Prediction of Attention-Deficit/Hyperactivity Disorder Diagnosis Using Brief, Low-Cost Clinical Measures: A Competitive Model Evaluation.

Proper diagnosis of ADHD is costly, requiring in-depth evaluation via interview, multi-informant and observational assessment, and scrutiny of possible other conditions. The increasing availability of data may allow the development of machine-learning algorithms capable of accurate diagnostic predictions using low-cost measures to supplement human decision-making. We report on the performance of multiple classification methods used to predict a clinician-consensus ADHD diagnosis. Methods ranged from fairly simple (e.g., logistic regression) to more complex (e.g., random forest), while emphasizing a multi-stage Bayesian approach. Classifiers were evaluated in two large (N>1000), independent cohorts. The multi-stage Bayesian classifier provides an intuitive approach consistent with clinical workflows, and was able to predict expert consensus ADHD diagnosis with high accuracy (>86%)-though not significantly better than other methods. Results suggest that parent and teacher surveys are sufficient for high-confidence classifications in the vast majority of cases, while an important minority require additional evaluation for accurate diagnosis.

Youth Polygenic Scores, Youth ADHD Symptoms, and Parenting Dimensions: An Evocative Gene-Environment Correlation Study.

Parenting practices and parental symptoms of attention-deficit/hyperactivity disorder (ADHD) have been linked to severity and course of youth ADHD. However, genetically influenced behaviors related to ADHD in youth may also influence parenting behaviors. Polygenic scores (PGS) have been widely used to quantify genetic vulnerability for ADHD but has rarely been used to examine gene-environment correlation effects. The current study examined the direct effects of youth ADHD PGS and its evocative effects on parenting behaviors via youth ADHD symptoms. 803 youth aged 6-18 years (58.5% male) completed a multistage, multi-informant assessment that included measures of parenting practices and youth and parental ADHD symptoms. A mediation model was used to evaluate direct and evocative effects. Furthermore, we examined if these evocative effects remain after controlling for parental ADHD symptoms. Sensitivity analyses across age, sex, and socioeconomic status (SES) as well as restricting ancestry groups to European only ancestry were also conducted. Results indicated that youth ADHD PGS reliably predicted youth ADHD symptoms across all models (ßs ranging from 0.18 to 0.26), including across age, sex, and SES and held even with ancestry restricted to the largest group (northern European). Evocative effects emerged such that higher youth PGS significantly predicted more youth ADHD symptoms, which in turn, significantly predicted lower levels of parental involvement and higher levels of poor supervision/monitoring and inconsistent discipline. These effects remained after controlling for parent ADHD symptoms.

Attention-Deficit/Hyperactivity Disorder: Restricted Phenotypes Prevalence, Comorbidity, and Polygenic Risk Sensitivity in the ABCD Baseline Cohort.

OBJECTIVE: To evaluate the prevalence and major comorbidities of ADHD using different operational definitions in a newly available national dataset and to test the utility of operational definitions against genetic and cognitive correlates. METHOD: The US Adolescent Brain Cognitive Development (ABCD) Study enrolled 11,878 children aged 9-10 years at baseline. ADHD prevalence, comorbidity, and association with polygenic risk score and laboratory-assessed executive functions were calculated at 4 thresholds of ADHD phenotype restrictiveness. Bias from missingness, sampling, and nesting were addressed statistically. RESULTS: Prevalence of current ADHD for 9- to 10-year old children was 3.53% (95% CI 3.14%-3.92%) when Computerized Schedule for Affective Disorders and Schizophrenia for School-Age Children (K-SADS-COMP) score and parent and teacher ratings were required to converge. Of ADHD cases so defined, 70% had a comorbid psychiatric disorder. After control for overlapping comorbidity and ruling out for psychosis or low IQ, 30.9% (95% CI 25.7%-36.7%) had a comorbid disruptive behavior disorder, 27.4% (95% CI 22.3%-33.1%) had an anxiety or fear disorder, and 2.1% (95% CI 1.2%-3.8%) had a mood disorder. Children in the top decile of polygenic load incurred a 63% increased chance of having ADHD vs the bottom half of polygenic load (p < .01)-an effect detected only with a stringent phenotype definition. Dimensional latent variables for irritability, externalizing, and ADHD yielded convergent results for cognitive correlates. CONCLUSION: This fresh estimate of national prevalence of ADHD in the United States suggests that the DSM-5 definition requiring multiple informants yields a prevalence of about 3.5%. Results may inform further ADHD studies in the ABCD sample.