Skip to main content

ORIGINAL RESEARCH article

Front. Psychiatry
Sec. Adolescent and Young Adult Psychiatry
Volume 15 - 2024 | doi: 10.3389/fpsyt.2024.1467486

A Novel Framework to Predict ADHD Symptoms using Irritability in Adolescents and Young Adults with and without ADHD

Provisionally accepted
Saeedeh Komijani Saeedeh Komijani 1,2*Dipak Ghosal Dipak Ghosal 1,2Manpreet K Singh Manpreet K Singh 3,4,5Julie Schweitzer Julie Schweitzer 3,4,5Prerona Mukherjee Prerona Mukherjee 3,4,5
  • 1 University of California, Davis, Davis, United States
  • 2 School of Engineering, Davis, United States
  • 3 Department of Psychiatry and Behavioral Sciences, Sacramento, United States
  • 4 MIND Institute, School of Medicine, University of California, Davis, Sacramento, California, United States
  • 5 University of California Davis, Sacramento, United States

The final, formatted version of the article will be published soon.

    Background: Attention Deficit Hyperactivity Disorder (ADHD) is a common neurodevelopmental disorder in children and adolescents characterized by persistent patterns of hyperactivity, impulsivity, and inattentiveness. ADHD persists for many into adulthood. While irritability is not a diagnostic symptom of ADHD, temper outbursts and irritable moods are common in individuals with ADHD. However, research on the association between irritability and ADHD symptoms in adolescents and young adults remains limited.Method: Prior research has used linear regression models to examine longitudinal relations between ADHD and irritability symptoms. This method may be impacted by the potential presence of highly colinear variables. We utilized a hierarchical clustering technique to mitigate these collinearity issues and implemented a non-parametric machine learning (ML) model to predict the significance of symptom relations over time. Our data included adolescents (N=148, 54% ADHD) and young adults (N=124, 42% ADHD) diagnosed with ADHD and neurotypical (NT) individuals, evaluated in a longitudinal study.Results: Results from the linear regression analysis indicate a significant association between irritability at time-point 1 (T1) and hyperactive-impulsive symptoms at time-point 2 (T2) in adolescent females (β=0.26, p<0.001), and inattentiveness at T1 with irritability at T2 in young adult females (β=0.49, p<0.05). Using a non-parametric-based approach, employing a Random Forest (RF) method, we found that among both adolescents and young adults, irritability in adolescent females significantly contributes to predicting impulsive symptoms in subsequent years, achieving a performance rate of 86%.Our results corroborate and extend prior findings, allowing for an in-depth examination of longitudinal relations between irritability and ADHD symptoms, namely hyperactivity, impulsivity, and inattentiveness, and the unique association between irritability and ADHD symptoms in females.

    Keywords: ADHD, irritability, adolescents, young adults, symptom prediction, hierarchical clustering, machine learning, random forest

    Received: 20 Jul 2024; Accepted: 27 Dec 2024.

    Copyright: © 2024 Komijani, Ghosal, Singh, Schweitzer and Mukherjee. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Saeedeh Komijani, University of California, Davis, Davis, United States

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.