Helping parents make sense of ADHD diagnosis and treatment

A Robust Machine Learning Based Framework for the Automated Detection of ADHD Using Pupillometric Biomarkers and Time Series Analysis

Accurate and efficient detection of attention-deficit/hyperactivity disorder (ADHD) is critical to ensure proper treatment for affected individuals. Current clinical examinations, however, are inefficient and prone to misdiagnosis, as they rely on qualitative observations of perceived behavior. We propose a robust machine learning based framework that analyzes pupil-size dynamics as an objective biomarker for the automated detection of ADHD. Our framework integrates a comprehensive pupillometric feature engineering and visualization pipeline with state-of-the-art binary classification algorithms and univariate feature selection. The support vector machine classifier achieved an average 85.6% area under the receiver operating characteristic (AUROC), 77.3% sensitivity, and 75.3% specificity using ten-fold nested cross-validation (CV) on a declassified dataset of 50 patients. 218 of the 783 engineered features, including fourier transform metrics, absolute energy, consecutive quantile changes, approximate entropy, aggregated linear trends, as well as pupil-size dilation velocity, were found to be statistically significant differentiators (p < 0.05), and provide novel behavioral insights into associations between pupil-size dynamics and the presence of ADHD. Despite a limited sample size, the strong AUROC values highlight the robustness of the binary classifiers in detecting ADHD—as such, with additional data, sensitivity and specificity metrics can be substantially augmented. This study is the first to apply machine learning based methods for the detection of ADHD using solely pupillometrics, and highlights its strength as a potential discriminative biomarker, paving the path for the development of novel diagnostic applications to aid in the detection of ADHD using oculometric paradigms and machine learning.

Prevalence and contributing factors to attention deficit hyperactivity disorder: a study of five- to fifteen-year-old children in Zhabei District, Shanghai

INTRODUCTION

This work aims to understand the features among 5- to 15-year-old children with attention deficit hyperactivity disorder (ADHD) in Zhabei District in Shanghai.

METHODS

Children with ADHD were studied using general background questionnaire, ADHD symptom rating questionnaire, and cluster-stratified sampling. A total of 9,900 valid questionnaires were utilized in this study. We conducted diagnostic interviews with suspected ADHD children and their parents using the criteria of the Diagnostic and Statistical Manual of Mental Disorders (4th Edition) for ADHD.

RESULTS

The prevalence rate of ADHD among the children was 4.6%, of which 2.4%, 0.4%, and 1.8% had ADHD-I ADHD-HI, and ADHD-C types, respectively. The prevalence rates in boys and girls were 6.6% and 2.7% (ratio, 2.41 : 1), respectively. Significant differences in prevalence rate were found among children with different age groups and ADHD types. Children aged 7-10 years had the highest prevalence rate (6.3%). Externally, residence children had higher prevalence than local residents. Significant differences in prevalence rate were also found among children with parents having different educational and socioeconomic level.

DISCUSSION

The prevalence of ADHD-HI was higher than the other two types. The highest prevalence was observed in 7- to 10-year-old children. The influential factors of ADHD prevalence were age, gender, and educational level.