Dataset Information

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

ABSTRACT: 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.

SUBMITTER: Mooney MA

PROVIDER: S-EPMC10191260 | biostudies-literature | 2023 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Mooney Michael A MA Neighbor Christopher C Karalunas Sarah S Dieckmann Nathan F NF Nikolas Molly M Nousen Elizabeth E Tipsord Jessica J Song Xubo X Nigg Joel T JT

Clinical psychological science : a journal of the Association for Psychological Science 20221222 3

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 ...[more]

PMID: 37205171

Similar Datasets

Project description:Objective: The Diagnostic and Statistical Manual of Mental Disorders, fifth edition (DSM-5), classifies attention-deficit/hyperactivity disorder (ADHD) as a neurodevelopmental disorder, with symptoms becoming apparent as early as the preschool years. Early recognition can lead to interventions such as parent/teacher-administered behavior therapy, the recommended first-line treatment for preschool patients. There are few data, however, to inform the use of second-line, pharmacotherapy options in this population. In this review, we identified recent literature on the diagnosis and treatment of ADHD in preschool children. Methods: A PubMed and clinicaltrials.gov search was conducted for trials assessing efficacy or safety of ADHD medications in children aged <6 years. Diagnostic methods and criteria focusing on recognition of ADHD in preschool children were also surveyed. Results: The DSM-5 describes different manifestations of ADHD in preschool versus school-aged children, but does not list separate criteria by age group. Importantly, behaviors indicative of ADHD in older children may be developmentally appropriate in preschool children. Several behavioral rating scales have been validated in children younger than 6 years of age for assessing ADHD. The Preschool ADHD Treatment Study (PATS) has provided the most extensive efficacy and safety data on methylphenidate (MPH) for ADHD in preschoolers to date, with significant improvement in ADHD symptoms observed with MPH compared with placebo, although adverse event-related discontinuation was higher in PATS compared with studies of MPH for ADHD in school-aged children. Since PATS was conducted, few studies designed to assess ADHD medication effectiveness in preschool children have been published. One article reported significant improvement in ADHD symptoms with MPH (immediate release) versus placebo, two studies showed no difference between MPH and risperidone or MPH plus risperidone in relief of ADHD symptoms, and one study demonstrated the efficacy of atomoxetine versus placebo for ADHD symptoms in preschoolers. Conclusions: Further research is needed on pharmacotherapy for preschool children with ADHD.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets