized, but efficacy of pharmacotherapy in this patient population is not well established. We aimed to review whether pharmacotherapy is efficacious in reducing ADHD symptoms and stimulant use in comorbid adult ADHD and stimulant use disorder. English articles until June 2017 were systematically searched in electronic databases (MEDLINE and PsycINFO), an online clinical trials register (ClinicalTrial.gov), and through hand-search of article references. Randomized, double-blind, placebo-controlled trials that studied efficacy of pharmacotherapy in adults with comorbid ADHD and stimulant dependence were included. Two reviewers assessed studies for inclusion and extracted data; disagreements were resolved by consensus. Study outcomes included were changes in ADHD symptom severity, substance abstinence, treatment retention rates and safety. From the 1394 records identified, five trials (n=358) were included. Four studies involved methylphenidate; in another study extended-release mixed amphetamine were used. The comorbid stimulant was cocaine in three studies, and amphetamines in the rest. All were short-term studies involving predominantly young male adults conducted in outpatient settings. There is early promising but mixed evidence for therapeutic efficacy in improving ADHD symptoms. Stimulant medications did not worsen stimulant dependence or adverse effects of stimulant medications. Side effects were mild and tolerable. High attrition rates and small sample size limited the generalizability of findings. Current limited evidence suggests that stimulant treatment for comorbid adult ADHD and stimulant dependence is feasible. Welldesigned trials with adequate power are needed for more robust evidence on ADHD and stimulant use outcomes.


CNS Spectrums ◽  
2008 ◽  
Vol 13 (11) ◽  
pp. 977-984 ◽  
Author(s):  
Russell A. Barkley ◽  
Thomas E. Brown

ABSTRACTMany adults with a diagnosed psychiatric disorder also have attention-deficit/hyperactivity disorder (ADHD). In many cases, comorbid ADHD is unrecognized and/or undertreated. Differential diagnosis of adult ADHD can be challenging because ADHD symptoms may overlap with other psychiatric disorders and patients may lack insight into their ADHD-related symptoms. Current ADHD diagnostic criteria in the Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition-Text Revision may prevent appropriate diagnosis of many patients with significant ADHD symptoms. Adults may not be able to provide a history of onset of symptoms during childhood, and it may be difficult to confirm that ADHD symptoms are not better accounted for by other comorbid psychiatric conditions. Comorbid ADHD is most prevalent among patients with mood, anxiety, substance use, and impulse-control disorders. ADHD can negatively affect outcomes of other comorbid psychiatric disorders, and ADHD symptoms may compromise compliance with treatment regimens. Furthermore, unrecognized ADHD symptoms may be mistaken for poor treatment response in these comorbid disorders. In these individuals, ADHD pharmacotherapy seems to be as effective in reducing core ADHD symptoms, as it is in patients who have no comorbidity. Limited evidence further suggests that ADHD therapy may help to improve symptoms of certain psychiatric comorbidities, such as depression. Therefore, management of ADHD may help to stabilize daily functioning and facilitate a fuller recovery.


2017 ◽  
Vol 36 (6) ◽  
pp. 552-561 ◽  
Author(s):  
Carolyn Cook ◽  
Melissa T. Buelow ◽  
Esther Lee ◽  
Ashley Howell ◽  
Brittni Morgan ◽  
...  

Malingering is a significant assessment concern in adults undergoing evaluations for attention deficit/hyperactivity disorder (ADHD) and may occur for a number of reasons, including access to medication and/or accommodations. Therefore, it is important to investigate ways to determine accuracy of self-reported ADHD symptoms. The present study used a simulation design to examine the impact of reasons for malingering on the Conners’ Adult ADHD Rating Scales (CAARS) Symptom subscales and the CAARS infrequency index (CII). Participants ( N = 157) were randomly assigned to one of three conditions: best effort, malingering for stimulant medication, or malingering for extra time accommodations. The three groups were compared with 34 individuals reporting previous diagnosis of ADHD. Results showed that individuals in both malingering groups scored higher than controls on all CAARS subscales and CII. Individuals in the medication malingering group, but not the extra time malingering group, scored higher than the ADHD group on CII and several CAARS subscales whose content overtly reflects ADHD symptomatology. Findings emphasize the influence of malingering on self-reported ADHD symptoms and the need to assess for malingering in ADHD evaluation. Results also suggest that reason for malingering might differentially affect self-report of ADHD symptoms.


2018 ◽  
Vol 52 ◽  
pp. 38-44 ◽  
Author(s):  
Erich Studerus ◽  
Salvatore Corbisiero ◽  
Nadine Mazzariello ◽  
Sarah Ittig ◽  
Letizia Leanza ◽  
...  

AbstractBackground:Patients with an at-risk mental state (ARMS) for psychosis and patients with attention-deficit/hyperactivity disorder (ADHD) have many overlapping signs and symptoms and hence can be difficult to differentiate clinically. The aim of this study was to investigate whether the differential diagnosis between ARMS and adult ADHD could be improved by neuropsychological testing.Methods:168 ARMS patients, 123 adult ADHD patients and 109 healthy controls (HC) were recruited via specialized clinics of the University of Basel Psychiatric Hospital. Sustained attention and impulsivity were tested with the Continuous Performance Test, verbal learning and memory with the California Verbal Learning Test, and problem solving abilities with the Tower of Hanoi Task. Group differences in neuropsychological performance were analyzed using generalized linear models. Furthermore, to investigate whether adult ADHD and ARMS can be correctly classified based on the pattern of cognitive deficits, machine learning (i.e. random forests) was applied.Results:Compared to HC, both patient groups showed deficits in attention and impulsivity and verbal learning and memory. However, in adult ADHD patients the deficits were comparatively larger. Accordingly, a machine learning model predicted group membership based on the individual neurocognitive performance profile with good accuracy (AUC = 0.82).Conclusions:Our results are in line with current meta-analyses reporting that impairments in the domains of attention and verbal learning are of medium effect size in adult ADHD and of small effect size in ARMS patients and suggest that measures of these domains can be exploited to improve the differential diagnosis between adult ADHD and ARMS patients.


1999 ◽  
Vol 5 (2) ◽  
pp. 112-119 ◽  
Author(s):  
Brian Toone ◽  
Maria Clarke ◽  
Susan Young

Attention-deficit hyperactivity disorder (ADHD) and hyperkinetic disorder are well-established diagnoses in children, with estimates of prevalence in pre-adolescent children from 3 to 5%. Until recently ADHD was not thought to persist beyond adolescence, but results from long-term prospective outcome studies indicate that 30–70% of children with ADHD exhibit some symptoms as adults. Recognition of this disorder is important as the persistence of ADHD symptoms has been shown to be associated with academic and occupational failure and high rates of psychiatric comorbidity. With the establishment of a UK support group (LADDER) and increasing media attention highlighting this problem it is likely that there will be an increased demand for psychiatric assessment of adult ADHD in the next few years.


Sign in / Sign up

Export Citation Format

Share Document