Who predict ADHD with better diagnostic accuracy?: Parents or teachers?

Use of Machine Learning Models to Differentiate Neurodevelopment Conditions Through Digitally Collected Data: Cross-Sectional Questionnaire Study

BACKGROUND

Diagnosis of child and adolescent psychopathologies involves a multifaceted approach, integrating clinical observations, behavioral assessments, medical history, cognitive testing, and familial context information. Digital technologies, especially internet-based platforms for administering caregiver-rated questionnaires, are increasingly used in this field, particularly during the screening phase. The ascent of digital platforms for data collection has propelled advanced psychopathology classification methods such as supervised machine learning (ML) into the forefront of both research and clinical environments. This shift, recently called psycho-informatics, has been facilitated by gradually incorporating computational devices into clinical workflows. However, an actual integration between telemedicine and the ML approach has yet to be fulfilled.

OBJECTIVE

Under these premises, exploring the potential of ML applications for analyzing digitally collected data may have significant implications for supporting the clinical practice of diagnosing early psychopathology. The purpose of this study was, therefore, to exploit ML models for the classification of attention-deficit/hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) using internet-based parent-reported socio-anamnestic data, aiming at obtaining accurate predictive models for new help-seeking families.

METHODS

In this retrospective, single-center observational study, socio-anamnestic data were collected from 1688 children and adolescents referred for suspected neurodevelopmental conditions. The data included sociodemographic, clinical, environmental, and developmental factors, collected remotely through the first Italian internet-based screening tool for neurodevelopmental disorders, the Medea Information and Clinical Assessment On-Line (MedicalBIT). Random forest (RF), decision tree, and logistic regression models were developed and evaluated using classification accuracy, sensitivity, specificity, and importance of independent variables.

RESULTS

The RF model demonstrated robust accuracy, achieving 84% (95% CI 82-85; P<.001) for ADHD and 86% (95% CI 84-87; P<.001) for ASD classifications. Sensitivities were also high, with 93% for ADHD and 95% for ASD. In contrast, the DT and LR models exhibited lower accuracy (DT 74%, 95% CI 71-77; P<.001 for ADHD; DT 79%, 95% CI 77-82; P<.001 for ASD; LR 61%, 95% CI 57-64; P<.001 for ADHD; LR 63%, 95% CI 60-67; P<.001 for ASD) and sensitivities (DT: 82% for ADHD and 88% for ASD; LR: 62% for ADHD and 68% for ASD). The independent variables considered for classification differed in importance between the 2 models, reflecting the distinct characteristics of the 3 ML approaches.

CONCLUSIONS

This study highlights the potential of ML models, particularly RF, in enhancing the diagnostic process of child and adolescent psychopathology. Altogether, the current findings underscore the significance of leveraging digital platforms and computational techniques in the diagnostic process. While interpretability remains crucial, the developed approach might provide valuable screening tools for clinicians, highlighting the significance of embedding computational techniques in the diagnostic process.

The Development and Content Validation of a Clinical Screening Scale to Identify Attention-Deficit Hyperactivity Disorder Cases Based on the Gender Perspective: An e-Delphi Study

BACKGROUND

Although many studies analyse gender differences in the clinical expression of Attention-Deficit Hyperactivity Disorder (ADHD) and prevalence studies show that girls with ADHD are underdiagnosed, there are no instruments that are sensitive to the detection of girls with ADHD.

OBJECTIVE

The objective of this study is to develop a self-report early detection instrument for boys and girls with ADHD aged 7 to 16, which includes the gender perspective and is sensitive to the detection of girls with ADHD.

METHODS

The scale was developed and the items that comprised it were created from the thematic analysis of ADHD and its evaluation in children based on the diagnostic criteria of the DSM-5-TR. A modified e-Delphi method involving a three-round web survey was used to establish a consensus on the content of the scale. Ten experts were recruited to form a professional panel. The panel members were asked to assess the differential symptomatology of ADHD in boys and girls, the dimensions to be evaluated, and the importance of scale items to evaluate the content.

RESULTS

A consensus was reached regarding 13 total items distributed in three dimensions: inattention; hyperactivity/impulsivity; and, a third dimension, internalisation, which includes symptoms most present in the expression of ADHD in girls.

CONCLUSIONS

To the best of our knowledge, the development of this scale using the Delphi method is the first specific scale used for identifying ADHD that also addresses the gender perspective and the differential symptomatology between boys and girls. However, we must proceed to the analysis of psychometric properties, as the scale requires an exhaustive study of its reliability and validity. We can anticipate that this scale will provide relevant and reliable information that can be used for the identification of ADHD in both boys and girls.

Factors associated with parent-teacher hyperactivity/inattention screening discrepancy: Findings from a UK national sample

BACKGROUND

To fulfil the diagnostic criteria of Attention Deficit Hyperactivity Disorder in the Fifth Edition of Diagnostic and Statistical Manual of Mental Disorders (DSM-5), symptoms should be observed in two or more settings. This implies that diagnostic procedures require observations reported from informants in different settings, such as teachers in school and caregivers at home. This study examined parent-teacher agreement in reporting hyperactivity/inattention and its relationship with child's, parent's, and family's characteristics.

METHOD

We used data from the 2004 United Kingdom Mental Health of Children and Young People survey, including 7977 children aged 4-17, to investigate cross-informant agreement between parents and teachers on the hyperactivity-inattention subscale of the Strengths and Difficulties Questionnaire. The characteristics of different patterns of informant agreement were assessed using multinomial logistic regression.

RESULTS

Cross-informant agreement of parent and teacher was low (weighted kappa = .34, 95% C.I.: .31, .37). Some characteristics, such as male child and parental emotional distress, were associated with higher likelihood of parent-teacher discrepancy.

CONCLUSION

We found low informant agreement in the hyperactive/inattention subscale, as hypothesised and consistent with previous studies. The current study has found several factors that predict discrepancy, which were partly consistent with previous research. Possible explanation, implications, and further research on parent-teacher informant discrepancy in reporting hyperactivity/inattention were discussed.

Exploring telediagnostic procedures in child neuropsychiatry: addressing ADHD diagnosis and autism symptoms through supervised machine learning

Recently, there has been an increase in telemedicine applied to child neuropsychiatry, such as the use of online platforms to collect remotely case histories and demographic and behavioral information. In the present proof-of-concept study, we aimed to understand to what extent information parents and teachers provide through online questionnaires overlaps with clinicians' diagnostic conclusions on attention-deficit/hyperactivity disorder (ADHD). Moreover, we intended to explore a possible role that autism spectrum disorders (ASD) symptoms played in this process. We examined parent- and teacher-rated questionnaires collected remotely and an on-site evaluation of intelligence quotients from 342 subjects (18% females), aged 3-16 years, and referred for suspected ADHD. An easily interpretable machine learning model-decision tree (DT)-was built to simulate the clinical process of classifying ADHD/non-ADHD based on collected data. Then, we tested the DT model's predictive accuracy through a cross-validation approach. The DT classifier's performance was compared with those that other machine learning models achieved, such as random forest and support vector machines. Differences in ASD symptoms in the DT-identified classes were tested to address their role in performing a diagnostic error using the DT model. The DT identified the decision rules clinicians adopt to classify an ADHD diagnosis with an 82% accuracy rate. Regarding the cross-validation experiment, our DT model reached a predictive accuracy of 74% that was similar to those of other classification algorithms. The caregiver-reported ADHD core symptom severity proved the most discriminative information for clinicians during the diagnostic decision process. However, ASD symptoms were a confounding factor when ADHD severity had to be established. Telehealth procedures proved effective in obtaining an automated output regarding a diagnostic risk, reducing the time delay between symptom detection and diagnosis. However, this should not be considered an alternative to on-site procedures but rather as automated support for clinical practice, enabling clinicians to allocate further resources to the most complex cases.

Sociodemographic disparities in ADHD diagnosis and treatment among U.S. elementary schoolchildren

We examined whether some groups of U.S. elementary schoolchildren are less likely to be diagnosed and treated for ADHD in analyses of a population-based cohort (N = 10,920). We predicted ADHD diagnosis using measures of race and ethnicity, age, socioeconomic status, birthweight, individually assessed academic, behavioral, and executive functioning, family language use, mental health, health insurance coverage, marital status, school composition, and geographic region. We predicted prescription medication use among those diagnosed with ADHD. We stratified additional analyses by biological sex. Black children (aOR, 0.60), girls (aOR, 0.55), and emergent bilinguals (aOR, 0.29) were less likely to have an ADHD diagnosis than observationally similar White children, boys, or those from English-speaking households. Black children's under-diagnosis occurred among boys. Emergent bilingual children's under-diagnosis occurred among both boys and girls. Girls (aOR, 0.52) and emergent bilinguals (aOR, 0.24) with ADHD were less likely to use prescription medication. Sociodemographic disparities in ADHD diagnosis and treatment occur among U.S. elementary schoolchildren. Measured confounds including independently assessed ADHD symptomatology and impairment do not explain the disparities. The findings empirically support cultural, linguistic, and biological sensitivity in the ADHD diagnostic and treatment procedures in use for the U.S. pediatric population.

Exploring Teachers' Knowledge and Attitudes Toward Attention Deficit Hyperactivity Disorder and Its Treatment in a District of Turkey

Background Teachers are pivotal in integrating children with attention deficit hyperactivity disorder (ADHD) into academic and social contexts. Their comprehension of and attitudes toward ADHD significantly influence the inclusion of these children. This study was conducted to assess teachers' knowledge, attitudes, and perceptions about ADHD and its treatment within a representative sample from Turkey. Methods An online self-administered questionnaire was formulated to gauge teachers' knowledge, attitudes, and perceptions related to ADHD and its treatment. Results Of the respondents, 57.7% accurately identified that ADHD is more commonly present in boys. Furthermore, a majority of teachers (60.8%) correctly answered the question related to the comorbidity of ADHD and learning disabilities. However, 20.3% of teachers believed that ADHD medications were addictive, with 9.7% expressing reluctance to use such treatment for their children if needed. Conclusion The results highlight the need for revising the current training curricula for novice teachers and providing additional training for experienced teachers. Such initiatives should aim to rectify any negative perceptions and attitudes toward ADHD held by teachers.

A Wearable Diagnostic Assessment System vs. SNAP-IV for the auxiliary diagnosis of ADHD: a diagnostic test

OBJECTIVE

We design a diagnostic test to evaluate the effectiveness and accuracy of A non-intrusive Wearable Diagnostic Assessment System versus SNAP-IV for auxiliary diagnosis of children with ADHD.

METHODS

This study included 55 children aged 6-16 years who were clinically diagnosed with ADHD by DSM-5, and 55 healthy children (typically developing). Each subject completes 10 tasks on the WeDA system (Wearable Diagnostic Assessment System) and Parents of each subject complete the SNAP-IV scale. We will calculate the validity indexes, including sensitivity, specificity, Youden's index, likelihood ratio, and other indexes including predictive value, diagnostic odds ratio, diagnostic accuracy and area under the curve [AUC] to assess the effectiveness of the WeDA system as well as the SNAP-IV.

RESULTS

The sensitivity (94.55% vs. 76.36%) and the specificity (98.18% vs. 80.36%) of the WeDA system were significantly higher than the SNAP-IV. The AUC of the WeDA system (0.964) was higher than the SNAP-IV (0.907). There is non-statistically significant difference between groups (p = 0.068), and both of them have high diagnostic accuracy. In addition, the diagnostic efficacy of the WeDA system was higher than that of SNAP-IV in terms of the Youden index, diagnostic accuracy, likelihood ratio, diagnostic odds ratio and predictive value.

CONCLUSION

The advantages of the WeDA system in terms of diagnostic objectivity, scientific design and ease of operation make it a promising system for widespread use in clinical practice.