Development of an innovative approach using portable eye tracking to assist ADHD screening: a machine learning study.

Introduction: Attention-deficit/hyperactivity disorder (ADHD) affects a significant proportion of the pediatric population, making early detection crucial for effective intervention. Eye movements are controlled by brain regions associated with neuropsychological functions, such as selective attention, response inhibition, and working memory, and their deficits are related to the core characteristics of ADHD. Herein, we aimed to develop a screening model for ADHD using machine learning (ML) and eye-tracking features from tasks that reflect neuropsychological deficits in ADHD. Methods: Fifty-six children (mean age 8.38 ± 1.58, 45 males) diagnosed with ADHD based on the Diagnostic and Statistical Manual of Mental Disorders, fifth edition were recruited along with seventy-nine typically developing children (TDC) (mean age 8.80 ± 1.82, 33 males). Eye-tracking data were collected using a digital device during the performance of five behavioral tasks measuring selective attention, working memory, and response inhibition (pro-saccade task, anti-saccade task, memory-guided saccade task, change detection task, and Stroop task). ML was employed to select relevant eye-tracking features for ADHD, and to subsequently construct an optimal model classifying ADHD from TDC. Results: We identified 33 eye-tracking features in the five tasks with the potential to distinguish children with ADHD from TDC. Participants with ADHD showed increased saccade latency and degree, and shorter fixation time in eye-tracking tasks. A soft voting model integrating extra tree and random forest classifiers demonstrated high accuracy (76.3%) at identifying ADHD using eye-tracking features alone. A comparison of the model using only eye-tracking features with models using the Advanced Test of Attention or Stroop test showed no significant difference in the area under the curve (AUC) (p = 0.419 and p=0.235, respectively). Combining demographic, behavioral, and clinical data with eye-tracking features improved accuracy, but did not significantly alter the AUC (p=0.208). Discussion: Our study suggests that eye-tracking features hold promise as ADHD screening tools, even when obtained using a simple digital device. The current findings emphasize that eye-tracking features could be reliable indicators of impaired neurobiological functioning in individuals with ADHD. To enhance utility as a screening tool, future research should be conducted with a larger sample of participants with a more balanced gender ratio.

Depression and posttraumatic stress disorder in adolescents with nonsuicidal self-injury: comparisons of the psychological correlates and suicidal presentations across diagnostic subgroups.

BACKGROUND: Nonsuicidal self-injury (NSSI) combined with suicide ideation increases the risk of suicidal behaviors. Depression and posttraumatic stress disorder (PTSD) are comorbidities of NSSI compounding this relationship. The present study compared diagnostic subgroups of NSSI based on current depression and PTSD on psychological correlates (i.e., vulnerabilities and impairment) and suicidal presentations (i.e., suicidal cognitions and behaviors) in a psychiatric sample of adolescents. METHODS: Eighty-seven adolescents meeting DSM-5 criteria for NSSI and 104 age-range-matched nonclinical controls (NC) participated. Participants completed self-report measures on psychological vulnerabilities and impairment (e.g., emotion regulation difficulties, negative cognitions). Adolescents with NSSI also completed clinical interviews on psychiatric diagnoses and a recent self-injurious behavior (SIB). Scores on the psychological correlates of NSSI were compared between adolescents with NSSI and NC, and across three diagnostic subgroups of NSSI (A: NSSI+/depression-/PTSD-, n = 14; B: NSSI+/depression+/PTSD-, n = 57; C: NSSI+/depression+/PTSD+, n = 14). Differences between NSSI diagnostic subgroups were tested on the motives for SIB and accompanying suicidal presentations (e.g., desire, intent, motive, lethality). RESULTS: Common comorbidities of NSSI included depression, panic disorder, generalized anxiety disorder, and PTSD. The NSSI subgroup classification was significantly associated with panic disorder, which was controlled for in the subsequent group comparisons. Overall, adolescents who engage in NSSI with vs. without depression reported more psychological vulnerabilities and impairment and a greater degree of suicidal thoughts/desire in SIB (i.e., groups B, C >A), which remained significant after controlling for panic disorder. An increased odds of the suicidal motive for SIB was found in adolescents with all three conditions (i.e., group C: NSSI+/depression+/PTSD+) compared to those with NSSI but neither depression nor PTSD (i.e., group A: NSSI+/depression-/PTSD-); however, this was not significant after controlling for panic disorder. CONCLUSIONS: Psychological underpinnings of adolescent NSSI in clinical contexts may be largely associated with concurrent depression. Suicidal motives in adolescents who engage in NSSI in the presence of depression and PTSD may be confounded by the co-occurrence of panic disorder. This study warrants the importance of attending to the comorbid depression with NSSI in adolescents as it is related to an increase in suicidal desire accompanying SIB.

Causing trouble and being transmissible: COVID-19 survivors' experiences of stigma and discrimination in South Korea.

Background: The stigma associated with coronavirus disease (COVID-19) is relatively neglected in policies for handling the disease. Stigmatization occurs only within specific social contexts in local societies. Objective: This study aims to examine COVID-19 survivors' experiences of social stigma and discrimination in South Korea in the first 2 years of the pandemic. Methods: Semi-structured interviews were conducted. Results: Of 52 participants, 45 reported that they had to cope with stigma and discrimination in their intimate social relationships, workplaces, and children's schools, ranging from subtle actions to job loss. Sexual minorities who were involved in mass disease transmission in the early part of the pandemic experienced a higher level of stigmatization. The stigmatization dealt with in this study was related to two themes: survivors' sense of causing trouble and possibility of transmission. Conclusion: By intertwining this stigma with the experiences of public health measures through the voices of survivors, this study reveals the local context of East Asia in terms of culture-specific aspects of COVID-19-related stigma.

Harm avoidance, daily stress, and problematic smartphone use in children and adolescents.

Objective: Temperament is close to susceptibility to stress and the increased level of stress may lead problematic smartphone use (PSU). In this study, the relationships between harm avoidance (HA) as a personality trait, daily traits, and PSU in children and adolescents were investigated. Methods: At baseline, all participants (184 children and adolescents, mean age 13.15 years) completed questionnaires on PSU using the Smartphone Addiction Scale-Short Version (SAS-SV) and the Korean Smartphone Addiction Proneness Scale (SAPS). The Daily Hassles Questionnaire (DHQ) and Junior Temperament and Character Inventory (JTCI) were also administered to evaluate stress levels and personality traits. SAS-SV, SAPS, and DHQ were reassessed at 3 and 6 months. Results: Among JTCI temperament, HA displayed robust positive correlations with SAS-SV, SAPS, and DHQ at all time points. Mediation effects of daily stress on the relationship between HA and PSU were observed at baseline, 3, and 6 months. Conclusion: The findings suggest that managing stress may important in PSU children and adolescents with high HA.

Enhanced resting-state EEG source functional connectivity within the default mode and reward-salience networks in internet gaming disorder.

BACKGROUND: The two key mechanisms affected by internet gaming disorder (IGD) are cognitive and reward processing. Despite their significance, little is known about neurophysiological features as determined using resting-state electroencephalography (EEG) source functional connectivity (FC). METHODS: We compared resting-state EEG source FC within the default mode network (DMN) and reward/salience network (RSN) between patients with IGD and healthy controls (HCs) to identify neurophysiological markers associated with cognitive and reward processing. A total of 158 young male adults (79 patients with IGD and 79 HCs) were included, and the source FC of the DMN and RSN in five spectral bands (delta, theta, alpha, beta, and gamma) were assessed. RESULTS: Patients with IGD showed increased theta, alpha, and beta connectivity within the DMN between the orbitofrontal cortex and parietal regions compared with HCs. In terms of RSN, patients with IGD exhibited elevated alpha and beta connectivity between the anterior cingulate gyrus and temporal regions compared with HCs. Furthermore, patients with IGD showed negative correlations between the severity of IGD symptoms and/or weekly gaming time and theta and alpha connectivity within the DMN and theta, alpha, and beta connectivity within the RSN. However, the duration of IGD was not associated with EEG source FC. CONCLUSIONS: Hyper-connectivities within the DMN and RSN may be considered potential state markers associated with symptom severity and gaming time in IGD.

Identification of Major Psychiatric Disorders From Resting-State Electroencephalography Using a Machine Learning Approach.

We aimed to develop a machine learning (ML) classifier to detect and compare major psychiatric disorders using electroencephalography (EEG). We retrospectively collected data from medical records, intelligence quotient (IQ) scores from psychological assessments, and quantitative EEG (QEEG) at resting-state assessments from 945 subjects [850 patients with major psychiatric disorders (six large-categorical and nine specific disorders) and 95 healthy controls (HCs)]. A combination of QEEG parameters including power spectrum density (PSD) and functional connectivity (FC) at frequency bands was used to establish models for the binary classification between patients with each disorder and HCs. The support vector machine, random forest, and elastic net ML methods were applied, and prediction performances were compared. The elastic net model with IQ adjustment showed the highest accuracy. The best feature combinations and classification accuracies for discrimination between patients and HCs with adjusted IQ were as follows: schizophrenia = alpha PSD, 93.83%; trauma and stress-related disorders = beta FC, 91.21%; anxiety disorders = whole band PSD, 91.03%; mood disorders = theta FC, 89.26%; addictive disorders = theta PSD, 85.66%; and obsessive-compulsive disorder = gamma FC, 74.52%. Our findings suggest that ML in EEG may predict major psychiatric disorders and provide an objective index of psychiatric disorders.

Relationship of Social and Behavioral Characteristics to Suicidality in Community Adolescents With Self-Harm: Considering Contagion and Connection on Social Media.

A close link has been established between self-harm and suicide risk in adolescents, and increasing attention is given to social media as possibly involved in this relationship. It is important to identify indicators of suicidality (i.e., suicide ideation or attempt) including aspects related to contagion in online and offline social networks and explore the role of social media in the relationship between social circumstances and suicidality in young adolescents with self-harm. This study explored characteristics of Korean adolescents with a recent history of self-harm and identified how behavioral and social features explain lifetime suicidality with emphasis on the impact of social media. Data came from a nationwide online survey among sixth- to ninth-graders with self-harm during the past 12 months (n = 906). We used χ2 tests of independence to explore potential concomitants of lifetime suicidality and employed a multivariate logistic regression model to examine the relationship between the explanatory variables and suicidality. Sensitivity analyses were performed with lifetime suicide attempt in place of lifetime suicidality. 33.9% (n = 306) and 71.2% (n = 642) reported to have started self-harm by the time they were fourth- and six-graders, respectively; 44.3% (n = 400) reported that they have friends who self-harm. Having endorsed moderate/severe forms and multiple forms of self-harm (OR 5.36, p < 0.001; OR 3.13, p < 0.001), having engaged in self-harm for two years or more (OR 2.42, p = 0.001), having friends who self-harm (OR 1.92, p = 0.013), and having been bullied at school were associated with an increased odds of lifetime suicidality (OR 2.08, p = 0.004). Notably, having posted content about one's self-harm on social media during the past 12 months was associated with an increased odds of lifetime suicidality (OR 3.15, p < 0.001), whereas having seen related content in the same period was not. Sensitivity analyses yielded similar results with lifetime suicide attempt, supporting our findings from the logistic regression. The current study suggests that self-harm may be prevalent from early adolescence in South Korea with assortative gathering. The relationship of vulnerable adolescents' social circumstances to suicide risk may be compounded by the role of social media. As the role of social media can be linked to both risk (i.e., contagion) and benefit (i.e., social connection and support), pre-existing vulnerabilities alongside SH and what online communication centers on should be a focus of clinical attention.

Effects of Antidepressant Treatment on Symptom Measures of Attention in Adolescents with Depression: A Preliminary Open-Label Study.

Objective: The effects of selective serotonin reuptake inhibitor (SSRI) on deficits in attention and executive function in adolescents with major depressive disorder (MDD) are relatively unknown. We aimed to investigate changes in symptom measures of attention in adolescents with MDD treated with escitalopram. Methods: The study included 82 MDD adolescents and 54 healthy controls aged from 12 to 17 years. Symptom measures of attention were assessed using the Attention-Deficit/Hyperactivity Disorder Rating Scale (ADHD-RS) and Child Behavior Checklist attention problems scale at baseline and during week 8. Adolescents who showed at least 40% improvement in the Children's Depression Rating Scale-Revised (CDRS-R) scores from baseline to week 8 were referred to as "responders." Results: No baseline differences were found between the responders (n = 47) and nonresponders (n = 35) in their age, sex, intelligence quotient, CDRS-R score, and attention measures. Linear mixed models showed significant group-by-time interaction effect in the ADHD-RS inattention subscale score, but not in the other attention measures. Conclusion: Our results suggest that treating depressive symptoms with SSRI may lead to improvements in attention in MDD adolescents. Monitoring changes in symptom measures of attention can be useful when treating adolescents with MDD. ClinicalTrials.gov identifier: NCT03547219.

Psychometric properties and factor structure of the Korean version of the screen for child anxiety related emotional disorders (SCARED).

BACKGROUND: The aim of this study was to examine the psychometric properties of the Korean version of Screen for Child Anxiety Related Emotional Disorders (SCARED) on a sample of Korean youths and to examine the cross-cultural differences in adolescents' anxiety. METHODS: Our study included 147 adolescents (ages 12-17, 92 girls), 93 with major depressive disorder and 54 as controls. Participants were evaluated using the Kiddie-Schedule for Affective Disorders and Schizophrenia for School-Age Children-Present and Lifetime Version (K-SADS-PL), SCARED, Child Behavior Checklist (CBCL), Disruptive Behavioral Disorder Scale (DBD) and Attention Deficit Hyperactivity Disorder Rating Scale (ADHD-RS). Pearson's r and Cronbach's α values of the SCARED were calculated, and exploratory factor analysis was conducted. RESULTS: The Korean SCARED scores were correlated with the total anxiety scores of K-SADS-PL (r = 0.74) and the CBCL anxious/depressed subscale scores (r = 0.35). Results showed a five-factor structure with good internal consistency, in which some items were loaded on different factors compared to previous studies. CONCLUSIONS: The Korean SCARED demonstrated promising psychometric properties, and could be a valid scale for screening anxiety symptoms in primary care. The fact that different items comprised the factors may reflect the cultural difference between United States and Korea in experiencing anxiety.

Attention-Deficit/Hyperactivity Disorder Symptom Characteristics in Korean Elementary School Children: Comparison with US Population.

OBJECTIVE: Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder in elementary school children. The present study investigated the characteristics of ADHD in Korean elementary school children using the Korean version of the ADHD Rating Scale (K-ARS). The data was compared with those obtained from a comparable American population. METHODS: Participants included 29,914 elementary school children, aged 6-12 years, from a medium-sized city. The parents completed the home version of the K-ARS. The total and subscale-specific normative data and sex- and age-related mean score differences were analyzed. These data were compared with those obtained from the American population using independent t-tests. RESULTS: Mean total and subscale K-ARS scores were significantly higher among boys (vs. girls) and younger children aged equal to or less than 8 years old (vs. older children). Mean scores on the hyperactivity-impulsivity subscale were lower than those of American children, but similar to another Korean sample. CONCLUSION: Our data characterized ADHD symptoms in Korean children. However, further studies are needed to identify the cultural differences underlying ratings of ADHD symptom severity.

Montreal cognitive assessment reflects cognitive reserve.

BACKGROUND: The Montreal Cognitive Assessment (MoCA) is known to have discriminative power for patients with Mild Cognitive Impairment (MCI). Recently Cognitive Reserve (CR) has been introduced as a factor that compensates cognitive decline. We aimed to assess whether the MoCA reflects CR. Furthermore, we assessed whether there were any differences in the efficacy between the MoCA and the Mini-Mental State Examination (MMSE) in reflecting CR. METHODS: MoCA, MMSE, and the Cognitive Reserve Index questionnaire (CRIq) were administered to 221 healthy participants. Normative data and associated factors of the MoCA were identified. Correlation and regression analyses of the MoCA, MMSE and CRIq scores were performed, and the MoCA score was compared with the MMSE score to evaluate the degree to which the MoCA reflected CR. RESULTS: The MoCA reflected total CRIq score (CRI; B = 0.076, P < 0.001), CRI-Education (B = 0.066, P <  0.001), and CRI-Working activity (B = 0.025, P = 0.042), while MMSE reflected total CRI (B = 0.044, P <  0.001) and CRI-Education (B = 0.049, P <  0.001) only. The MoCA differed from the MMSE in the reflection of total CRI (Z = 2.30). CONCLUSION: In this study, we show that the MoCA score reflects CR more sensitively than the MMSE score. Therefore, we suggest that MoCA can be used to assess CR and early cognitive decline.

Overflow risk analysis for designing a nonpoint sources control detention.

This paper presents a design method by which the overflow risk related to a detention for managing nonpoint pollutant sources in urban areas can be evaluated. The overall overflow risk of a nonpoint pollutant sources control detention can be estimated by inherent overflow risk and operational overflow risk. For the purpose of calculating overflow risk, the 3-parameter mixed exponential distribution is applied to describe the probability distribution of rainfall event depth. As a rainfall-runoff calculation procedure required for deriving a rainfall capture curve, the U.S. Natural Resources Conservation Service runoff curve number method is applied to consider the nonlinearity of the rainfall-runoff relation. Finally, the detention overflow risk is assessed with respect to the detention design capacity and drainage time. The proposed overflow risk assessment is expected to provide a baseline to determine quantitative parameters in designing a nonpoint sources control detention.