Utility of the diagnostic interview schedule for children for assessing Tourette syndrome in children

ADHD/CD-NET: automated EEG-based characterization of ADHD and CD using explainable deep neural network technique

In this study, attention deficit hyperactivity disorder (ADHD), a childhood neurodevelopmental disorder, is being studied alongside its comorbidity, conduct disorder (CD), a behavioral disorder. Because ADHD and CD share commonalities, distinguishing them is difficult, thus increasing the risk of misdiagnosis. It is crucial that these two conditions are not mistakenly identified as the same because the treatment plan varies depending on whether the patient has CD or ADHD. Hence, this study proposes an electroencephalogram (EEG)-based deep learning system known as ADHD/CD-NET that is capable of objectively distinguishing ADHD, ADHD + CD, and CD. The 12-channel EEG signals were first segmented and converted into channel-wise continuous wavelet transform (CWT) correlation matrices. The resulting matrices were then used to train the convolutional neural network (CNN) model, and the model's performance was evaluated using 10-fold cross-validation. Gradient-weighted class activation mapping (Grad-CAM) was also used to provide explanations for the prediction result made by the 'black box' CNN model. Internal private dataset (45 ADHD, 62 ADHD + CD and 16 CD) and external public dataset (61 ADHD and 60 healthy controls) were used to evaluate ADHD/CD-NET. As a result, ADHD/CD-NET achieved classification accuracy, sensitivity, specificity, and precision of 93.70%, 90.83%, 95.35% and 91.85% for the internal evaluation, and 98.19%, 98.36%, 98.03% and 98.06% for the external evaluation. Grad-CAM also identified significant channels that contributed to the diagnosis outcome. Therefore, ADHD/CD-NET can perform temporal localization and choose significant EEG channels for diagnosis, thus providing objective analysis for mental health professionals and clinicians to consider when making a diagnosis.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11571-023-10028-2.

Deep neural network technique for automated detection of ADHD and CD using ECG signal

BACKGROUND AND OBJECTIVE

Attention Deficit Hyperactivity problem (ADHD) is a common neurodevelopment problem in children and adolescents that can lead to long-term challenges in life outcomes if left untreated. Also, ADHD is frequently associated with Conduct Disorder (CD), and multiple research have found similarities in clinical signs and behavioral symptoms between both diseases, making differentiation between ADHD, ADHD comorbid with CD (ADHD+CD), and CD a subjective diagnosis. Therefore, the goal of this pilot study is to create the first explainable deep learning (DL) model for objective ECG-based ADHD/CD diagnosis as having an objective biomarker may improve diagnostic accuracy.

METHODS

The dataset used in this study consist of ECG data collected from 45 ADHD, 62 ADHD+CD, and 16 CD patients at the Child Guidance Clinic in Singapore. The ECG data were segmented into 2 s epochs and directly used to train our 1-dimensional (1D) convolutional neural network (CNN) model.

RESULTS

The proposed model yielded 96.04% classification accuracy, 96.26% precision, 95.99% sensitivity, and 96.11% F1-score. The Gradient-weighted class activation mapping (Grad-CAM) function was also used to highlight the important ECG characteristics at specific time points that most impact the classification score.

CONCLUSION

In addition to achieving model performance results with our suggested DL method, Grad-CAM's implementation also offers vital temporal data that clinicians and other mental healthcare professionals can use to make wise medical judgments. We hope that by conducting this pilot study, we will be able to encourage larger-scale research with a larger biosignal dataset. Hence allowing biosignal-based computer-aided diagnostic (CAD) tools to be implemented in healthcare and ambulatory settings, as ECG can be easily obtained via wearable devices such as smartwatches.

Teacher Knowledge of Tourette Syndrome and Associated Factors

BACKGROUND

TS is associated with learning disabilities and educational impairment. Teacher knowledge about TS may have a positive impact on students with TS, but factors associated with teacher knowledge of TS are not known.

METHODS

In this cross-sectional study, teachers of youth with TS and of a community control group completed a Teacher Understanding of Tourette Syndrome Survey (TUTS), a pilot questionnaire enquiring about self-perceived understanding, teacher knowledge, and sources of information. We compared TUTS scores between TS and control groups and between those who did and did not use specific sources of information about TS using Wilcoxon rank-sum tests. Bivariate correlation analyses were used to evaluate associations between teacher knowledge and potential contributing factors.

RESULTS

Data from 114 teachers of children with TS and 78 teachers of control subjects were included. Teachers of youth with TS had significantly more knowledge, had higher self-perceived understanding, and used more sources of information than teachers of the control group. Teachers who knew of the Tourette Association of America and who gathered information themselves had higher knowledge about TS than those who did not.

CONCLUSION

Teachers of children with TS know more about TS and use more sources to learn about TS than teachers of children without TS.

Brief youth self-report screener for tics: Can a subscale of the Motor tic, Obsession and compulsion, and Vocal tic Evaluation Survey (MOVES) identify tic disorders in youth?

Tics are unwanted, repetitive movements and sounds that frequently present during childhood. They are typically brief and purposeless, but can create significant distress for individuals, and often co-occur with other neuropsychiatric conditions. Thus, early identification of tics is warranted. Unfortunately, tics are often misdiagnosed, and because tics may wax and wane, identification can be difficult, especially in the context of routine clinical visits. There are limited tools that can be used to reliably identify tics in clinical practice, especially in non-specialty settings. The purpose of the current study was to evaluate the performance of the Motor tic, Obsession and compulsion, and Vocal tic Evaluation Survey (MOVES), a self-report scale with some support as a screening tool. In addition, the performance of a subset of questions (the MOVES-6) was evaluated for rapid screening. Participants were recruited across two study sites and included children and adolescents diagnosed with Tourette syndrome (n = 151) or another persistent tic disorder (n = 10) and community controls (n = 74). Results suggest both the MOVES and the MOVES-6 have high sensitivity (90% and 88%, respectively) and at least acceptable specificity (77% and 86%, respectively) compared with expert assessment of tic disorders, suggesting that both versions can identify tic disorders without high proportions of false negatives. Both versions were highly sensitive with acceptable specificity regardless of sex, race/ethnicity, and age. The MOVES and MOVES-6 show promise as a screener for tics or tic disorders, but additional research is needed, particularly in a general population setting.

Validation of the Diagnostic Interview Schedule for Children (DISC-5) Tic Disorder and Attention-Deficit/Hyperactivity Disorder Modules

Effective methods to assess mental disorders in children are necessary for accurate prevalence estimates and to monitor prevalence over time. This study assessed updates of the tic disorder and attention-deficit/hyperactivity disorder (ADHD) modules of the Diagnostic Interview Schedule for Children, Version 5 (DISC-5) that reflect changes in diagnostic criteria in the Diagnostic and Statistical Manual of Mental Disorders (Fifth edition, DSM-5). The DISC-5 tic disorder and ADHD parent- and child-report modules were compared to expert clinical assessment for 100 children aged 6-17 years (40 with tic disorder alone, 17 with tic disorder and ADHD, 9 with ADHD alone, and 34 with neither) for validation. For the tic disorder module, parent-report had high (>90%) sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy, while the youth-report had high specificity and PPV, moderate accuracy (81.4%), and lower sensitivity (69.8%) and NPV (67.3%). The ADHD module performed less well: parent-report had high NPV (91.4%), moderate sensitivity (80.8%), and lower specificity (71.6%), PPV (50.0%), and accuracy (74.0%); youth-report had moderate specificity (82.8%) and NPV (88.3%), and lower sensitivity (65.0%), PPV (54.2%), and accuracy (78.6%). Adding teacher-report of ADHD symptoms to DISC-5 parent-report of ADHD increased sensitivity (94.7%) and NPV (97.1%), but decreased specificity (64.2%), PPV (48.7%), and accuracy (72.2%). These findings support using the parent-report tic disorder module alone or in combination with the child report module in future research and epidemiologic studies; additional validation studies are warranted for the ADHD module.

Evaluation of new instruments for screening and diagnosis of tics and tic disorders in a well-characterized sample of youth with tics and recruited controls

Tics and tic disorders can significantly impact children, but limited screening tools and diagnostic challenges may delay access to care. The current study attempted to address these gaps by evaluating sensitivity and specificity of the Motor or Vocal Inventory of Tics (MOVeIT), a tic symptom screener, and the Description of Tic Symptoms (DoTS), a brief diagnostic assessment for tic disorders. Children (n=100, age 6-17 years old) with tic disorders attending a Tourette specialty clinic and a community-recruited sample without tics completed a gold-standard assessment by a tic expert; these evaluations were compared to child self-report and parent and teacher report versions of the MOVeIT, and child and parent versions of the DoTS. The parent and child MOVeIT met or exceeded pre-specified 85% sensitivity and specificity criteria for detecting the presence of tics when compared to a gold-standard tic expert diagnosis. The Teacher MOVeIT had lower sensitivity (71.4%) but good specificity (95.7%) for identifying any tic symptoms compared to gold standard. For determination of the presence or absence of any tic disorder, sensitivity of both parent and child DoTS was 100%; specificity of the parent DoTS was 92.7% and child DoTS specificity was 75.9%. More work may be needed to refine the teacher MOVeIT, but it is also recognized that tic expression may vary by setting. While the MOVeIT and DoTS parent and child questionnaires demonstrated adequate sensitivity and specificity for determining the presence of tics and tic disorders in this well-defined sample, additional testing in a general population is warranted.

European clinical guidelines for Tourette syndrome and other tic disorders-version 2.0. Part I: assessment

In 2011 a working group of the European Society for the Study of Tourette Syndrome (ESSTS) has developed the first European assessment guidelines for Tourette syndrome (TS). Now, we present an updated version 2.0 of these European clinical guidelines for Tourette syndrome and other tic disorders, part I: assessment. Therefore, the available literature has been thoroughly screened, supplemented with national guidelines across countries and discussions among ESSTS experts. Diagnostic changes between DSM-IV and DSM-5 classifications were taken into account and new information has been added regarding differential diagnoses, with an emphasis on functional movement disorders in both children and adults. Further, recommendations regarding rating scales to evaluate tics, comorbidities, and neuropsychological status are provided. Finally, results from a recently performed survey among ESSTS members on assessment in TS are described. We acknowledge that the Yale Global Tic Severity Scale (YGTSS) is still the gold standard for assessing tics. Recommendations are provided for scales for the assessment of tics and psychiatric comorbidities in patients with TS not only in routine clinical practice, but also in the context of clinical research. Furthermore, assessments supporting the differential diagnosis process are given as well as tests to analyse cognitive abilities, emotional functions and motor skills.

Community-Based Prevalence of Externalizing and Internalizing Disorders among School-Aged Children and Adolescents in Four Geographically Dispersed School Districts in the United States

The Project to Learn About Youth-Mental Health (PLAY-MH; 2014-2018) is a school-based, two-stage study designed to estimate the prevalence of selected mental disorders among K-12 students in four U.S.-based sites (Colorado, Florida, Ohio, and South Carolina). In Stage 1, teachers completed validated screeners to determine student risk status for externalizing or internalizing problems or tics; the percentage of students identified as being at high risk ranged from 17.8% to 34.4%. In Stage 2, parents completed a structured diagnostic interview to determine whether their child met criteria for fourteen externalizing or internalizing disorders; weighted prevalence estimates of meeting criteria for any disorder were similar in three sites (14.8%-17.8%) and higher in Ohio (33.3%). PLAY-MH produced point-in-time estimates of mental disorders in K-12 students, which may be used to supplement estimates from other modes of mental disorder surveillance and inform mental health screening and healthcare and educational services.

Automated detection of conduct disorder and attention deficit hyperactivity disorder using decomposition and nonlinear techniques with EEG signals

BACKGROUND AND OBJECTIVES

Attention deficit hyperactivity disorder (ADHD) is often presented with conduct disorder (CD). There is currently no objective laboratory test or diagnostic method to discern between ADHD and CD, and diagnosis is further made difficult as ADHD is a common neuro-developmental disorder often presenting with other co-morbid difficulties; and in particular with conduct disorder which has a high degree of associated behavioural challenges. A novel automated system (AS) is proposed as a convenient supplementary tool to support clinicians in their diagnostic decisions. To the best of our knowledge, we are the first group to develop an automated classification system to classify ADHD, CD and ADHD+CD classes using brain signals.

METHODS

The empirical mode decomposition (EMD) and discrete wavelet transform (DWT) methods were employed to decompose the electroencephalogram (EEG) signals. Autoregressive modelling coefficients and relative wavelet energy were then computed on the signals. Various nonlinear features were extracted from the decomposed coefficients. Adaptive synthetic sampling (ADASYN) was then employed to balance the dataset. The significant features were selected using sequential forward selection method. The highly discriminatory features were subsequently fed to an array of classifiers.

RESULTS

The highest accuracy of 97.88% was achieved with the K-Nearest Neighbour (KNN) classifier. The proposed system was developed using ten-fold validation strategy on EEG data from 123 children. To the best of our knowledge this is the first study to develop an AS for the classification of ADHD, CD and ADHD+CD classes using EEG signals.

POTENTIAL APPLICATION

Our AS can potentially be used as a web-based application with cloud system to aid the clinical diagnosis of ADHD and/or CD, thus supporting faster and accurate treatment for the children. It is important to note that testing with larger data is required before the AS can be employed for clinical applications.

Efficacy of Parent-Delivered, Home-Based Therapy for Tics

BACKGROUND

Although behavioral therapy is an effective approach to reduce tics in children and adults, there is an insufficient availability and accessibility of behavioral therapy in the community.

OBJECTIVE

The goal of the study was to test the clinical efficacy of home-based, parent-provided behavioral therapy in children with Tourette syndrome aged seven to 13 years.

METHOD

An instructional habit reversal training-based video and guide was developed for use by parents. Eligible families, in this 10-week study, were enrolled in either a home-based therapy (DVD) group (received disk and written instructions) or an in-person therapist group (had scheduled visits with the therapist). Outcome scales included the Yale Global Tic Severity Scale, both the total Tic Severity Score and total Global Severity Score, and the parent report of Clinical Global Impressions of Improvement.

RESULTS

Forty-four children (mean age = 10.21 ± 1.69 years) were enrolled into either the DVD (n = 33) or in-person therapist (n = 11) groups. Eighteen completed the study-eight in the DVD and 10 in the in-person therapist group. Outcome measures showed significant reductions in Yale Global Tic Severity Scale change ratios: mean improvement on the Tic Severity Score was DVD 32.4% (P < 0.001) and in-person therapist 26.6% (P = 0.01); and for the Global Severity Score, DVD 33.7% (P < 0.001) and in-person therapist 26.7% (P < 0.001).

CONCLUSIONS

Home-based, parent-administered habit reversal training behavioral therapy is efficacious for reducing tics in children. Telephone contacts early in the DVD treatment course might reduce the number of dropouts.

Design of a Multisite Study Assessing the Impact of Tic Disorders on Individuals, Families, and Communities

BACKGROUND

Tic disorders, including Tourette syndrome, are complex, multisymptom diseases, yet the impact of these disorders on affected children, families, and communities is not well understood.

METHODS

To improve the understanding of the impacts of Tourette syndrome, two research groups conducted independent cross-sectional studies using qualitative and quantitative measures. They focused on similar themes, but distinct scientific objectives, and the sites collaborated to align methods of independent research proposals with the aim of increasing the analyzable sample size.

RESULTS

Site 1 (University of Rochester) was a Pediatric Neurology referral center. Site 2 (University of South Florida) was a Child Psychiatry referral center. A total of 205 children with tic disorders were enrolled from both studies. The University of Rochester also enrolled 100 control children in order to clearly isolate impacts of Tourette syndrome distinct from those occurring in the general population. The majority of children with tic disorders (n = 191, 93.1%) had Tourette syndrome, the primary population targeted for these studies. Children with Tourette syndrome were similar across sites in terms of tic severity and the occurrence of comorbid conditions. The occurrence of psychiatric comorbidities in the control group was comparable with that in the general pediatric population of the United States, making this a well-justified comparison group.

CONCLUSIONS

Through collaboration, two sites conducting independent research developed convergent research methods to enable pooling of data, and by extension increased power, for future analyses. This method of collaboration is a novel model for future epidemiological research of tic disorders.

Predictors of parent-child agreement on child anxiety diagnoses on the ADIS-IV-C/P

Diagnostic agreement between parents' and children's reports on children's anxiety problems is notoriously poor; however, very few investigations have examined specific predictors of inter-rater agreement on child anxiety diagnoses. This study examined predictors of categories of parent and child diagnostic endorsement on the Anxiety Disorders Interview Schedule for Children-IV. One hundred eight children (ages 7-13) and their parents completed structured diagnostic interviews for non-OCD/PTSD anxiety diagnoses and paper and pencil measures of functioning and impairment in a variety of domains. Parent-child agreement was statistically significant for social phobia and separation anxiety disorder, but was overall poor for all anxiety diagnoses. Externalizing disorder status, family accommodation frequency, and child rated impairment in various domains differentially predicted informant discrepancies for different anxiety disorders. These data are among the first to suggest variables that may explain parent-child concordance.

VISIT-TS: A multimedia tool for population studies on tic disorders

Population-based assessment of Tourette syndrome (TS) and other tic disorders produces a paradox. On one hand, ideally diagnosis of tic disorders requires expert observation. In fact, diagnostic criteria for TS explicitly require expert assessment of tics for a definite diagnosis. On the other hand, large-scale population surveys with expert assessment of every subject are impracticable. True, several published studies have successfully used expert assessment to find tic prevalence in a representative population (e.g. all students in a school district). However, extending these studies to larger populations is daunting.

We created a multimedia tool to demonstrate tics to a lay audience, discuss their defining and common attributes, and address features that differentiate tics from other movements and vocalizations. A first version was modified to improve clarity and to include a more diverse group in terms of age and ethnicity. The result is a tool intended for epidemiological research. It may also provide additional benefits, such as more representative minority recruitment for other TS studies and increased community awareness of TS.